@inbook{498771,
  author = {Skarnitzl, Radek and Vaňková, Jitka and Bořil, Tomáš},
  editor = {Niebuhr, Oliver and Skarnitzl, Radek},
  title = {{Optimizing the extraction of vowel formants}},
  booktitle = {{Tackling the Complexity in Speech}},
  series = {1st ed},
  year = {2015},
  abstract = {The chapter describes the complexity associated with the analysis of vowel formants in two frequently used software packages: automatic extraction settings are compared with manually verified values.},
  keywords = {formant; vowel; speech acoustics},
  publisher = {{Univerzita Karlova v Praze, Filozofická fakulta}},
  address = {{Praha}},
  isbn = {978-80-7308-558-2},
  pages = {165-182},
  language = {English}
}

@misc{617662,
  author = {Skarnitzl, Radek and Volín, Jan and Bořil, Tomáš and Houzar, Alžběta and Nechanský, Tomáš and Svatošová, Michaela and Nudga, Natalia},
  title = {{The 30th Annual Conference of the International Association for Forensic Phonetics and Acoustics}},
  year = {2022},
  abstract = {The International Association for Forensic Phonetics and Acoustics (IAFPA) is the professional association for forensic scientists and researchers who analyze voices, speech and audio recordings.
  Annual conferences of the association are organized to facilitate the exchange of phonetic and acoustic research, methodology and best practice for the analysis of recordings and interpretation of findings, and any other issues pertinent to the organization's aims.
  The Institute of Phonetics at Charles University's Faculty of Arts in Prague is looking forward to welcoming you to this year's conference, to be held on July 10-13, 2022.},
  keywords = {International conference; Forensic phonetics; Acoustics},
  language = {English}
}

@misc{658696,
  author = {Skarnitzl, Radek and Volín, Jan and Chládková, Kateřina and Bořil, Tomáš and Podlipský, Václav Jonáš and Šturm, Pavel and Hejná, Michaela and Paillereau, Nikola and Šimáčková, Šárka},
  title = {{20th International Congress of Phonetic Sciences 2023 - ICPhS 2023}},
  year = {2023},
  abstract = {The International Congress of Phonetic Sciences (ICPhS) takes place every four years. It is held under the auspices of the International Phonetic Association and provides an interdisciplinary forum for the presentation of basic and applied research in the phonetic sciences. The main areas covered by the Congress are speech production, speech acoustics, speech perception, speech prosody, sound change, phonology, sociophonetics, language typology, first and second language acquisition, forensic phonetics, speaking styles, voice quality, clinical phonetics and speech technology. The last four Congresses were each attended by ca. 1000 participants from all over the world.
  The conference theme for ICPhS 2023 is "Intermingling Communities and Changing Cultures". The last decades have seen an unprecedented increase in mobility and interpersonal contacts which bridge national languages and which impact speech patterns everywhere. Europe is aspiring to become a united community of people who, although they speak many languages, seek mutual understanding. Surrounded by a multitude of languages, people learn the languages and discover various cultures associated with them, both implicitly and with conscious efforts. All these multiple contacts enrich individuals and open promising research potentials.},
  keywords = {Congress; Phonetics; International},
  language = {English}
}

@book{657649,
  author = {Volín, Jan and Šturm, Pavel and Skarnitzl, Radek and Bořil, Tomáš},
  title = {{Prosodic phrase in spoken Czech}},
  series = {1},
  year = {2024},
  abstract = {The book provides a missing source of information on a crucial element in the sound structure of the Czech language, the prosodic phrase. The core of the study is the description of phrases in three genres in terms of their phonetic structure, acoustic properties, and a specific syntactic issue.},
  keywords = {prosody; prosodic phrase; phonetics; Czech},
  publisher = {{Karolinum}},
  address = {{Praha}},
  isbn = {978-80-246-5798-1},
  doi = {10.2307/jj.20558244},
  
  language = {English}
}

@article{198621,
  author = {Bořil, Tomáš and Sovka, Pavel},
  title = {{Autoregressive causal relation: Digital filtering approach to causality measures in frequency domain}},
  journal = {Digital Signal Processing: A Review Journal},
  number = {5},
  year = {2013},
  abstract = {A novel measure of the Autoregressive Causal Relation based on a multivariate autoregressive model is proposed. It reveals the strength of the connections among a simultaneous time series and also the direction of the information flow. It is defined in the frequency domain, similar to the formerly published methods such as: Directed Transfer Function, Direct Directed Transfer Function, Partial Directed Coherence, and Generalized Partial Directed Coherence. Compared to the Granger causality concept, frequency decomposition extends the possibility to reveal the frequency rhythms participating on the information flow in causal relations. The Autoregressive Causal Relation decomposes diagonal elements of a spectral matrix and enables a user to distinguish between direct and indirect causal relations. The main advantage lies in its definition using power spectral densities, thus allowing for a clear interpretation of strength of causal relation in meaningful physical terms. The causal measures can be used in neuroscience applications like the analysis of underlying structures of brain connectivity in neural multichannel time series during different tasks measured via electroencephalography or functional magnetic resonance imaging, or other areas using the multivariate autoregressive models for causality modeling like econometrics or atmospheric physics but this paper is focused on theoretical aspects and model data examples in order to illustrate a behavior of methods in known situations.},
  keywords = {Autoregressive processes; Frequency domain analysis; Brain modeling; Electroencephalography},
  volume = {23},
  issn = {1051-2004},
  doi = {10.1016/j.dsp.2013.04.006},
  pages = {1756-1766},
  language = {English}
}

@article{280111,
  author = {Volín, Jan and Bořil, Tomáš},
  title = {{General and Speaker-Specific Properties of F0 Contours in Short Utterances}},
  journal = {Acta Universitatis Carolinae. Philologica},
  number = {1},
  year = {2013},
  abstract = {This study compares three major quantitative methods of contour analysis with the aim to establish their merit for intonation research. Utterances of 24 speakers (7–9 syllables long) taken from short dialogues were used to see whether general prosodic patterning determined by the intonational grammar of the language and the individual production habits of the speakers can be captured by computational means. The three methods exploited were: k-means clustering (KMC), polynomial regression analysis (PRA), and functional principal component analysis (FPCA). The numerical outputs of the methods are confronted with human perception of the contour in both auditory and visual domains. The results suggest that the observed contour properties are reflected by all three methods reasonably well: phonetically interpretable outcomes can be achieved by each of them. As to speakers’ individual features, KMC seems to be least vulnerable to spurious effects.},
  keywords = {melody of speech; cluster analysis; speaker identity; recognition; fundamental frequency},
  volume = {2014},
  issn = {0567-8269},
  pages = {9-19},
  language = {English}
}

@article{616388,
  author = {Svoboda, Emil and Bořil, Tomáš and Rusz, Jan and Tykalová, T. and Horáková, Dana and Guttmann, C. R. G. and Blagoev, K. B. and Hatabu, H. and Valtchinov, V.},
  title = {{Assessing clinical utility of machine learning and artificial intelligence approaches to analyze speech recordings in multiple sclerosis: A pilot study}},
  journal = {Computers in Biology and Medicine},
  number = {September},
  year = {2022},
  abstract = {Background: An early diagnosis together with an accurate disease progression monitoring of multiple sclerosis is an important component of successful disease management. Prior studies have established that multiple sclerosis is correlated with speech discrepancies. Early research using objective acoustic measurements has discovered measurable dysarthria.Method: The objective was to determine the potential clinical utility of machine learning and deep learning/AI approaches for the aiding of diagnosis, biomarker extraction and progression monitoring of multiple sclerosis using speech recordings. A corpus of 65 MS-positive and 66 healthy individuals reading the same text aloud was used for targeted acoustic feature extraction utilizing automatic phoneme segmentation. A series of binary classification models was trained, tuned, and evaluated regarding their Accuracy and area-under-the-curve.Results: The Random Forest model performed best, achieving an Accuracy of 0.82 on the validation dataset and an area-under-the-curve of 0.76 across 5 k-fold cycles on the training dataset. 5 out of 7 acoustic features were statistically significant.Conclusion: Machine learning and artificial intelligence in automatic analyses of voice recordings for aiding multiple sclerosis diagnosis and progression tracking seems promising. Further clinical validation of these methods and their mapping onto multiple sclerosis progression is needed, as well as a validating utility for English-speaking populations.},
  keywords = {Multiple sclerosis; Dysarthria; Machine learning; Speech acoustics; Phonetics; Technology assessment; Biomedical;},
  volume = {148},
  issn = {0010-4825},
  doi = {10.1016/j.compbiomed.2022.105853},
  pages = {1-9},
  language = {English}
}

@article{617649,
  author = {Volín, Jan and Bořil, Tomáš},
  title = {{Individualita mluvčího v užití základní hlasové frekvence při přednesu básní}},
  journal = {Naše {ř}eč},
  number = {3},
  year = {2022},
  abstract = {Základní frekvence (f0) je považována za významný rys akustické struktury řečového signálu. Cílem naší studie bylo prozkoumat charakteristiky f0 mluvčích při recitaci poezie. Nahráli jsme 24 mluvčích, kteří si připravili a přednesli dvě básně od stejného autora, ale rozdílného charakteru, a to jak po formální, tak po obsahové stránce. Hlavní výzkumnou otázkou bylo, zda se nám podaří najít stabilní charakteristiky mluvčích, které by byly přítomny v obou textech. Související otázka stejného významu se týká identifikace rysů, které se v obou textech trvale liší. Chtěli jsme zjistit, do jaké míry rozdíly ve struktuře a náladě obou básní mění parametry f0 produkované jednotlivými mluvčími. Bylo provedeno šestnáct analýz, z nichž sedm lze považovat za standardní, zatímco devět je méně obvyklých, a proto stojí za prozkoumání. Výsledky naznačují, že různé metody zkoumání mají své přednosti a kombinace přístupů je doporučeníhodná. Nejlépe si v našem vzorku vedly proměnné základní linie f0, trendová linie deklinace a podíl pokračovacích melodémů, které mluvčí používá. Tyto tři charakteristiky jsou prezentovány v 3D zobrazení.},
  keywords = {idiosynkratické rysy; melodém; přednes poezie; spádový trend; základní hlasová frekvence},
  volume = {105},
  issn = {0027-8203},
  pages = {133-150},
  language = {Czech}
}

@article{617651,
  author = {Bořil, Tomáš and Šturm, Pavel and Skarnitzl, Radek and Hévrová, Marie and Köpke, Barbara},
  title = {{The effect of non-conclusive melodic rises on Czech speech sounding French}},
  journal = {Linguistica Pragensia},
  number = {1},
  year = {2022},
  abstract = {This paper is based on a study of first language attrition in Czechs living in France, which reveals that Czech expatriates in France use prominent rises in non-conclusive intonation patterns in their native language. We manipulated the speech of six expatriates by reducing the fundamental frequency (f0) range of non-conclusive rises in a phrase, and the speech of six Czech control speakers by expanding the f0 range to mimic the French-like prominent rises. The manipulations served, alongside filler items, as the basis for a perception test in which 37 native Czech listeners assessed how much the speakers' pronunciation manifested marks of a long-term stay in France. The results confirmed our hypothesis that expanding the control speakers' f0 range would increase the perceived effect of French. However, reducing the f0 range in the expatriate group did not yield lower French-effect ratings, most likely due to the presence of other pronunciation features in their speech.},
  keywords = {cross-linguistic influence; intonation; L1 attrition; non-conclusive melody; speech perception},
  volume = {32},
  issn = {0862-8432},
  doi = {10.14712/18059635.2022.1.7},
  pages = {125-141},
  language = {English}
}

@article{621128,
  author = {Hévrová, Marie and Bořil, Tomáš},
  title = {{Longitudinal study of phonetic drift in L1 speech of late Czech-French bilinguals}},
  journal = {Acta Universitatis Carolinae. Philologica},
  number = {1},
  year = {2022},
  abstract = {This study investigates temporal development of phonetic drift (i.e., when L1 pronunciation is affected by acquiring an L2 language) in the L1 speech of four Czech university students (two female and two male) who went to study in Toulouse as part of the Erasmus programme. Having started studying L2 French at the age of twelve to sixteen, they are considered the so-called Czech-French late bilinguals. The subjects were recorded reading out a Czech text and producing semi-spontaneous speech in three sessions - immediately after their arrival, and then at the end of the first and the third month of their stay in France. Based on acoustic analyses, we statistically evaluated the formant frequencies of vowels, the spectral moments of the fricatives /ɦ/ and /x/, and the production frequency of schwa in the word-final position, which is a distinctive pronunciation feature for Toulouse French. Even though speech and its development are highly individual, we were able to witness certain pronunciation shifts regarding all the examined phones. However, the majority of statistically significant shifts were linked to the formant values of vowels.},
  keywords = {Phonetic drift; Late Czech-French bilinguals; Vowels’ quality; Spectral moments of /ɦ/ and /x/; Schwa in the word-final position},
  volume = {2022},
  issn = {0567-8269},
  doi = {10.14712/24646830.2022.33},
  pages = {131-149},
  language = {English}
}

@article{647525,
  author = {Kocjančič Antolík, Tanja and Bořil, Tomáš and Hofmann, Susanna},
  title = {{Acoustic and Articulatory Visual Feedback in Classroom L2 Vowel Remediation}},
  journal = {Language and Speech},
  number = {May 2024},
  year = {2024},
  abstract = {This paper presents L2 vowel remediation in a classroom setting via two real-time visual feedback methods: articulatory ultrasound tongue imaging, which shows tongue shape and position, and a newly developed acoustic formant analyzer, which visualizes a point correlating with the combined effect of tongue position and lip rounding in a vowel quadrilateral. Ten Czech students of the Swedish language participated in the study. Swedish vowel production is difficult for Czech speakers since the languages differ significantly in their vowel systems. The students selected the vowel targets on their own and practiced in two classroom groups, with six students receiving two ultrasound training lessons, followed by one acoustic, and four students receiving two acoustic lessons, followed by one ultrasound. Audio data were collected pre-training, after the two sessions employing the first visual feedback method, and at post-training, allowing measuring Euclidean distance among selected groups of vowels and observing the direction of change within the vowel quadrilateral as a result of practice. Perception tests were performed before and after training, revealing that most learners perceived selected vowels correctly already before the practice. The study showed that both feedback methods can be successfully applied to L2 classroom learning, and both lead to the improvement in the pronunciation of the selected vowels, as well as the Swedish vowel set as a whole. However, ultrasound tongue imaging seems to have an advantage as it resulted in a greater number of improved targets.},
  keywords = {L2 vowel remediation; real-time visual feedback; ultrasound tongue imaging; formants; Swedish},
  
  issn = {0023-8309},
  doi = {10.1177/00238309231223736},
  pages = {1-22},
  language = {English}
}

@article{657650,
  author = {Nechanský, Tomáš and Houzar, Alžběta and Bořil, Tomáš and Skarnitzl, Radek},
  title = {{Controlled voice quality modifications: Acoustic, perceptual and ASR analysis}},
  journal = {International Journal of Speech, Language and the Law},
  number = {1},
  year = {2024},
  abstract = {The study examines targeted modifications of voice quality, both phonatory and articulatory, in Czech. Acoustic analyses revealed that F3 is relatively stable across various voice quality settings, while harmonicity and spectral slope indicators are sensitive to the phonatory modifications. Pressed phonation turned out to have the greatest effect on all three types of analysis.},
  keywords = {voice quality; voice disguise; phonation; articulation; Czech},
  publisher = {{University of Birmingham Press}},
  address = {{Birmingham}},
  volume = {31},
  issn = {1748-8885},
  doi = {10.1558/ijsll.26094},
  pages = {49-76},
  language = {English}
}


@article{663213,
  author = {Skarnitzl, Radek and Bořil, Tomáš},
  title = {{Training of English prosody with acoustically modified voices}},
  journal = {Journal of Second Language Pronunciation},
  number = {3},
  year = {2024},
  abstract = {The paper describes an innovative training of English phrasal prosody using participants' own speech as models, with their melodic and rhythmic patterns manipulated by means of PSOLA. After the training, the participants were perceived as sounding significantly more competent in the after-training recordings, their phrasing corresponded more to text-based predictions, and their melodic variability was significantly greater.},
  keywords = {prosody; PSOLA manipulation; intonation; visualization; English as a foreign language},
  volume = {10},
  issn = {2215-1931},
  doi = {10.1075/jslp.24041.ska},
  pages = {375-403},
  language = {English}
}

@article{537568,
  author = {Volín, Jan and Bořil, Tomáš},
  title = {{Acoustic correlates of prosodic dimensions in younger and older speakers of Czech}},
  journal = {Acta Universitatis Carolinae. Philologica},
  number = {3},
  year = {2017},
  abstract = {The present study reports phonetic data applicable for diagnostic purposes in voice related pathologies. However, apart from purely physiological concern, linguistic considerations are also acknowledged since the speech material consists of a continuous spoken text. Three age groups of speakers were recorded (young, middle-aged and old adults), each represented by 15 men and 15 women (n = 90). Several measures of fundamental frequency, together with variation in intensity and speech tempo were captured. An appreciably innovative metric, Cumulative Slope Index (CSI), was successfully employed to capture F0 variability in utterances. The results confirm differences between the age groups, but also between men and women, and contribute the normative mapping of the Czech population.},
  keywords = {intonation; aging; diagnostics; articulation rate; fundamental frequency},
  
  issn = {0567-8269},
  doi = {10.14712/24646830.2017.32},
  pages = {45-54},
  language = {English}
}

@article{537570,
  author = {Hruška, Robin and Bořil, Tomáš},
  title = {{Temporal variability of fundamental frequency contours}},
  journal = {Acta Universitatis Carolinae. Philologica},
  number = {3},
  year = {2017},
  abstract = {Intonation is one of the means of performing a speech style. Thus, observing pitch variation in an utterance may be a clue to identifying speech style. We design a cumulative slope (CS) index based upon the amount of pitch variation in a measured F0 contour and the duration of that contour. The more pitch changes there are and the greater their frequency range is, the greater the CS index is. This is confirmed by an experiment we conduct: the CS index of utterances with expressive intonation is higher than that of utterances with neutral intonation, and for utterances with neutral intonation the CS index is higher than for utterances with monotonous or flat intonation. However, as there is a great variability between speakers, the CS index as defined currently, cannot be used to universally differentiate between the styles. Results obtained using automatic voice activity detection (VAD) are close to those obtained with manual VAD and thus the extraction of CS index can be reliably automatized.},
  keywords = {fundamental frequency; melody of speech; stylization; variability of pitch contours},
  
  issn = {0567-8269},
  doi = {10.14712/24646830.2017.31},
  pages = {35-44},
  language = {English}
}

@article{566262,
  author = {Bořil, Tomáš and Skarnitzl, Radek},
  title = {{Discontinuities in fundamental frequency: When do they really matter in synthetic speech?}},
  journal = {Akustické {l}isty},
  number = {1-2},
  year = {2019},
  abstract = {The paper reports a perceptual experiment which aimed at relaxing the criteria for concatenation cost in the domain of fundamental frequency (f0) when concatenating diphones pertaining to voiced consonants. The results suggest that f0 discontinuities only matter in sonorants and only when they exceed 1 semitone. Most importantly, the direction of f0 change should be taken into account.},
  keywords = {voicing; fundamental frequency; concatenative synthesis; concatenation cost},
  volume = {25},
  issn = {1212-4702},
  pages = {4-9},
  language = {English}
}

@article{590101,
  author = {Hejná, Míša and Šturm, Pavel and Tylečková, Lea and Bořil, Tomáš},
  title = {{Normophonic Breathiness in Czech and Danish: Are Females Breathier than Men?}},
  journal = {Journal of Voice},
  number = {3},
  year = {2021},
  abstract = {The present study compares the voice quality of female and male speech in two languages: Czech, a Slavic language, and Danish, a Germanic language. For both languages, the results based on a total of 120 vocally healthy speakers are in line with the claim that females are universally breathier than males. This was supported by the Cepstral Peak Prominence (CPP) and H1*-H2* measures, which are generally known as the most robust correlates of breathiness, and also by the H1*-A3* measure. However, the sex distinction was unsupported or even contradictory when using some other measures suggested to reflect breathiness, which provides an incentive to insist on employing a number of acoustic measures in future voice research. The perceptual component of the study nevertheless suggests that these contradictory findings are due to differences in perceived roughness rather than breathiness, and that CPP and H1*-H2* do reflect breathiness differences, and CPP in particular. We therefore conclude that it is indeed the case that female speakers are breathier than male speakers. Finally, in terms of the two robust measures (CPP and H1*-H2*), no language-specific differences in the magnitude of the effect of sex on breathiness were found.},
  keywords = {Breathiness; Czech; Danish; Phonation; Sex},
  volume = {35},
  issn = {0892-1997},
  doi = {10.1016/j.jvoice.2019.10.019},
  pages = {498.e1-498.e22},
  language = {English}
}

@article{590353,
  author = {Tykalová, Tereza and Škrabal, Dominik and Bořil, Tomáš and Čmejla, Roman and Volín, Jan and Rusz, Jan},
  title = {{Effect of Ageing on Acoustic Characteristics of Voice Pitch and Formants in Czech Vowels}},
  journal = {Journal of Voice},
  number = {6},
  year = {2021},
  abstract = {Background The relevance of formant-based measures has been noted across a spectrum of medical, technical, and linguistic applications. Therefore, the primary aim of the study was to evaluate the effect of ageing on vowel articulation, as the previous research revealed contradictory findings. The secondary aim was to provide normative acoustic data for all Czech monophthongs. Methods The database consisted of 100 healthy speakers (50 men and 50 women) aged between 20 and 90. Acoustic characteristics, including vowel duration, vowel space area (VSA), fundamental frequency (f o), and the first to fourth formant frequencies (F 1-F 4) of 10 Czech vowels were extracted from a reading passage. In addition, the articulation rate was calculated from the entire duration of the reading passage. Results Age-related changes in pitch were sex-dependent, while age-related alterations in F 2/a/, F 2/u/, VSA, and vowel duration seemed to be sex-independent. In particular, we observed a clear lowering of f o with age for women, but no change for men. With regard to formants, we found lowering of F 2/a/ and F 2/u/ with increased age, but no statistically significant changes in F 1, F 3, or F 4 frequencies with advanced age. Although the alterations in F 1 and F 2 frequencies were rather small, they appeared to be in a direction against vowel centralization, resulting in a significantly greater VSA in the older population. The greater VSA was found to be related partly to longer vowel duration. Conclusions Alterations in vowel formant frequencies across several decades of adult life appear to be small or in a direction against vowel centralization, thus indicating the good preservation of articulatory precision in older speakers.},
  keywords = {Aging; Czech; Formant; Vowel; Acoustic analysis; Fundamental frequency},
  volume = {35},
  issn = {0892-1997},
  doi = {10.1016/j.jvoice.2020.02.022},
  pages = {931.e21-931.e33},
  language = {English}
}

@article{621085,
  author = {Nechanský, Tomáš and Bořil, Tomáš and Houzar, Alžběta and Skarnitzl, Radek},
  title = {{The impact of mismatched recordings on an automatic-speaker-recognition system and human listeners}},
  journal = {Acta Universitatis Carolinae. Philologica},
  number = {1},
  year = {2022},
  abstract = {The study explores to what extent an automatic-speaker-recognition system's and the earwitness' ability to identify speakers is influenced when recordings are acquired in different languages and at different times},
  keywords = {forensic voice comparison; mismatch; automatic speaker recognition; voice parade},
  volume = {2022},
  issn = {0567-8269},
  doi = {10.14712/24646830.2022.25},
  pages = {11-22},
  language = {English}
}

@book{500668,
  author = {Skarnitzl, Radek and Bořil, Tomáš and Vaňková, Jitka and Weingartová, Lenka and Volín, Jan and Šturm, Pavel and Hývlová, Dita and Lazárková, Dita and Nechanský, Tomáš and Svobodová, Marie},
  editor = {Skarnitzl, Radek},
  title = {{Fonetická identifikace mluvčího}},
  series = {1. vyd},
  year = {2014},
  abstract = {Publikace se zabývá možnostmi identifikace mluvčího z řečového signálu a zároveň ve vybraných oblastech doplňuje či aktualizuje popis zvukového plánu češtiny.},
  keywords = {identifikace mluvčího; řeč; fonetika; čeština},
  publisher = {{Univerzita Karlova v Praze, Filozofická fakulta}},
  address = {{Praha}},
  isbn = {978-80-7308-548-3},
  
  language = {Czech}
}

@inbook{487257,
  author = {Volín, Jan and Bořil, Tomáš},
  editor = {Skarnitzl, Radek},
  title = {{Základní frekvence v konturách a průbězích}},
  booktitle = {{Fonetická identifikace mluvčího}},
  series = {1. vyd},
  year = {2014},
  abstract = {Kapitola se věnuje průběhům základní frekvence z hlediska využitelnosti pro identifikaci mluvčích, zkoumá parametrizaci pomocí gradientu regresní přímky, koeficientů polynomické regrese a fPCA.},
  keywords = {základní frekvence; identifikace mluvčích; fPCA; fonetika; řeč},
  publisher = {{Univerzita Karlova v Praze, Filozofická fakulta}},
  address = {{Praha}},
  isbn = {978-80-7308-548-3},
  pages = {65-76},
  language = {Czech}
}

@inbook{487258,
  author = {Weingartová, Lenka and Bořil, Tomáš and Vaňková, Jitka},
  editor = {Skarnitzl, Radek},
  title = {{Spektrální sklon}},
  booktitle = {{Fonetická identifikace mluvčího}},
  series = {1. vyd},
  year = {2014},
  abstract = {Kapitola se věnuje spektrálním vlastnostem řeči z hlediska využitelnosti pro identifikaci mluvčích, zabývá se dlouhodobými i krátkodobými ukazateli spektrálního sklonu.},
  keywords = {spektrální sklon; kvalita hlasu; fonační modifikace; identifikace mluvčího; fonetika; řeč},
  publisher = {{Univerzita Karlova v Praze, Filozofická fakulta}},
  address = {{Praha}},
  isbn = {978-80-7308-548-3},
  pages = {77-94},
  language = {Czech}
}

@inbook{487262,
  author = {Vaňková, Jitka and Bořil, Tomáš},
  editor = {Skarnitzl, Radek},
  title = {{Telefonní přenos}},
  booktitle = {{Fonetická identifikace mluvčího}},
  series = {1. vyd},
  year = {2014},
  abstract = {Kapitola se věnuje vlivu telefonního přenosu, především mobilního telefonu, na různé akustické parametry a dopadům pro identifikaci mluvčích.},
  keywords = {telefonní přenos; GSM; identifikace mluvčího; fonetika; řeč},
  publisher = {{Univerzita Karlova v Praze, Filozofická fakulta}},
  address = {{Praha}},
  isbn = {978-80-7308-548-3},
  pages = {104-115},
  language = {Czech}
}

@inbook{487263,
  author = {Bořil, Tomáš and Weingartová, Lenka},
  editor = {Skarnitzl, Radek},
  title = {{Rozhodování a statistika}},
  booktitle = {{Fonetická identifikace mluvčího}},
  series = {1. vyd},
  year = {2014},
  abstract = {Kapitola představuje současné standardy v rozhodování a statistice ve forenzně fonetické praxi.},
  keywords = {statistika; Bayesovská pravděpodobnost; identifikace mluvčího; fonetika; řeč},
  publisher = {{Univerzita Karlova v Praze, Filozofická fakulta}},
  address = {{Praha}},
  isbn = {978-80-7308-548-3},
  pages = {116-135},
  language = {Czech}
}

@inbook{583194,
  author = {Veroňková, Jitka and Bořil, Tomáš and Palková, Zdenka and Poukarová, Petra},
  title = {{Délka českých samohlásek u polských mluvčích v taktech s různou strukturou kvantity}},
  booktitle = {{Area Slavica 3 (Jazyk na hranici – hranice v jazyku)}},
  series = {1. vyd},
  year = {2020},
  abstract = {Příspěvek je součástí širšího výzkumu věnovaného problematice osvojování češtiny ve funkci L2 u skupin mluvčích s různým L1. Jedním ze strukturních jevů, který v rovině zvukové stavby činí potíže nerodilým mluvčím, je kvantita vokálů. Uvádíme několik poznatků sondy zaměřené na výkon rodilých mluvčích polštiny. Na bázi souboru šestislabičných sekvencí hledáme aspekty s potenciálním vlivem na obtížnost realizace kvantity. Kontrolován je jednak počet krátkých a dlouhých vokálů v sekvenci, jednak způsob rozložení sekvence do dvou slov (taktů). Zdá se, že ten ovlivňuje realizaci dlouhých vokálů více. Slovo (takt) je výchozí jednotkou realizace, následně záleží na umístění délek. Chybovost výrazně zvyšuje výskyt dvou délek za sebou.},
  keywords = {;čeština; čeština jako cizí jazyk; polština; kvantita vokálů; fonologická opozice; slovo; mluvní takt},
  publisher = {{Ostravská univerzita, Filozofická fakulta}},
  address = {{Ostrava}},
  isbn = {978-80-7599-180-5},
  pages = {51-61},
  language = {Czech}
}

@misc{498759,
  author = {Vaňková, Jitka and Bořil, Tomáš and Skarnitzl, Radek},
  title = {{Stability of short-term voice quality parameters in GSM}},
  year = {2014},
  abstract = {Voice quality parameters have not been investigated to a great extent in technical speaker identification tasks, in spite of the fact that forensic phoneticians appear to make rather frequent use of voice quality in their casework (Nolan, 2005; Gold & French, 2011). The main reason for the lack of acoustic investigations appears to be the fact that the presence of especially laryngeal voice quality features is compromised in telephone speech (Nolan, 2005). In addition, the plasticity of our voice production mechanism allows for great stylistically conditioned variability, and it is mostly voice quality which is affected. Yet we believe that there still is space for acoustic examinations of speaker specificity of voice quality, especially of its short-term correlates which reflect spectral slope by comparing the amplitudes of various events in the acoustic spectrum (Hanson et al., 2001). The motivation for using the parameters H1*-H2*, H1*-A1*, H1*-A2*, H1*-A3* and H2*-H4* is twofold: first, it appears that some of them yield favourable rates of intra-speaker stability and inter-speaker variability (Vaňková and Skarnitzl, 2014); second, low frequencies relevant for H1 are actually not filtered out by the Adaptive Multi-Rate (AMR) codec, which is the current standard in mobile telephony (Guillemin and Watson, 2008; Vaňková and Bořil, submitted).},
  language = {English}
}

@misc{607687,
  author = {Nechanský, Tomáš and Bořil, Tomáš and Růžičková, Alžběta and Skarnitzl, Radek and Skořepa, Vojtěch},
  title = {{The effect of language and temporal mismatch on LTF and ASR analyses}},
  year = {2021},
  abstract = {Forensic phoneticians, when identifying a speaker, encounter various cases differing in complexity and typicality. Non-contemporary (e.g., Hollien and Schwartz, 2001), disguised (e.g., Eriksson, 2010; Künzel, 2000; Masthoff, 1996) or language- or accent-mismatched recordings are very likely the more complex and less frequent ones. The aim of this study is to present rather an underresearched area in forensic speaker comparison (FSC), namely, the comparison of native-language and contemporary/non-contemporary recordings of speech produced in a foreign language by the same speaker. This setting simulates two hypothetical situations. The unknown speaker during the perpetration of a crime uses his L2; however, the suspect recording, obtained either immediately after, or considerably later, is in the speaker’s mother tongue. In case it is the police that record the suspect, they are likely to ask the speaker to produce speech textually identical to that of the unknown speaker (e.g., Rogers, 1998). There are several studies dealing with foreign accent in FSC; however, they report on foreign accent imitation (Torstensson et al., 2004), listeners’ ability to identify authentic foreign accents (Neuhauser and Simpson, 2007; Sullivan and Schlichting, 2000), or to what degree non-native language background helps witness experts identify a speaker of another language (Schiller at al. 1997). Nevertheless, we are aiming at situations when the suspect recording is for instance wiretapped, and thus it is not possible to ensure textual identity; nor does the speaker attempt to disguise their voice. Our database comprises a hundred Czech speakers (78 females and 22 males) aged 20–25. All speakers were studying English at university at the time of recording, which took place in a sound-treated recording studio at the Institute of Phonetics, Charles University. We investigate three recording sessions. In October (henceforward referred to as O), the speakers read a phonetically rich Czech text (L1) and a piece of BBC news in English (L2). Four months later in January, the same students were recorded reading the same English text again (referred to as J). On average, each participant produced ca. 1 minute of speech in Czech, and 3+3 minutes in English. We performed the analysis of long-term formant distributions (LTF; Nolan and Grigoras, 2005). A secondary aim was to compare the performance of LTF data originating only from vowels and from all voiced segments: these two types of “vocalic stream” were obtained automatically using a script in the Praat Vocal Toolkit (Corretge, 2020). We then used a Praat script (Boersma and Weenink, 2020) to extract the first three formants (using the “robust” settings for male and female speakers) and plotted histograms in 25-Hz bins. Since all the speakers are known, but were recorded under three conditions, for each speaker we plan to compare the following condition pairs as if they were the unknown and suspect recordings: O-L1+O-L2 (contemporary pair, language mismatch); O-L2+J-L2 (non-contemporary pair, language match); O-L1+J-L2 (non-contemporary pair, language mismatch). LTF distributions will then be compared across the different conditions. As mentioned above, we are also interested in finding whether “vocalic streams” are more speaker-specific when extracted from vowels only or from all voiced frames. In addition, we have conducted speaker comparisons in VOCALISE (Oxford Wave Research, 2019a) using the i-vector PLDA framework, with the i-vector PLDA scores calibrated using cross-validation in the Bio-Metrics software (Oxford Wave Research, 2019b). Preliminary analyses of the ASR-based results suggest very good performance in single mismatch conditions (i.e., only temporal, or only language), with EERs of around 1%, but a much higher EER of 7.5% in double mismatch conditions.},
  keywords = {forensic phonetics; long-term formant distributions; i-vector PLDA framework},
  language = {English}
}

@inproceedings{518086,
  author = {Bořil, Tomáš and Skarnitzl, Radek},
  title = {{Tools rPraat and mPraat: Interfacing Phonetic Analyses with Signal Processing}},
  booktitle = {{Text, Speech, and Dialogue: 19th International Conference, TSD 2016, Brno, Czech Republic, September 12-16, 2016, Proceedings}},
  series = {1st ed},
  year = {2016},
  abstract = {The paper presents the rPraat package for R/mPraat toolbox for Matlab which constitutes an interface between the most popular software for phonetic analyses, Praat, and the two more general programmes. The package adds on to the functionality of Praat, it is shown to be superior in terms of processing speed to other tools. The use of the tool is demonstrated on a comparison of real speech data with synthetic speech.},
  keywords = {Matlab; R; Praat; Phonetics; Speech synthesis},
  publisher = {{Springer International Publishing}},
  address = {{Cham}},
  isbn = {978-3-319-45510-5},
  doi = {10.1007/978-3-319-45510-5_42},
  pages = {367-374},
  language = {English}
}

@inproceedings{592401,
  author = {Palková, Zdenka and Bořil, Tomáš and Veroňková, Jitka},
  title = {{Difficulties in adjacent vowel length of L1 Russian speakers in Czech}},
  booktitle = {{ExLing 2020}},
  series = {1st ed},
  year = {2020},
  abstract = {The sound category of the vowel quantity is applied in the structure of languages in different ways, and its adaptation from one system to another is difficult. The subject of the paper is the difficulties Russian speakers have in the production of Czech texts with more long vowels in a row, i.e., in a situation that does not exist in Russian. Sample of Czech created for the purpose of the experiment and recorded by Russian and Czech native speakers serve as the basis. The success in the realization of quantity in Russian speakers as assessed by Czech native listeners was monitored, and the duration values of short and long vowels and their ratio in the speech of Russian and Czech speakers were compared.},
  keywords = {Czech as L2; Russian as L1; vowel length; perception; word},
  publisher = {{ExLing Society}},
  address = {{Athens, Greece}},
  isbn = {978-618-84585-1-2},
  issn = {2529-1092},
  doi = {10.36505/ExLing-2020/11/0037/000452},
  pages = {149-152},
  language = {English}
}

@inproceedings{658256,
  author = {Skarnitzl, Radek and Bořil, Tomáš},
  title = {{Training English prosody with manipulated voices: Can both intermediate and advanced learners benefit?}},
  booktitle = {{Proceedings of the 5th International Symposium on Applied Phonetics}},
  series = {1},
  year = {2024},
  abstract = {The paper reports on a short prosody-focused training, where participants' own PSOLA-modified speech was used as model. The individualized training was delivered to six intermediate and six advanced Czech speakers of English. Both groups benefitted from the training, particularly with their melodic variability significantly greater.},
  keywords = {phrasing; melody; rhythm; prosody manipulations; learner proficiency},
  publisher = {{ISCA}},
  address = {{Tartu, Estonsko}},
  isbn = {0-000-00000-0},
  doi = {10.21437/ISAPh.2024-18},
  pages = {94-99},
  language = {English}
}

@inproceedings{530366,
  author = {Bořil, Tomáš and Šturm, Pavel and Skarnitzl, Radek and Volín, Jan},
  title = {{Effect of formant and F0 discontinuity on perceived vowel duration: Impacts for concatenative speech synthesis}},
  booktitle = {{Proceedings of the 18th Annual Conference of the International Speech Communication Association (INTERSPEECH 2017)}},
  series = {1st ed},
  year = {2017},
  abstract = {This study investigates the effect of F0 and formant discontinuities on the perceived duration of vowels in Czech synthetic speech.},
  keywords = {concatenative synthesis; fundamental frequency; formants; vowel duration},
  publisher = {{International Speech Communication Association}},
  address = {{Stockholm}},
  isbn = {0-000-00000-0},
  issn = {2308-457X},
  doi = {10.21437/Interspeech.2017-1161},
  pages = {2998-3002},
  language = {English}
}

@inproceedings{537566,
  author = {Volín, Jan and Tykalová, Tereza and Bořil, Tomáš},
  title = {{Stability of prosodic characteristics across age and gender groups}},
  booktitle = {{Proceedings of the 18th Annual Conference of the International Speech Communication Association (INTERSPEECH 2017)}},
  series = {1st ed},
  year = {2017},
  abstract = {Our study provides data for the population of adult speakers of Czech - a West Slavic language of Central Europe. The sample consists of six age groups (20 to 80 years of age) with balanced representation of gender. The search for age and gender related attributes covered both global acoustic descriptors and linguistically informed prosodic feature extraction.},
  keywords = {speech prosody; intonation; aging; gender; cluster analysis; Legendre polynomials},
  publisher = {{International Speech Communication Association}},
  address = {{Stockholm}},
  isbn = {0-000-00000-0},
  issn = {2308-457X},
  doi = {10.21437/Interspeech.2017-1503},
  pages = {3902-3906},
  language = {English}
}

@inproceedings{547891,
  author = {Kaiser, Jitka and Bořil, Tomáš},
  title = {{Impact of the GSM AMR Codec on Automatic Vowel Formant Measurement in Praat and VoiceSauce}},
  booktitle = {{41st International Conference on Telecommunications and Signal Processing (TSP)}},
  series = {1st ed},
  year = {2018},
  abstract = {Automatic formant measurement is generally reliable but can be affected by various factors, such as telephone transmission. As forensic speaker identification often involves comparison of direct (face-to-face) speech with a telephone recording, it is necessary to examine what effect telephony has on the speech signal. This study focuses on the impact of the AMR codec - this codec being the standard in mobile telephony - on formants. In comparison with previous studies, our study analyses the impact of both versions of the codec (narrowband and wideband) at all possible bit rates and on a large amount of data. Furthermore, the effect was examined in two processing tools - Praat and VoiceSauce. Our results revealed considerable shifts of formants when compressed by the codec and indicate that the extent of the shifts differs not only for individual formants but also for the two genders, vowel qualities and the software used.},
  keywords = {automatic extraction; formants; GSM AMR codec; speech coding; telephone transmission},
  publisher = {{IEEE}},
  address = {{Brno, Czech Republic}},
  isbn = {978-1-5386-4695-3},
  doi = {10.1109/TSP.2018.8441185},
  pages = {409-412},
  language = {English}
}

@inproceedings{589654,
  author = {Hévrová, Marie and Bořil, Tomáš and Köpke, Barbara},
  title = {{Phonetic Attrition in Vowels' Quality in L1 Speech of Late Czech-French Bilinguals}},
  booktitle = {{Text, Speech, and Dialogue 23rd International Conference, TSD 2020, Brno, Czech Republic, September 8–11, 2020, Proceedings}},
  series = {1st ed},
  year = {2020},
  abstract = {This study examines phonetic attrition of the first language (L1) affected by second language (L2) in Czech speakers living in Toulouse (late Czech-French bilinguals - CF). We compared the production of vowels by 13 CF and 13 Czech monolinguals living in the Central Bohemian Region (C). CF had been living in France for at least one year and started to learn French when they were more than 6 years old. Both C and CF were speakers of Common Czech. We recorded their production in reading task and semi-spontaneous speech and performed measurements of vowel formants. Results show a statistically significant difference between F1 of CF [a Open image in new window ] and F1 of C [a Open image in new window ], and between F3 of CF [i Open image in new window ] and F3 of C [i Open image in new window ]. These findings are discussed in relation to the perceptual approach suggesting that several vowels can be perceived as different in C and CF production.},
  keywords = {Phonetic attrition;Vowels’ quality;Late Czech-French bilinguals},
  publisher = {{Springer}},
  address = {{Cham}},
  isbn = {978-3-030-58323-1},
  doi = {10.1007/978-3-030-58323-1_38},
  pages = {348-355},
  language = {English}
}

@inproceedings{589691,
  author = {Veroňková, Jitka and Bořil, Tomáš},
  title = {{Czech vowel quantity in Polish speakers as perceived by Moravian-Silesian listeners}},
  booktitle = {{Speech Research conference. Beszédkutatás konferencia}},
  series = {1st ed},
  year = {2020},
  abstract = {The vowel quantity in Czech is a difficult phenomenon for foreign-speaking speakers. The probe focuses on the perceptual evaluation of Czech vowels' length in speakers with mother tongue Polish. The material is read sentences with an ambiguous context, which form the basis of the perception test. The listeners' group comes from the Ostrava region, a region bordering Poland whose dialect contains some features identical or similar to Polish.},
  keywords = {Czech as L2; Vowel length; Duration; Formants; Intelligibility; Foreign accent; Perception},
  publisher = {{Hungarian Research Institute for Linguistics. Budapest}},
  address = {{Budapest}},
  isbn = {0-000-00000-0},
  doi = {10.18135/BeszKutKonf.2020},
  pages = {89-91},
  language = {English}
}

@inproceedings{589692,
  author = {Bořil, Tomáš and Veroňková, Jitka},
  title = {{Perceived length of Czech high vowels in relation to formant frequencies evaluated by automatic speech recognition}},
  booktitle = {{Text, Speech, and Dialogue 23rd International Conference, TSD 2020, Brno, Czech Republic, September 8–11, 2020, Proceedings}},
  series = {1st ed},
  year = {2020},
  abstract = {Recent studies measured significant differences in formant values in the production of short and long high vowel pairs in the Czech language. Perceptional impacts of such findings were confirmed employing listening tests proving that a perceived vowel length is influenced by formant values related to a tongue position. Non-native speakers of Czech may experience difficulties in communication when they interchange the vowel length in words, which may lead to a completely different meaning of the message. This paper analyses perception of two-syllable words with manipulated duration and formant frequencies of high vowels i/i: or u/u: in the first syllable using automatic speech recognition (ASR) system. Such a procedure makes it possible to set a fine resolution in the range of examined factors. Our study confirms the formant values have a substantial impact on the perception of high vowels' length by ASR, comparable to mean values obtained from listening tests performed on a group of human participants.},
  keywords = {High Czech vowels; Vowel length; Vowel quality; Automatic speech recognition; Perception},
  publisher = {{Springer}},
  address = {{Cham}},
  isbn = {978-3-030-58323-1},
  doi = {10.1007/978-3-030-58323-1_44},
  pages = {409-417},
  language = {English}
}

@inproceedings{589694,
  author = {Veroňková, Jitka and Bořil, Tomáš},
  title = {{Phonological Length of L2 Czech Speakers' Vowels in Ambiguous Contexts as Perceived by L1 Listeners}},
  booktitle = {{Speech and Computer, 22nd International Conference, SPECOM 2020}},
  series = {1st ed},
  year = {2020},
  abstract = {The paper focuses on the vowel length of non-native speakers' Czech and their perception by native speakers. Due to its phonological status, the length of vowels in Czech is an important sound feature. Its improper realization can result in communication breakdown. From the Czech read speech of 8 Russian and Ukrainian female speakers, a perception test was created: 78 items consisting of 5 pairs and 1 triad of the same sentences that differed only in the target word. These two-syllable words were distinguished by a combination of short/long vowels, e.g., /lanu/ - /la:nu/, /la:nu/ - /la:nu:/. The L1 Czech listeners rated the degree of the foreign accent of the items and intelligibility of the target words. The agreement of listeners with the speakers' intent is evaluated, and the types of substitutions are analyzed in particular with respect to the combination of short/long vowel and the position of a stressed/unstressed syllable. The vowel duration and the formants of i-vowels were measured. In the second perception experiment, durations of both vowels in /lanu/ were manipulated in the range from 60 ms to 240 ms and native Czech speakers rated their perceived length.},
  keywords = {Czech as L2; Vowel length; Duration; Formants; Intelligibility; Foreign accent; Perception},
  publisher = {{Springer}},
  address = {{Cham}},
  isbn = {978-3-030-60276-5},
  issn = {1611-3349},
  doi = {10.1007/978-3-030-60276-5_60},
  pages = {624-635},
  language = {English}
}

@inproceedings{607061,
  author = {Volín, Jan and Bořil, Tomáš},
  title = {{Four Approaches to Extracting Gradient of Intonation Downtrends in Czech}},
  booktitle = {{2021 44TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP)}},
  year = {2021},
  abstract = {Linguistic descriptions of speech often exclude the concept of naturalness since they usually focus on ideal forms. As a consequence, they sometimes miss essential features of speech structure which not only contribute to its natural sound, but also support the coding of the meaning. That is the case of intonation downtrends, which received the deserved level of attention only relatively recently. However, there are still uncertainties concerning the methodology of their quantification. The present study evaluates four different approaches across two prosodic domains and two speech genres. We processed over 2400 prosodic phrases and over 850 declination units produced by 24 speakers. The chief objective was to map behavior of downtrends in Czech spoken texts, and suggest a suitable method of their quantification facilitating future cross-linguistic comparisons. Moreover, reference data are provided on intonation downtrends for Czech, a West Slavic language of Central Europe.},
  keywords = {declinaton; downtrend; fundamental frequency; prosodic phrase; speech unit},
  publisher = {{IEEE}},
  address = {{NEW YORK}},
  isbn = {978-1-66542-933-7},
  doi = {10.1109/TSP52935.2021.9522643},
  pages = {204-207},
  language = {English}
}

@inproceedings{607080,
  author = {Hévrová, Marie and Köpke, Barbara and Bořil, Tomáš},
  title = {{Perception of L1 Speech of late Czech-French Bilinguals by Czech Monolinguals}},
  booktitle = {{Propuestas en fonética experimental: enfoques metodológicos y nuevas tecnologías}},
  series = {1st ed},
  year = {2022},
  abstract = {This study examines the perception of L1 speech of 14 late Czech-French bilinguals who have been living in France for at least two months by Czech monolinguals. We wanted to know whether native speakers judge the L1 production of late Czech-French bilinguals differently from the L1 production of Czech monolingual. The perceptual experiment involved samples taken from L1 production of the bilinguals and Czech monolinguals in a reading task and a semi-spontaneous speech task and was submitted to 17 Czech students of phonetics in the Charles University in Prague. The results show a significant difference between the perception of L1 speech of bilinguals and monolinguals and between the two production tasks.},
  keywords = {L1 attrition; cross-linguistic influence; perception; late Czech-French bilinguals},
  publisher = {{Universitat de Girona. Servei de Publicacions}},
  address = {{Girona, Spain}},
  isbn = {978-84-8458-590-9},
  pages = {127-131},
  language = {English}
}

@misc{498754,
  author = {Vaňková, Jitka and Bořil, Tomáš and Skarnitzl, Radek},
  title = {{Stability of short-term voice quality parameters in GSM}},
  journal = {Proceedings of IAFPA 2014},
  series = {1st ed},
  year = {2014},
  abstract = {Voice quality parameters have not been investigated to a great extent in technical speaker identification tasks, in spite of the fact that forensic phoneticians appear to make rather frequent use of voice quality in their casework (Nolan, 2005; Gold & French, 2011). The main reason for the lack of acoustic investigations appears to be the fact that the presence of especially laryngeal voice quality features is compromised in telephone speech (Nolan, 2005). In addition, the plasticity of our voice production mechanism allows for great stylistically conditioned variability, and it is mostly voice quality which is affected. Yet we believe that there still is space for acoustic examinations of speaker specificity of voice quality, especially of its short-term correlates which reflect spectral slope by comparing the amplitudes of various events in the acoustic spectrum (Hanson et al., 2001). The motivation for using the parameters H1*-H2*, H1*-A1*, H1*-A2*, H1*-A3* and H2*-H4* is twofold: first, it appears that some of them yield favourable rates of intra-speaker stability and inter-speaker variability (Vaňková and Skarnitzl, 2014); second, low frequencies relevant for H1 are actually not filtered out by the Adaptive Multi-Rate (AMR) codec, which is the current standard in mobile telephony (Guillemin and Watson, 2008; Vaňková and Bořil, submitted).},
  publisher = {{IAFPA}},
  address = {{Curych, Švýcarsko}},
  volume = {2014},
  pages = {75-76},
  language = {English}
}

@inproceedings{637657,
  author = {Svatošová, Michaela and Bořil, Tomáš},
  editor = {Skarnitzl, Radek and Volín, Jan},
  title = {{Duration as a cue for phonological voicing contrast in whispered Czech}},
  booktitle = {{20th International Congress of Phonetic Sciences (ICPhS)}},
  year = {2023},
  abstract = {In Czech, the phonological contrast of voicing is primarily realized by the presence or absence of the fundamental frequency. However, this main correlate is missing in whisper, because the vocal folds do not vibrate. The present study explored the acoustical and perceptual side of this phonological contrast. Firstly, it compared the duration of voicing counterparts of Czech plosives and fricatives embedded in modal and whispered pseudowords. The duration of voicing counterparts differed significantly, but the durational ratios were smaller in whisper than in modal phonation. Secondly, a perception experiment was created from the whispered stimuli, assessing the recognisability of whispered obstruents in phonetic context only. Listeners recognised many obstruents especially in the medial position, but substantial variability between individual voicing pairs was found.},
  keywords = {phonological voicing; whisper; Czech; perception; duration},
  publisher = {{Guarant International}},
  address = {{Prague, Czech Republic}},
  volume = {2023},
  isbn = {978-80-908114-2-3},
  pages = {1741-1745},
  language = {English}
}

@article{677097,
  author = {Šebek, Jan and Bořil, Tomáš},
  title = {{Perceptual evaluation of the effect of external radiotherapy in the neck area on changes of voice and the voice quality of Czech patients}},
  journal = {Acta Universitatis Carolinae. Philologica},
  number = {3},
  year = {2025},
  abstract = {This research is focused on changes of voice and the voice quality before radiotherapy treatment and in time of one year after external radiotherapy (RT) in the neck area of Czech patients and to compare measurement for different subgroups of patients (by age, gender, surgical resection, aphonia, etc.). The perceptual test was performed on 16 patients undergoing external radiotherapy in the neck area and the changes of voice and the voice quality compared at before RT and 1, 6 and 12 months after RT. 2 clinicians and 1 trained voice specialist evaluated GIRBAS parameters of the voice quality and 96 lay listeners evaluated the scope of change of voice. The results of perceptual tests of lay listeners point to the difference of change in voice is the most pronounced in patients who had aphonia during the RT. Of the GIRBAS parameters, instability and roughness changed the most after RT treatment.},
  keywords = {changes of voice; voice quality; perceptual test; GIRBAS parameters; radiotherapy treatment; Czech patients},
  publisher = {{Univerzita Karlova v Praze, Nakladatelství Karolinum}},
  volume = {2025},
  issn = {0567-8269},
  doi = {10.14712/24646830.2025.19},
  pages = {33-42},
  language = {English}
}

@inproceedings{637625,
  author = {Hanžlová, Adléta and Bořil, Tomáš},
  editor = {Skarnitzl, Radek and Volín, Jan},
  title = {{A perceptual and acoustic study of melody in whispered Czech words}},
  booktitle = {{20th International Congress of Phonetic Sciences (ICPhS)}},
  year = {2023},
  abstract = {The perception of melody in speech depends mainly on the fundamental frequency (f0) which reflects vocal fold oscillation speed. Whisper is defined by the absence of phonation and therefore the lack of f0. Intended melody in whisper, however, seems to be discernible regardless.
  This paper presents a perception experiment assessing the discernibility of melody in whispered Czech words and words sung in whisper, which proved that melody in whisper in certain cases can in fact be discerned, along with an acoustical analysis of the effect of intended melody in whisper on formant frequencies, formant to formant ratios, center of gravity (CoG) and spectral slope. The parameters affected by intended melody in whispered speech were F2 and CoG of stopband filtered signal with main formant bandwidths removed. In words sung in whisper, the affected parameters were F2, F3, F2:F1 and F3:F2 ratios, CoG and spectral slope.},
  keywords = {whisper; melody; absence of phonation; acoustic correlates of intonation; pitch perception},
  publisher = {{Guarant International}},
  address = {{Prague, Czech Republic}},
  volume = {2023},
  isbn = {978-80-908114-2-3},
  pages = {669-673},
  language = {English}
}

@article{BorilElektrorevue2010,
  author = {Bo{\v r}il, Tom{\'a}{\v s} and Sovka, Pavel},
  journal = {Elektrorevue},
  number = {126},
  pages = {1--6},
  title = {Metody pro anal{\'y}zu kauz{\'a}ln{\'i}ch vztah{\r{u}} v {{EEG}}},
  year = {2010},
  issn = {ISSN 1213-1539}
}

@inproceedings{BorilEusipco2011,
  author = {Bo{\v r}il, Tom{\'a}{\v s}  and Sovka, Pavel},
  booktitle = {19th {E}uropean Signal Processing Conference {{(EUSIPCO 2011)}}},
  pages = {1539--1543},
  title = {System interpretation of causality measures in frequency domain used in {{EEG} analysis}},
  year = {2011},
  publisher = {{EURASIP}},
  issn = {2076-1465}
}

@inproceedings{boril_sovka_2010,
  author = {Bo{\v r}il, Tom{\'a}{\v s} and Sovka, Pavel},
  title = {{Performance study of causality measures}},
  booktitle = {{Technical Computing Bratislava 2010}},
  year = {2010},
  address = {{Bratislava}},
  publisher = {{RT systems, s.r.o.}},
  pages = {1--5}
}


@inproceedings{boril2010a,
  author = {Bo{\v r}il, Tom{\'a}{\v s}},
  booktitle = {{Technical Computing Bratislava 2010}},
  pages = {1--4},
  title = {{The use of Matlab and Simulink in signal and system theory course}},
  year = {2010},
  address = {{Bratislava}},
  publisher = {{RT systems, s.r.o.}}
}


@inproceedings{boril2010b,
  author = {Bo{\v r}il, Tom{\'a}{\v s}},
  booktitle = {{ Analýza a zpracování řečových a biologických signálů – sborník prací 2010}},
  pages = {9--13},
  title = {{Multivariate autoregressive modelling of causal connections in EEG}},
  year = {2010},
  address = {{Praha}},
  publisher = {{České vysoké učení technické v Praze}}
}


@inproceedings{boril2009a,
  author = {Bo{\v r}il, Tom{\'a}{\v s}},
  booktitle = {{Proceedings of the 8th Czech-Slovak Conference Trends in Biomedical Engineering}},
  pages = {1--4},
  title = {{Toolkit for EASYS2 EEG data format processing in Matlab, EEGLAB and sLoreta environment}},
  year = {2009},
  address = {{Bratislava}},
  publisher = {{Slovak University of Technology in Bratislava}}
}


@inproceedings{boril2009b,
  author = {Bo{\v r}il, Tom{\'a}{\v s}},
  booktitle = {{13th International Student Conference on Electrical Engineering}},
  pages = {1--4},
  title = {{Revealing of Relations in EEG via Granger Causality}},
  year = {2009},
  address = {{Prague}},
  publisher = {{CTU, Faculty of Electrical Engineering}}
}

@inproceedings{boril_sovka_2009,
  author = {Bo{\v r}il, Tom{\'a}{\v s} and Sovka, Pavel},
  title = {{Active brain centres selection for function connection analysis}},
  booktitle = {{Technical Computing Prague 2009}},
  year = {2009},
  address = {{Prague}},
  publisher = {{{HUMUSOFT}}},
  pages = {18--21}
}

@inproceedings{boril2009c,
  author = {Bo{\v r}il, Tom{\'a}{\v s}},
  booktitle = {{Analýza a zpracování řečových a biologických signálů – sborník prací 2009}},
  pages = {30--37},
  title = {{Grangerova kauzalita a EEG}},
  year = {2009},
  address = {{Praha}},
  publisher = {{České vysoké učení technické v Praze}}
}

@inproceedings{boril_sovka_2008,
  author = {Bo{\v r}il, Tom{\'a}{\v s} and Sovka, Pavel},
  title = {{Performance study of bivariate granger causality}},
  booktitle = {{Digital Technologies 2008}},
  year = {2008},
  address = {{Žilina}},
  publisher = {{{University of Žilina, Faculty of electrical engineering}}},
  pages = {1--4}
}

@inproceedings{hyk_lrec2006,
  author = {Bo{\v r}il, Hynek and Bo{\v r}il, Tom{\'a}{\v s} and Poll\'{a}k, Petr},
  title = {Methodology of {L}ombard Speech Database Acquisition: {E}xperiences with {{CLSD}}},
  booktitle = {Proc. of {{LREC} 2006 -- 5th Conference on Language Resources and Evaluation}},
  month = {May},
  year = {2006},
  address = {{G}enova, {{I}taly}},
  pages = {1644--1647}
}

@inproceedings{hyk_radioelektronika2005,
  author = {Bo{\v r}il, Hynek and Bo{\v r}il, Tom{\'a}{\v s} and Poll\'{a}k, Petr},
  title = {{Design of Lombard effect speech database}},
  booktitle = {{Proceedings of Radioelektronika 2005}},
  year = {2005},
  address = {{Brno}},
  pages = {1--4}
}