@misc{656539,
  author = {Hanžlová, Adléta and Volín, Jan},
  title = {{Phonetic grounding of vocal skills development courses focused on public speaking, stage speech and singing at Czech universities}},
  journal = {PEVoC 15 Abstracts Book},
  year = {2024},
  abstract = {Phonetic knowledge can usefully inform vocal skills development. However, many voice professionals in the Czech Republic do not come from a phonetic-based education. The purpose of this study, therefore, was to examine literature used in university courses focused on vocal skills development in three fields - public speaking, stage speech and singing - as to their phonetic grounding. The aim was to establish the main themes in university courses and evaluate to which extent the methods presented are informed by phonetic knowledge in five operational domains - fundamental frequency, sound spectrum, amplitude, temporal characteristics and articulation.

  Twenty publications (at least 6 in each field) were chosen from university curricula. Based on recurring themes across the publications, a set of categories was identified for each of the fields examined, into which the publications' contents were sorted. Relevant categories were then assessed in terms of awareness of the phonetic domains (above). Publications of all fields referenced phonetic domains, however, the extent to which the domains were presented varied.

  Public speaking publications focused mainly on elocution and orthoepy, thus drawing mainly on knowledge of the phonetic articulatory domain. Other domains were referenced in sections focused on intonation (fo), loudness (amplitude), rhythm and speech tempo (t) and voice resonance (spectrum). However, the publications showed varying degrees of knowledge in these domains, some of them only acknowledging all prosodic properties jointly as "voice modulation".

  Publications on stage speech paid attention to the articulatory domain along with other topics such as voice resonance and timbre (spectrum), intonation and pitch (fo) speech tempo and rhythm (t) or loudness (amplitude). Interestingly, about half of the publications were prevalently focused on elocution, while others focused mainly on the other topics mentioned, one omitting the articulatory domain entirely.

  Singing publications addressed phonetic domains in various topics such as articulation, voice range (fo), voice resonance (spectrum) or dynamics (amplitude). The temporal domain was discussed only very scarcely. Many topics and subtopics (e.g. voice registers) focused on multiple phonetic domains at once. Discussion of the spectral domain was more prevalent than in the other two fields, and most publications showed a satisfactory phonetic knowledge base.},
  keywords = {vocal skills; public speaking; singing voice; stage speech; phonetic domains},
  address = {{Santander}},
  pages = {230-230},
  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}
}

@inproceedings{642198,
  author = {Hanžl, Václav and Hanžlová, Adléta},
  editor = {Skarnitzl, Radek and Volín, Jan},
  title = {{Prak: An automatic phonetic alignment tool for Czech}},
  booktitle = {{20th International Congress of Phonetic Sciences (ICPhS)}},
  year = {2023},
  abstract = {Labeling speech down to the identity and time boundaries of phones is a labor-intensive part of phonetic research. To simplify this work, we created a free open-source tool generating phone sequences from Czech text and time-aligning them with audio.
  Low architecture complexity makes the design approachable for students of phonetics. Acoustic model ReLU NN with 56k weights was trained using PyTorch on small CommonVoice data. Alignment and variant selection decoder is implemented in Python with matrix library.
  A Czech pronunciation generator is composed of simple rule-based blocks capturing the logic of the language where possible, allowing modification of transcription approach details.
  Compared to tools used until now, data preparation efficiency improved, the tool is usable on Mac, Linux and Windows in Praat GUI or command line, achieves mostly correct pronunciation variant choice including glottal stop detection, algorithmically captures most of Czech assimilation logic and is both didactic and practical.},
  keywords = {phonetic alignment; segmentation; PyTorch; Czech; Praat},
  publisher = {{Guarant International}},
  address = {{Prague, Czech Republic}},
  volume = {2023},
  isbn = {978-80-908114-2-3},
  pages = {3121-3125},
  language = {English}
}