Prak: An automatic phonetic alignment tool for Czech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11210%2F23%3A10474535" target="_blank" >RIV/00216208:11210/23:10474535 - isvavai.cz</a>

Výsledek na webu

<a href="https://guarant.cz/icphs2023/525.pdf" target="_blank" >https://guarant.cz/icphs2023/525.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Prak: An automatic phonetic alignment tool for Czech

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Prak: An automatic phonetic alignment tool for Czech

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

60203 - Linguistics

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

20th International Congress of Phonetic Sciences (ICPhS)

ISBN

978-80-908114-2-3

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

3121-3125

Název nakladatele

Guarant International

Místo vydání

Prague, Czech Republic

Místo konání akce

Prague Congress Center, Czech Republic

Datum konání akce

7. 8. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—