Automatic Phonetic Segmentation Using the Kaldi Toolkit

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43932638" target="_blank" >RIV/49777513:23520/17:43932638 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-319-64206-2_16" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-319-64206-2_16</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-64206-2_16" target="_blank" >10.1007/978-3-319-64206-2_16</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Phonetic Segmentation Using the Kaldi Toolkit

Popis výsledku v původním jazyce

In this paper we explore the possibilities of hidden Markov model based automatic phonetic segmentation with the Kaldi toolkit. We compare the Kaldi toolkit and the Hidden Markov Model Toolkit (HTK) in terms of segmentation accuracy. The well-tuned HTK-based phonetic segmentation framework was taken as the baseline and compared to a newly proposed segmentation framework built from the default examples and recipes available in the Kaldi repository. Since the segmentation accuracy of the HTK-based system was significantly higher than that of the Kaldi-based system, the default Kaldi setting was modified with respect to pause model topology, the way of generating phonetic questions for clustering, and the number of Gaussian mixtures used during modeling. The modified Kaldi-based system achieved results comparable to those obtained by HTK—slightly worse for small segmentation errors but better for gross segmentation errors. We also confirmed that, for both toolkits, the standard three-state left-to-right model topology was significantly outperformed by a modified five-state left-to-right topology, especially with respect to small segmentation errors.

Název v anglickém jazyce

Automatic Phonetic Segmentation Using the Kaldi Toolkit

Popis výsledku anglicky

In this paper we explore the possibilities of hidden Markov model based automatic phonetic segmentation with the Kaldi toolkit. We compare the Kaldi toolkit and the Hidden Markov Model Toolkit (HTK) in terms of segmentation accuracy. The well-tuned HTK-based phonetic segmentation framework was taken as the baseline and compared to a newly proposed segmentation framework built from the default examples and recipes available in the Kaldi repository. Since the segmentation accuracy of the HTK-based system was significantly higher than that of the Kaldi-based system, the default Kaldi setting was modified with respect to pause model topology, the way of generating phonetic questions for clustering, and the number of Gaussian mixtures used during modeling. The modified Kaldi-based system achieved results comparable to those obtained by HTK—slightly worse for small segmentation errors but better for gross segmentation errors. We also confirmed that, for both toolkits, the standard three-state left-to-right model topology was significantly outperformed by a modified five-state left-to-right topology, especially with respect to small segmentation errors.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/TH02010307" target="_blank" >TH02010307: Automatická konzervace a rekonstrukce hlasu se zaměřením na pacienty po totální laryngektomii</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Text, Speech and Dialogue, 20th International Conference, TSD 2017, Prague, Czech Republic, August 27-31 August, 2017, Proceedings

ISBN

978-3-319-64205-5

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

9

Strana od-do

138-146

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Prague, Czech Republic

Datum konání akce

27. 8. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000449869200016