Using LSTM neural networks for cross-lingual phonetic speech segmentation with an iterative correction procedure

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43969623" target="_blank" >RIV/49777513:23520/24:43969623 - isvavai.cz</a>

Výsledek na webu

<a href="https://onlinelibrary.wiley.com/doi/10.1111/coin.12602" target="_blank" >https://onlinelibrary.wiley.com/doi/10.1111/coin.12602</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1111/coin.12602" target="_blank" >10.1111/coin.12602</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Using LSTM neural networks for cross-lingual phonetic speech segmentation with an iterative correction procedure

Popis výsledku v původním jazyce

This article describes experiments on speech segmentation using long short-term memory recurrent neural networks. The main part of the paper deals with multi-lingual and cross-lingual segmentation, that is, it is performed on a language different from the one on which the model was trained. The experimental data involves large Czech, English, German, and Russian speech corpora designated for speech synthesis. For optimal multi-lingual modeling, a compact phonetic alphabet was proposed by sharing and clustering phones of particular languages. Many experiments were performed exploring various experimental conditions and data combinations. We proposed a simple procedure that iteratively adapts the inaccurate default model to the new voice/language. The segmentation accuracy was evaluated by comparison with reference segmentation created by a well-tuned hidden Markov model-based framework with additional manual corrections. The resulting segmentation was also employed in a unit selection text-to-speech system. The generated speech quality was compared with the reference segmentation by a preference listening test.

Název v anglickém jazyce

Using LSTM neural networks for cross-lingual phonetic speech segmentation with an iterative correction procedure

Popis výsledku anglicky

This article describes experiments on speech segmentation using long short-term memory recurrent neural networks. The main part of the paper deals with multi-lingual and cross-lingual segmentation, that is, it is performed on a language different from the one on which the model was trained. The experimental data involves large Czech, English, German, and Russian speech corpora designated for speech synthesis. For optimal multi-lingual modeling, a compact phonetic alphabet was proposed by sharing and clustering phones of particular languages. Many experiments were performed exploring various experimental conditions and data combinations. We proposed a simple procedure that iteratively adapts the inaccurate default model to the new voice/language. The segmentation accuracy was evaluated by comparison with reference segmentation created by a well-tuned hidden Markov model-based framework with additional manual corrections. The resulting segmentation was also employed in a unit selection text-to-speech system. The generated speech quality was compared with the reference segmentation by a preference listening test.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/GA19-19324S" target="_blank" >GA19-19324S: Plně trénovatelná syntéza české řeči z textu s využitím hlubokých neuronových sítí</a><br>

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Computational Intelligence

ISSN

0824-7935

e-ISSN

1467-8640

Svazek periodika

40

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

36

Strana od-do

—

Kód UT WoS článku

001066674400001

EID výsledku v databázi Scopus

2-s2.0-85171439072