Various DNN-HMM architectures used in acoustic modeling with single-speaker and single-channel

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F21%3A43962798" target="_blank" >RIV/49777513:23520/21:43962798 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-89579-2_8" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-89579-2_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-89579-2_8" target="_blank" >10.1007/978-3-030-89579-2_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Various DNN-HMM architectures used in acoustic modeling with single-speaker and single-channel

Popis výsledku v původním jazyce

In this paper, we discuss some interesting features of training a special acoustic model for only one speaker with a constant acoustic background (acoustic channel). Currently, the LF-MMI method achieves the best results in many speech recognition tasks. A typical LF-MMI training procedure uses a special 1-state HMM topology that has different pdfs at the self-loop and forward transitions. We would like to discuss the replacement of this typical LF-MMI HMM by different types of HMM topologies (1-, 2- and 3-state HMM topologies that have outputs associated with states). Next, we discuss the advantages of using biphone context modeling over using the triphone context or even simpler context-free monophone. We also address the effect of the amount of training data and the context of DNN on WER, and all this with regard to a special acoustic model with one speaker and an almost constant acoustic channel.

Název v anglickém jazyce

Various DNN-HMM architectures used in acoustic modeling with single-speaker and single-channel

Popis výsledku anglicky

In this paper, we discuss some interesting features of training a special acoustic model for only one speaker with a constant acoustic background (acoustic channel). Currently, the LF-MMI method achieves the best results in many speech recognition tasks. A typical LF-MMI training procedure uses a special 1-state HMM topology that has different pdfs at the self-loop and forward transitions. We would like to discuss the replacement of this typical LF-MMI HMM by different types of HMM topologies (1-, 2- and 3-state HMM topologies that have outputs associated with states). Next, we discuss the advantages of using biphone context modeling over using the triphone context or even simpler context-free monophone. We also address the effect of the amount of training data and the context of DNN on WER, and all this with regard to a special acoustic model with one speaker and an almost constant acoustic channel.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/EF17_048%2F0007267" target="_blank" >EF17_048/0007267: VaV inteligentních komponent pokročilých technologií pro plzeňskou metropolitní oblast</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Statistical Language and Speech Processing, 9th International Conference, SLSP 2021, Cardiff, UK, November 23–25, 2021, Proceedings

ISBN

978-3-030-89578-5

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

12

Strana od-do

85-96

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Cardiff, United Kingdom

Datum konání akce

23. 11. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—