Complexity of the TDNN Acoustic Model with Respect to the HMM Topology

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F20%3A43959365" target="_blank" >RIV/49777513:23520/20:43959365 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-030-58323-1_50" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-030-58323-1_50</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-58323-1_50" target="_blank" >10.1007/978-3-030-58323-1_50</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Complexity of the TDNN Acoustic Model with Respect to the HMM Topology

Popis výsledku v původním jazyce

In this paper, we discuss some of the properties of training acoustic models using a lattice-free version of the maximum mutual information criterion (LF-MMI). Currently, the LF-MMI method achieves state-of-the-art results on many speech recognition tasks. Some of the key features of the LF-MMI approach are: training DNN without initialization from a cross-entropy system, the use of a 3-fold reduced frame rate and the use of a simpler HMM topology. The conventional 3-state HMM topology was replaced in a typical LF-MMI training procedure with a special 1-stage HMM topology, that has different pdfs on the self-loop and forward transitions. In this paper, we would like to discuss both the different types of HMM topologies (conventional 1-, 2- and 3-state HMM topology) and the advantages of using biphone context modeling over using the original triphone or a simpler monophone context. We would also like to mention the impact of the subsampling factor to WER.

Název v anglickém jazyce

Complexity of the TDNN Acoustic Model with Respect to the HMM Topology

Popis výsledku anglicky

In this paper, we discuss some of the properties of training acoustic models using a lattice-free version of the maximum mutual information criterion (LF-MMI). Currently, the LF-MMI method achieves state-of-the-art results on many speech recognition tasks. Some of the key features of the LF-MMI approach are: training DNN without initialization from a cross-entropy system, the use of a 3-fold reduced frame rate and the use of a simpler HMM topology. The conventional 3-state HMM topology was replaced in a typical LF-MMI training procedure with a special 1-stage HMM topology, that has different pdfs on the self-loop and forward transitions. In this paper, we would like to discuss both the different types of HMM topologies (conventional 1-, 2- and 3-state HMM topology) and the advantages of using biphone context modeling over using the original triphone or a simpler monophone context. We would also like to mention the impact of the subsampling factor to WER.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/LO1506" target="_blank" >LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost</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

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Text, Speech, and Dialogue 23rd International Conference, TSD 2020, Brno, Czech Republic, September 8-11, 2020, Proceedings

ISBN

978-3-030-58322-4

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

9

Strana od-do

465-473

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Brno, Česká republika

Datum konání akce

8. 9. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—