Study on the use and adaptation of bottleneck features for robust speech recognition of nonlinearly distorted speech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F16%3A00000301" target="_blank" >RIV/46747885:24220/16:00000301 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.5220/0005955500650071" target="_blank" >http://dx.doi.org/10.5220/0005955500650071</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0005955500650071" target="_blank" >10.5220/0005955500650071</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Study on the use and adaptation of bottleneck features for robust speech recognition of nonlinearly distorted speech

Popis výsledku v původním jazyce

This paper focuses on the robust recognition of nonlinearly distorted speech. We have previously reported that hybrid acoustic models based on a combination of Hidden Markov Models and Deep Neural Networks (HMM-DNNs) are better suited to this task than conventional HMMs utilizing Gaussian Mixture Models (HMM-GMMs). To further improve recognition accuracy, this paper investigates the possibility of combining the modeling power of deep neural networks with the adaptation to given acoustic conditions. For this purpose, the deep neural networks are utilized to produce bottleneck coefficients / features (BNC). The BNCs are subsequently used for training of HMM-GMM based acoustic models and then adapted using Constrained Maximum Likelihood Linear Regression (CMLLR). Our results obtained for three types of nonlinear distortions and three types of input features show that the adapted BNC-based system (a) outperforms HMM-DNN acoustic models in the case of strong compression and (b) yields comparable performance for speech affected by nonlinear amplification in the analog domain.

Název v anglickém jazyce

Study on the use and adaptation of bottleneck features for robust speech recognition of nonlinearly distorted speech

Popis výsledku anglicky

This paper focuses on the robust recognition of nonlinearly distorted speech. We have previously reported that hybrid acoustic models based on a combination of Hidden Markov Models and Deep Neural Networks (HMM-DNNs) are better suited to this task than conventional HMMs utilizing Gaussian Mixture Models (HMM-GMMs). To further improve recognition accuracy, this paper investigates the possibility of combining the modeling power of deep neural networks with the adaptation to given acoustic conditions. For this purpose, the deep neural networks are utilized to produce bottleneck coefficients / features (BNC). The BNCs are subsequently used for training of HMM-GMM based acoustic models and then adapted using Constrained Maximum Likelihood Linear Regression (CMLLR). Our results obtained for three types of nonlinear distortions and three types of input features show that the adapted BNC-based system (a) outperforms HMM-DNN acoustic models in the case of strong compression and (b) yields comparable performance for speech affected by nonlinear amplification in the analog domain.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/TA04010199" target="_blank" >TA04010199: MULTILINMEDIA - Multilinguální platforma pro monitoring a analýzu multimédií</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proc. of 13th International Conference on Signal Processing and Multimedia Applications (SIGMAP 2016)

ISBN

978-989-758-196-0

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

65-71

Název nakladatele

SciTePress

Místo vydání

Lisabon, Portugalsko

Místo konání akce

Lisabon, Portugalsko

Datum konání akce

1. 1. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000391091400006