Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F16%3APU122427" target="_blank" >RIV/00216305:26230/16:PU122427 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.researchgate.net/publication/307889648_Exploiting_Hidden-Layer_Responses_of_Deep_Neural_Networks_for_Language_Recognition" target="_blank" >https://www.researchgate.net/publication/307889648_Exploiting_Hidden-Layer_Responses_of_Deep_Neural_Networks_for_Language_Recognition</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2016-1584" target="_blank" >10.21437/Interspeech.2016-1584</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition

Popis výsledku v původním jazyce

The most popular way to apply Deep Neural Network (DNN) for Language IDentification (LID) involves the extraction of bottleneck features from a network that was trained on automatic speech recognition task. These features are modeled using a classical I-vector system. Recently, a more direct DNN approach was proposed, it consists of estimating the language posteriors directly from a stacked frames input. The final decision score is based on averaging the scores for all the frames for a given speech segment. In this paper, we extended the direct DNN approach by modeling all hidden-layer activations rather than just averaging the output scores. One super-vector per utterance is formed by concatenating all hidden-layer responses. The dimensionality of this vector is then reduced using a Principal Component Analysis (PCA). The obtained reduce vector summarizes the most discriminative features for language recognition based on the trained DNNs. We evaluated this approach in NIST 2015 language recognition evaluation. The performances achieved by the proposed approach are very competitive to the classical I-vector baseline.

Název v anglickém jazyce

Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition

Popis výsledku anglicky

The most popular way to apply Deep Neural Network (DNN) for Language IDentification (LID) involves the extraction of bottleneck features from a network that was trained on automatic speech recognition task. These features are modeled using a classical I-vector system. Recently, a more direct DNN approach was proposed, it consists of estimating the language posteriors directly from a stacked frames input. The final decision score is based on averaging the scores for all the frames for a given speech segment. In this paper, we extended the direct DNN approach by modeling all hidden-layer activations rather than just averaging the output scores. One super-vector per utterance is formed by concatenating all hidden-layer responses. The dimensionality of this vector is then reduced using a Principal Component Analysis (PCA). The obtained reduce vector summarizes the most discriminative features for language recognition based on the trained DNNs. We evaluated this approach in NIST 2015 language recognition evaluation. The performances achieved by the proposed approach are very competitive to the classical I-vector baseline.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of Interspeech 2016

ISBN

978-1-5108-3313-5

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

2365-2369

Název nakladatele

International Speech Communication Association

Místo vydání

San Francisco

Místo konání akce

San Francisco

Datum konání akce

8. 9. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000409394402034