Sequence Summarizing Neural Networks for Spoken Language Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F16%3APU121675" target="_blank" >RIV/00216305:26230/16:PU121675 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.researchgate.net/publication/307889421_Sequence_Summarizing_Neural_Networks_for_Spoken_Language_Recognition" target="_blank" >https://www.researchgate.net/publication/307889421_Sequence_Summarizing_Neural_Networks_for_Spoken_Language_Recognition</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2016-764" target="_blank" >10.21437/Interspeech.2016-764</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Sequence Summarizing Neural Networks for Spoken Language Recognition

Popis výsledku v původním jazyce

This paper explores the use of Sequence Summarizing Neural Networks (SSNNs) as a variant of deep neural networks (DNNs) for classifying sequences. In this work, it is applied to the task of spoken language recognition. Unlike other classification tasks in speech processing where the DNN needs to produce a per-frame output, language is considered constant during an utterance. We introduce a summarization component into the DNN structure producing one set of language posteriors per utterance. The training of the DNN is performed by an appropriately modified gradient-descent algorithm. In our initial experiments, the SSNN results are compared to a single state-of-the-art i-vector based baseline system with a similar complexity (i.e. no system fusion, etc.). For some conditions, SSNNs is able to provide performance comparable to the baseline system. Relative improvement up to 30% is obtained with the score level fusion of the baseline and the SSNN systems.

Název v anglickém jazyce

Sequence Summarizing Neural Networks for Spoken Language Recognition

Popis výsledku anglicky

This paper explores the use of Sequence Summarizing Neural Networks (SSNNs) as a variant of deep neural networks (DNNs) for classifying sequences. In this work, it is applied to the task of spoken language recognition. Unlike other classification tasks in speech processing where the DNN needs to produce a per-frame output, language is considered constant during an utterance. We introduce a summarization component into the DNN structure producing one set of language posteriors per utterance. The training of the DNN is performed by an appropriately modified gradient-descent algorithm. In our initial experiments, the SSNN results are compared to a single state-of-the-art i-vector based baseline system with a similar complexity (i.e. no system fusion, etc.). For some conditions, SSNNs is able to provide performance comparable to the baseline system. Relative improvement up to 30% is obtained with the score level fusion of the baseline and the SSNN systems.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

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

3285-3289

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

000409394402038