Learning Speaker Representation for Neural Network Based Multichannel Speaker Extraction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F17%3APU126480" target="_blank" >RIV/00216305:26230/17:PU126480 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.fit.vutbr.cz/research/groups/speech/publi/2017/zmolikova_asru2017.pdf" target="_blank" >http://www.fit.vutbr.cz/research/groups/speech/publi/2017/zmolikova_asru2017.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ASRU.2017.8268910" target="_blank" >10.1109/ASRU.2017.8268910</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning Speaker Representation for Neural Network Based Multichannel Speaker Extraction

Popis výsledku v původním jazyce

Recently, schemes employing deep neural networks (DNNs) for extracting speech from noisy observation have demonstrated great potential for noise robust automatic speech recognition. However, these schemes are not well suited when the interfering noise is another speaker. To enable extracting a target speaker from a mixture of speakers, we have recently proposed to inform the neural network using speaker information extracted from an adaptation utterance from the same speaker. In our previous work, we explored ways how to inform the network about the speaker and found a speaker adaptive layer approach to be suitable for this task. In our experiments, we used speaker features designed for speaker recognition tasks as the additional speaker information, which may not be optimal for the speaker extraction task. In this paper, we propose a usage of a sequence summarizing scheme enabling to learn the speaker representation jointly with the network. Furthermore, we extend the previous experiments to demonstrate the potential of our proposed method as a front-end for speech recognition and explore the effect of additional noise on the performance of the method.

Název v anglickém jazyce

Learning Speaker Representation for Neural Network Based Multichannel Speaker Extraction

Popis výsledku anglicky

Recently, schemes employing deep neural networks (DNNs) for extracting speech from noisy observation have demonstrated great potential for noise robust automatic speech recognition. However, these schemes are not well suited when the interfering noise is another speaker. To enable extracting a target speaker from a mixture of speakers, we have recently proposed to inform the neural network using speaker information extracted from an adaptation utterance from the same speaker. In our previous work, we explored ways how to inform the network about the speaker and found a speaker adaptive layer approach to be suitable for this task. In our experiments, we used speaker features designed for speaker recognition tasks as the additional speaker information, which may not be optimal for the speaker extraction task. In this paper, we propose a usage of a sequence summarizing scheme enabling to learn the speaker representation jointly with the network. Furthermore, we extend the previous experiments to demonstrate the potential of our proposed method as a front-end for speech recognition and explore the effect of additional noise on the performance of the method.

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

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of ASRU 2017

ISBN

978-1-5090-4788-8

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

8-15

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Okinawa

Místo konání akce

Okinawa

Datum konání akce

16. 12. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000426066100002