Optimization of Speaker-aware Multichannel Speech Extraction with ASR Criterion

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130736" target="_blank" >RIV/00216305:26230/18:PU130736 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11722" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11722</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2018.8461533" target="_blank" >10.1109/ICASSP.2018.8461533</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Optimization of Speaker-aware Multichannel Speech Extraction with ASR Criterion

Popis výsledku v původním jazyce

This paper addresses the problem of recognizing speech corrupted by overlapping speakers in a multichannel setting. To extract a target speaker from the mixture, we use a neural network based beamformer which uses masks estimated by a neural network to compute statistically optimal spatial filters. Following our previous work, we inform the neural network about the target speaker using information extracted from an adaptation utterance, enabling the network to track the target speaker. While in the previous work, this method was used to separately extract the speaker and then pass such preprocessed speech to a speech recognition system, here we explore training both systems jointly with a common speech recognition criterion. We show that integrating the two systems and training for the final objective improves the performance. In addition, the integration enables further sharing of information between the acoustic model and the speaker extraction system, by making use of the predicted HMMstate posteriors to refine the masks used for beamforming.

Název v anglickém jazyce

Optimization of Speaker-aware Multichannel Speech Extraction with ASR Criterion

Popis výsledku anglicky

This paper addresses the problem of recognizing speech corrupted by overlapping speakers in a multichannel setting. To extract a target speaker from the mixture, we use a neural network based beamformer which uses masks estimated by a neural network to compute statistically optimal spatial filters. Following our previous work, we inform the neural network about the target speaker using information extracted from an adaptation utterance, enabling the network to track the target speaker. While in the previous work, this method was used to separately extract the speaker and then pass such preprocessed speech to a speech recognition system, here we explore training both systems jointly with a common speech recognition criterion. We show that integrating the two systems and training for the final objective improves the performance. In addition, the integration enables further sharing of information between the acoustic model and the speaker extraction system, by making use of the predicted HMMstate posteriors to refine the masks used for beamforming.

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

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of ICASSP 2018

ISBN

978-1-5386-4658-8

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

6702-6706

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Calgary

Místo konání akce

Calgary

Datum konání akce

15. 4. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000446384606172