Learning Speaker Representation for Neural Network Based Multichannel Speaker Extraction

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

Learning Speaker Representation for Neural Network Based Multichannel Speaker Extraction

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

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

Article name in the collection

Proceedings of ASRU 2017

ISBN

978-1-5090-4788-8

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

8-15

Publisher name

IEEE Signal Processing Society

Place of publication

Okinawa

Event location

Okinawa

Event date

Dec 16, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000426066100002