Single Channel Target Speaker Extraction and Recognition with Speaker Beam

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130735" target="_blank" >RIV/00216305:26230/18:PU130735 - isvavai.cz</a>

Result on the web

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11721" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11721</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2018.8462661" target="_blank" >10.1109/ICASSP.2018.8462661</a>

Result language

angličtina

Original language name

Single Channel Target Speaker Extraction and Recognition with Speaker Beam

Original language description

This paper addresses the problem of single channel speech recognition of a target speaker in a mixture of speech signals. We propose to exploit auxiliary speaker information provided by an adaptation utterance from the target speaker to extract and recognize only that speaker. Using such auxiliary information, we can build a speaker extraction neural network (NN) that is independent of the number of sources in the mixture, and that can track speakers across different utterances, which are two challenging issues occurring with conventional approaches for speech recognition of mixtures. We call such an informed speaker extraction scheme "SpeakerBeam". SpeakerBeam exploits a recently developed context adaptive deep NN (CADNN) that allows tracking speech from a target speaker using a speaker adaptation layer, whose parameters are adjusted depending on auxiliary features representing the target speaker characteristics. SpeakerBeam was previously investigated for speaker extraction using a microphone array. In this paper, we demonstrate that it is also efficient for single channel speaker extraction. The speaker adaptation layer can be employed either to build a speaker adaptive acoustic model that recognizes only the target speaker or a maskbased speaker extraction network that extracts the target speech from the speech mixture signal prior to recognition. We also show that the latter speaker extraction network can be optimized jointly with an acoustic model to further improve ASR performance.

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

<a href="/en/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Continuities

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

Publication year

2018

Confidentiality

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

Article name in the collection

Proceedings of ICASSP 2018

ISBN

978-1-5386-4658-8

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

5554-5558

Publisher name

IEEE Signal Processing Society

Place of publication

Calgary

Event location

Calgary

Event date

Apr 15, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000446384605144