Single Channel Target Speaker Extraction and Recognition with Speaker Beam

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Single Channel Target Speaker Extraction and Recognition with Speaker Beam

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Single Channel Target Speaker Extraction and Recognition with Speaker Beam

Popis výsledku anglicky

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.

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

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

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

5554-5558

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

000446384605144