Speaker activity driven neural speech extraction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU140966" target="_blank" >RIV/00216305:26230/21:PU140966 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.fit.vut.cz/research/publication/12479/" target="_blank" >https://www.fit.vut.cz/research/publication/12479/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP39728.2021.9414998" target="_blank" >10.1109/ICASSP39728.2021.9414998</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Speaker activity driven neural speech extraction

Popis výsledku v původním jazyce

Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances, direction information, or video of the target speaker. In this paper, we explore the use of speaker activity information as an auxiliary clue for single-channel neural network-based speech extraction. We propose a speaker activity driven speech extraction neural network (ADEnet) and show that it can achieve performance levels competitive with enrollmentbased approaches, without the need for pre-recordings. We further demonstrate the potential of the proposed approach for processing meeting-like recordings, where speaker activity obtained from a diarization system is used as a speaker clue for ADEnet. We show that this simple yet practical approach can successfully extract speakers after diarization, which leads to improved ASR performance when using a single microphone, especially in high overlapping conditions, with relative word error rate reduction of up to 25 %.

Název v anglickém jazyce

Speaker activity driven neural speech extraction

Popis výsledku anglicky

Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances, direction information, or video of the target speaker. In this paper, we explore the use of speaker activity information as an auxiliary clue for single-channel neural network-based speech extraction. We propose a speaker activity driven speech extraction neural network (ADEnet) and show that it can achieve performance levels competitive with enrollmentbased approaches, without the need for pre-recordings. We further demonstrate the potential of the proposed approach for processing meeting-like recordings, where speaker activity obtained from a diarization system is used as a speaker clue for ADEnet. We show that this simple yet practical approach can successfully extract speakers after diarization, which leads to improved ASR performance when using a single microphone, especially in high overlapping conditions, with relative word error rate reduction of up to 25 %.

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ISBN

978-1-7281-7605-5

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

6099-6103

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Toronto

Místo konání akce

Toronto, Canada

Datum konání akce

6. 6. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000704288406074