Compact Network for Speakerbeam Target Speaker Extraction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134186" target="_blank" >RIV/00216305:26230/19:PU134186 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8683087" target="_blank" >https://ieeexplore.ieee.org/document/8683087</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2019.8683087" target="_blank" >10.1109/ICASSP.2019.8683087</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Compact Network for Speakerbeam Target Speaker Extraction

Popis výsledku v původním jazyce

Speech separation that separates a mixture of speech signals into each of its sources has been an active research topic for a long time and has seen recent progress with the advent of deep learning. A related problem is target speaker extraction, i.e. extraction of only speech of a target speaker out of a mixture, given characteristics of his/her voice. We have recently proposed SpeakerBeam, which is a neural network-based target speaker extraction method. Speaker- Beam uses a speech extraction network that is adapted to the target speaker using auxiliary features derived from an adaptation utterance of that speaker. Initially, we implemented SpeakerBeam with a factorized adaptation layer, which consists of several parallel linear transformations weighted by weights derived from the auxiliary features. The factorized layer is effective for target speech extraction, but it requires a large number of parameters. In this paper, we propose to simply scale the activations of a hidden layer of the speech extraction network with weights derived from the auxiliary features. This simpler approach greatly reduces the number of model parameters by up to 60%, making it much more practical, while maintaining a similar level of performance. We tested our approach on simulated and real noisy and reverberant mixtures, showing the potential of SpeakerBeam for real-life applications. Moreover, we showed that speech extraction performance of SpeakerBeam compares favorably with that of a state-of-the-art speech separation method with a similar network configuration.

Název v anglickém jazyce

Compact Network for Speakerbeam Target Speaker Extraction

Popis výsledku anglicky

Speech separation that separates a mixture of speech signals into each of its sources has been an active research topic for a long time and has seen recent progress with the advent of deep learning. A related problem is target speaker extraction, i.e. extraction of only speech of a target speaker out of a mixture, given characteristics of his/her voice. We have recently proposed SpeakerBeam, which is a neural network-based target speaker extraction method. Speaker- Beam uses a speech extraction network that is adapted to the target speaker using auxiliary features derived from an adaptation utterance of that speaker. Initially, we implemented SpeakerBeam with a factorized adaptation layer, which consists of several parallel linear transformations weighted by weights derived from the auxiliary features. The factorized layer is effective for target speech extraction, but it requires a large number of parameters. In this paper, we propose to simply scale the activations of a hidden layer of the speech extraction network with weights derived from the auxiliary features. This simpler approach greatly reduces the number of model parameters by up to 60%, making it much more practical, while maintaining a similar level of performance. We tested our approach on simulated and real noisy and reverberant mixtures, showing the potential of SpeakerBeam for real-life applications. Moreover, we showed that speech extraction performance of SpeakerBeam compares favorably with that of a state-of-the-art speech separation method with a similar network configuration.

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/TJ01000208" target="_blank" >TJ01000208: NeurOnové sítě pro zpracování SIgnálu a dolování informací v řeČI - NOSIČI</a><br>

Návaznosti

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

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of ICASSP

ISBN

978-1-5386-4658-8

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

6965-6969

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Brighton

Místo konání akce

Brighton

Datum konání akce

12. 5. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000482554007040