Speaker adaptation for Wav2vec2 based dysarthric ASR

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU146142" target="_blank" >RIV/00216305:26230/22:PU146142 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-speech.org/archive/pdfs/interspeech_2022/baskar22b_interspeech.pdf" target="_blank" >https://www.isca-speech.org/archive/pdfs/interspeech_2022/baskar22b_interspeech.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2022-10896" target="_blank" >10.21437/Interspeech.2022-10896</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Speaker adaptation for Wav2vec2 based dysarthric ASR

Popis výsledku v původním jazyce

Dysarthric speech recognition has posed major challenges due to lack of training data and heavy mismatch in speaker characteristics. Recent ASR systems have benefited from readily available pretrained models such as wav2vec2 to improve the recognition performance. Speaker adaptation using fMLLR and xvectors have provided major gains for dysarthric speech with very little adaptation data. However, integration of wav2vec2 with fMLLR features or xvectors during wav2vec2 finetuning is yet to be explored. In this work, we propose a simple adaptation network for fine-tuning wav2vec2 using fMLLR features. The adaptation network is also flexible to handle other speaker adaptive features such as xvectors. Experimental analysis show steady improvements using our proposed approach across all impairment severity levels and attains 57.72% WER for high severity in UASpeech dataset. We also performed experiments on German dataset to substantiate the consistency of our proposed approach across diverse domains.

Název v anglickém jazyce

Speaker adaptation for Wav2vec2 based dysarthric ASR

Popis výsledku anglicky

Dysarthric speech recognition has posed major challenges due to lack of training data and heavy mismatch in speaker characteristics. Recent ASR systems have benefited from readily available pretrained models such as wav2vec2 to improve the recognition performance. Speaker adaptation using fMLLR and xvectors have provided major gains for dysarthric speech with very little adaptation data. However, integration of wav2vec2 with fMLLR features or xvectors during wav2vec2 finetuning is yet to be explored. In this work, we propose a simple adaptation network for fine-tuning wav2vec2 using fMLLR features. The adaptation network is also flexible to handle other speaker adaptive features such as xvectors. Experimental analysis show steady improvements using our proposed approach across all impairment severity levels and attains 57.72% WER for high severity in UASpeech dataset. We also performed experiments on German dataset to substantiate the consistency of our proposed approach across diverse domains.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ISBN

—

ISSN

1990-9772

e-ISSN

—

Počet stran výsledku

5

Strana od-do

3403-3407

Název nakladatele

International Speech Communication Association

Místo vydání

Incheon

Místo konání akce

Incheon Korea

Datum konání akce

18. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—