Publication Details

Speaker adaptation for Wav2vec2 based dysarthric ASR

BASKAR Murali K., HERZIG Tim, NGUYEN Diana, DIEZ Sánchez Mireia, POLZEHL Tim, BURGET Lukáš and ČERNOCKÝ Jan. Speaker adaptation for Wav2vec2 based dysarthric ASR. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Incheon: International Speech Communication Association, 2022, pp. 3403-3407. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/pdfs/interspeech_2022/baskar22b_interspeech.pdf
Type
conference paper
Language
english
Authors
Baskar Murali K. (DCGM FIT BUT)
Herzig Tim (TU-BERLIN)
Nguyen Diana (TU-BERLIN)
Diez Sánchez Mireia, M.Sc., Ph.D. (DCGM FIT BUT)
Polzehl Tim (TU-BERLIN)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

Dysarthria, self-supervision, ASR, wav2vec2, fMLLR, xvectors, speaker adaptation

Abstract

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.

Published
2022
Pages
3403-3407
Journal
Proceedings of Interspeech - on-line, vol. 9, no. 9, ISSN 1990-9772
Proceedings
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Conference
Interspeech 2022, Incheon Korea, KR
Publisher
International Speech Communication Association
Place
Incheon, KR
DOI
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12854,
   author = "K. Murali Baskar and Tim Herzig and Diana Nguyen and Mireia S\'{a}nchez Diez and Tim Polzehl and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Speaker adaptation for Wav2vec2 based dysarthric ASR",
   pages = "3403--3407",
   booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
   journal = "Proceedings of Interspeech - on-line",
   volume = 9,
   number = 9,
   year = 2022,
   location = "Incheon, KR",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2022-10896",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12854"
}
Back to top