On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition
Refereed conference paper presented and published in conference proceedings
Officially Accepted for Publication
CUHK Authors
Full Text
There are no full text file(s) associated with this record. |
Other information
AbstractAccurate recognition of dysarthric and elderly speech re- main challenging tasks to date. Speaker-level heterogeneity attributed to accent or gender, when aggregated with age and speech impairment, create large diversity among these speak- ers. Scarcity of speaker-level data limits the practical use of data-intensive model based speaker adaptation methods. To this end, this paper proposes two novel forms of data-efficient. feature based on-the-fly speaker adaptation methods: variance- regularized spectral basis embedding (SVR) and spectral fea- ture driven f-LHUC transforms. Experiments conducted on UASpeech dysarthric and DementiaBank Pitt elderly speech corpora suggest the proposed on-the-fly speaker adaptation ap- proaches consistently outperform baseline iVector adapted hy- brid DNN/TDNN and E2E Conformer systems by statistically significant WER reduction of 2.48%-2.85% absolute (7.92%- 8.06% relative), and offline model based LHUC adaptation by 1.82% absolute (5.63% relative) respectively.
Acceptance Date18/05/2023
All Author(s) ListMengzhe Geng, Xurong Xie, Rongfeng Su, Jianwei Yu, Zengrui Jin, Tianzi Wang, Shujie Hu, Zi Ye, Helen Meng, Xunying Liu
Name of ConferenceISCA Interspeech2023
Start Date of Conference20/08/2023
End Date of Conference24/08/2023
Place of ConferenceDublin
Country/Region of ConferenceIreland
Year2023
LanguagesEnglish-United States
