On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition

Autor:	Geng, Mengzhe, Xie, Xurong, Su, Rongfeng, Yu, Jianwei, Jin, Zengrui, Wang, Tianzi, Hu, Shujie, Ye, Zi, Meng, Helen, Liu, Xunying
Rok vydání:	2022
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	Accurate recognition of dysarthric and elderly speech remain challenging tasks to date. Speaker-level heterogeneity attributed to accent or gender, when aggregated with age and speech impairment, create large diversity among these speakers. 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 feature driven f-LHUC transforms. Experiments conducted on UASpeech dysarthric and DementiaBank Pitt elderly speech corpora suggest the proposed on-the-fly speaker adaptation approaches consistently outperform baseline iVector adapted hybrid 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. Comment: Accepted to INTERSPEECH 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.14593 Zobrazit plný text záznamu View this record from Arxiv