On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition
This addresses the problem of speaker-level heterogeneity and data scarcity in speech recognition for dysarthric and elderly individuals, offering an incremental improvement over existing adaptation methods.
The paper tackles the challenge of recognizing dysarthric and elderly speech by proposing data-efficient, feature-based on-the-fly speaker adaptation methods, resulting in statistically significant word error rate reductions of 2.48%-2.85% absolute (7.92%-8.06% relative) compared to baseline systems.
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.