Parameter-efficient Dysarthric Speech Recognition Using Adapter Fusion And Householder Transformation
2023 · Jinzi Qi, Hugo van Hamme
Abstract
In dysarthric speech recognition, data scarcity and the vast diversity between dysarthric speakers pose significant challenges. While finetuning has been a popular solution, it can lead to overfitting and low parameter efficiency. Adapter modules offer a better solution, with their small size and easy applicability. Additionally, Adapter Fusion can facilitate knowledge transfer from multiple learned adapters, but may employ more parameters. In this work, we apply Adapter Fusion for target speaker adaptation and speech recognition, achieving acceptable accuracy with significantly fewer speaker-specific trainable parameters than classical finetuning methods. We further improve the parameter efficiency of the fusion layer by reducing the size of query and key layers and using Householder transformation to reparameterize the value linear layer. Our proposed fusion layer achieves comparable recognition results to the original method with only one third of the parameters.
Authors
(none)
Tags
Stats
Related papers
- Residual Adapters For Parameter-efficient ASR Adaptation To Atypical And Accented Speech (2021)10.74
- ADAPTERMIX: Exploring The Efficacy Of Mixture Of Adapters For Low-resource TTS Adaptation (2023)6.34
- Enhancing Dysarthric Speech Recognition For Unseen Speakers Via Prototype-based Adaptation (2024)9.45
- Elp-adapters: Parameter Efficient Adapter Tuning For Various Speech Processing Tasks (2024)7.81
- Hyper-parameter Adaptation Of Conformer ASR Systems For Elderly And Dysarthric Speech Recognition (2023)0.00
- On-the-fly Feature Based Rapid Speaker Adaptation For Dysarthric And Elderly Speech Recognition (2022)6.34
- Efficient Adapter Tuning Of Pre-trained Speech Models For Automatic Speaker Verification (2024)0.00
- Homogeneous Speaker Features For On-the-fly Dysarthric And Elderly Speaker Adaptation (2024)0.00