Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition

06/27/2023

∙

Automatic recognition of disordered and elderly speech remains highly challenging tasks to date due to data scarcity. Parameter fine-tuning is often used to exploit the large quantities of non-aged and healthy speech pre-trained models, while neural architecture hyper-parameters are set using expert knowledge and remain unchanged. This paper investigates hyper-parameter adaptation for Conformer ASR systems that are pre-trained on the Librispeech corpus before being domain adapted to the DementiaBank elderly and UASpeech dysarthric speech datasets. Experimental results suggest that hyper-parameter adaptation produced word error rate (WER) reductions of 0.45 parameter-only fine-tuning on DBank and UASpeech tasks respectively. An intuitive correlation is found between the performance improvements by hyper-parameter domain adaptation and the relative utterance length ratio between the source and target domain data.

READ FULL TEXT

Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition

Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition

Parameter-Efficient Learning for Text-to-Speech Accent Adaptation

Hyper-Decision Transformer for Efficient Online Policy Adaptation

Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech

Joint Learning of Pre-Trained and Random Units for Domain Adaptation in Part-of-Speech Tagging

Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning

Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems

Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition

Related Research

Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition

Parameter-Efficient Learning for Text-to-Speech Accent Adaptation

Hyper-Decision Transformer for Efficient Online Policy Adaptation

Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech

Joint Learning of Pre-Trained and Random Units for Domain Adaptation in Part-of-Speech Tagging

Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning

Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems