A Sequential Contrastive Learning Framework for Robust Dysarthric Speech Recognition
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7303-7307
Abstract
Dysarthria is a manifestation of disruption in the neuromuscular physiology resulting in uneven, slow, slurred, harsh, or quiet speech. Despite the remarkable progress of automatic speech recognition (ASR), it poses great challenges in developing stable ASR for dysarthric individuals due to the high intra- and inter-speaker variations and data deficiency. In this paper, we propose a contrastive learning framework for robust dysarthric speech recognition (DSR) by capturing the dysarthric speech variability. Several speech data augmentation strategies are explored to form two branches of the framework, meanwhile alleviating the scarcity of dysarthria data. We also develop an efficient projection head acting on a sequence of learned hidden representations for defining contrastive loss. Experiment results on DSR demonstrate that the model is better than or comparable to the supervised baseline.Keywords
This publication has 16 references indexed in Scilit:
- Phonetic Analysis of Dysarthric Speech Tempo and Applications to Robust Personalised Dysarthric Speech Recognition2019
- Dysarthric Speech Recognition Using Convolutional LSTM Neural Network2018
- Dysarthric Speech Recognition Using Time-delay Neural Network Based Denoising Autoencoder2018
- Data Augmentation Using Healthy Speech for Dysarthric Speech Recognition2018
- Improving Acoustic Models in TORGO Dysarthric Speech DatabaseIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018
- Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM2017
- Deep Autoencoder Based Speech Features for Improved Dysarthric Speech Recognition2017
- Listen, attend and spell: A neural network for large vocabulary conversational speech recognition2016
- Librispeech: An ASR corpus based on public domain audio books2015
- The TORGO database of acoustic and articulatory speech from speakers with dysarthriaLanguage Resources and Evaluation, 2011