Towards Automatic Data Augmentation for Disordered Speech Recognition
Automatic recognition of disordered speech remains a highly challenging task to date due to data scarcity. This paper presents a reinforcement learning (RL) based on-the-fly data augmentation approach for training state-of-the-art PyChain TDNN and end-to-end Conformer ASR systems on such data. The handcrafted temporal and spectral mask operations in the standard SpecAugment method that are task and system dependent, together with additionally introduced minimum and maximum cut-offs of these time-frequency masks, are now automatically learned using an RNN-based policy controller and tightly integrated with ASR system training. Experiments on the UASpeech corpus suggest the proposed RL-based data augmentation approach consistently produced performance superior or comparable that obtained using expert or handcrafted SpecAugment policies. Our RL auto-augmented PyChain TDNN system produced an overall WER of 28.79% on the UASpeech test set of 16 dysarthric speakers.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationReinforcement Learning (RL)speech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Data Augmentation for Disordered Speech Recognition
Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting …
Data Augmentationspeech-recognitionSpeech RecognitionAdversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition
Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting …
Data AugmentationGenerative Adversarial Networkspeech-recognitionSpeech RecognitionInvestigation of Data Augmentation Techniques for Disordered Speech Recognition
Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in colle…
Data Augmentationspeech-recognitionSpeech RecognitionSpectro-Temporal Deep Features for Disordered Speech Assessment and Recognition
Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying ca…
Data Augmentationspeech-recognitionSpeech RecognitionRecent Progress in the CUHK Dysarthric Speech Recognition System
Despite the rapid progress of automatic speech recognition (ASR) technologies in the past few decades, recognition of disordered speech remains a highly challenging task to date. Disordered speech presents a wide spectru…
Audio-Visual Speech RecognitionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentation+3