paper-with-me

Papers

Towards Automatic Data Augmentation for Disordered Speech Recognition

2023-12-14 · Zengrui Jin, Xurong Xie, Tianzi Wang, Mengzhe Geng, Jiajun Deng, Guinan Li, Shujie Hu, Xunying Liu

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.

📄 PDF Abstract BibTeX arXiv:2312.08641

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationReinforcement Learning (RL)speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Adversarial Data Augmentation for Disordered Speech Recognition

2021-08-02 · Zengrui Jin, Mengzhe Geng, Xurong Xie, Jianwei Yu 외

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 Recognition

Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition

2022-11-03 · Zengrui Jin, Xurong Xie, Mengzhe Geng, Tianzi Wang 외

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 Recognition

Investigation of Data Augmentation Techniques for Disordered Speech Recognition

2022-01-14 · Mengzhe Geng, Xurong Xie, Shansong Liu, Jianwei Yu 외

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 Recognition

Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition

2022-01-14 · Mengzhe Geng, Shansong Liu, Jianwei Yu, Xurong Xie 외

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 Recognition

Recent Progress in the CUHK Dysarthric Speech Recognition System

2022-01-15 · Shansong Liu, Mengzhe Geng, Shoukang Hu, Xurong Xie 외

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