Paper ID | SPE-48.1 | ||
Paper Title | MIXSPEECH: DATA AUGMENTATION FOR LOW-RESOURCE AUTOMATIC SPEECH RECOGNITION | ||
Authors | Linghui Meng, Institute of Automation, Chinese Academy of Sciences, China; Jin Xu, Institute for Interdisciplinary Information Sciences, Tsinghua University, China; Xu Tan, Jindong Wang, Tao Qin, Microsoft Research Asia, China; Bo Xu, Institute of Automation, Chinese Academy of Sciences, China | ||
Session | SPE-48: Speech Recognition 18: Low Resource ASR | ||
Location | Gather.Town | ||
Session Time: | Friday, 11 June, 11:30 - 12:15 | ||
Presentation Time: | Friday, 11 June, 11:30 - 12:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-GASR] General Topics in Speech Recognition | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features (e.g., mel-spectrograms or MFCC) as the input, and recognizing both text sequences, where the two recognition losses use the same combination weight. We apply MixSpeech on two popular end-to-end speech recognition models including LAS (Listen, Attend and Spell) and Transformer, and conduct experiments on several low-resource datasets including TIMIT, WSJ, and HKUST. Experimental results show that MixSpeech achieves better accuracy than the baseline models without data augmentation, and outperforms a strong data augmentation method SpecAugment on these recognition tasks. Specifically, MixSpeech outperforms SpecAugment with a relative PER improvement of 10.6% on TIMIT dataset, and achieves a strong WER of 4.7% on WSJ dataset. |