Knowledge Commons of Institute of Automation,CAS
Mixspeech: Data augmentation for low-resource automatic speech recognition | |
Meng Linghui1,2![]() | |
2021-06 | |
会议名称 | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021. |
会议日期 | 2021.6.6-2021.6.11 |
会议地点 | Toronto, Canada |
摘要 | 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. |
七大方向——子方向分类 | 语音识别与合成 |
国重实验室规划方向分类 | 人机混合智能 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57334 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Meng Linghui,Xu Jin,Tan Xu,et al. Mixspeech: Data augmentation for low-resource automatic speech recognition[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
mixspeech_full_paper(1111KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论