Knowledge Commons of Institute of Automation,CAS
One In A Hundred: Selecting the Best Predicted Sequence from Numerous Candidates for Speech Recognition | |
Zhengkun Tian1,2; Jiangyan Yi1; Ye Bai1,2; Jianhua Tao1,2,3; Shuai Zhang1,2; Zhengqi Wen1 | |
2021-12 | |
会议名称 | 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) |
会议日期 | 14-17 December 2021 |
会议地点 | Tokyo, Japan |
摘要 | The RNN - Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it cannot capture the linguistic dependencies between the output tokens. Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model. During inference, the CTC decoder first generates many candidates in a streaming fashion. Then the transformer decoder selects the best candidate based on the corresponding acoustic encoded states. The second -stage transformer decoder can be regarded as a conditional language model. We assume that a large enough number and enough diversity of candidates generated in the first stage can compensate the CTC model for the lack of language modeling ability. All the experiments are conducted on a Chinese Mandarin dataset AISHELL-l. The results show that our proposed model can implement streaming decoding in a fast and straightforward way. Our model can achieve up to a 20% reduction in the character error rate than the baseline CTC model. In addition, our model can also perform non-streaming inference with only a little performance degradation. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48606 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
通讯作者 | Jianhua Tao |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhengkun Tian,Jiangyan Yi,Ye Bai,et al. One In A Hundred: Selecting the Best Predicted Sequence from Numerous Candidates for 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 | ||
One_In_A_Hundred_Sel(563KB) | 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