Knowledge Commons of Institute of Automation,CAS
Synchronous Transformers for end-to-end Speech Recognition | |
Zhengkun Tian![]() ![]() ![]() ![]() ![]() ![]() | |
2020 | |
会议名称 | 45th IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP 2020) |
会议日期 | 2020.05.04-2020.05.08 |
会议地点 | Barcelona, Spain |
摘要 | For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these models difficult to be applied for online speech recognition. In this paper, we propose a model named synchronous transformer to address this problem, which can predict the output sequence chunk by chunk. Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately. During training, a forward-backward algorithm is introduced to optimize all the possible alignment paths. Our model is evaluated on a Mandarin dataset AISHELL-1. The experiments show that the synchronous transformer is able to perform encoding and decoding synchronously, and achieves a character error rate of 8.91% on the test set. |
七大方向——子方向分类 | 语音识别与合成 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40666 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
作者单位 | 1.中国科学院自动化研究所; 2.中国科学院大学 |
推荐引用方式 GB/T 7714 | Zhengkun Tian,Jiangyan Yi,Ye Bai,et al. Synchronous Transformers for end-to-end Speech Recognition[C],2020. |
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 | ||
6会议-Synchronous Tran(496KB) | 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