Knowledge Commons of Institute of Automation,CAS
Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition | |
Zhengkun Tian1,2; Jiangyan Yi1; Jianhua Tao1,2,3; Shuai Zhang1,2; Zhengqi Wen1 | |
发表期刊 | IEEE SIGNAL PROCESSING LETTERS |
2022-02 | |
页码 | 762-766 |
摘要 | The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded states, which is inefficient on GPUs. The non-autoregressive (NAR) models can get rid of the temporal dependency between the output tokens and predict the entire output tokens in one inference step. However, the NAR model still faces two major problems. Firstly, there is still a great gap in performance between the NAR models and the advanced AR models. Secondly, it's difficult for most of the NAR models to train and converge. We propose a hybrid autoregressive and non-autoregressive transformer (HANAT) model, which integrates AR and NAR models deeply by sharing parameters. We assume that the AR model will assist the NAR model to learn some linguistic dependencies and accelerate the convergence. Furthermore, the two-stage hybrid inference is applied to improve the model performance. All the experiments are conducted on a mandarin dataset ASIEHLL-1 and a english dataset librispeech-960 h. The results show that the HANAT can achieve a competitive performancewith the AR model and outperform many complicated NAR models. Besides, the RTF is only 1/5 of the AR model. |
收录类别 | SCI |
语种 | 英语 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48614 |
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 | Jiangyan Yi; Jianhua Tao |
作者单位 | 1.NLPR, 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,Jianhua Tao,et al. Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition[J]. IEEE SIGNAL PROCESSING LETTERS,2022:762-766. |
APA | Zhengkun Tian,Jiangyan Yi,Jianhua Tao,Shuai Zhang,&Zhengqi Wen.(2022).Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition.IEEE SIGNAL PROCESSING LETTERS,762-766. |
MLA | Zhengkun Tian,et al."Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition".IEEE SIGNAL PROCESSING LETTERS (2022):762-766. |
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 | ||
Hybrid_Autoregressiv(934KB) | 期刊论文 | 作者接受稿 | 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