Knowledge Commons of Institute of Automation,CAS
CIF-Based Collaborative Decoding for End-to-End Contextual Speech Recognition | |
Minglun Han1,2; Linhao Dong1; Shiyu Zhou1; Bo Xu1,2 | |
2021-05 | |
会议名称 | ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
会议日期 | 2021-06-06 |
会议地点 | Toronto, Canada |
摘要 | End-to-end (E2E) models have achieved promising results on multiple speech recognition benchmarks, and shown the potential to become the mainstream. However, the unified structure and the E2E training hamper injecting context information into them for contextual biasing. Though contextual LAS (CLAS) gives an excellent all-neural solution, the degree of biasing to given contextual information is not explicitly controllable. In this paper, we focus on incorporating contextual information into the continuous integrate-and-fire (CIF) based model that supports contextual biasing in a more controllable fashion. Specifically, an extra context processing network is introduced to extract contextual embeddings, integrate acoustically relevant contextual information and decode the contextual output distribution, thus forming a collaborative decoding with the decoder of the CIF-based model. Evaluated on the named entity rich evaluation sets of HKUST/AISHELL-2, our method brings relative character error rate (CER) reduction of 8.83%/21.13% and relative named entity character error rate (NE-CER) reduction of 40.14%/51.50% when compared with a strong baseline. Besides, it keeps the performance on original evaluation set without degradation. |
关键词 | Contextual Speech Recognition Automatic Speech Recognition Context Biasing |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 是 |
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 | 语音语言处理 |
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/173211/51692 |
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.中国科学院自动化研究所 2.中国科学院大学人工智能学院 |
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 | Minglun Han,Linhao Dong,Shiyu Zhou,et al. CIF-Based Collaborative Decoding for End-to-End Contextual 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 | ||
CIF_BASED_COLLABORAT(469KB) | 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