Mixture Encoder for Joint Speech Separation and Recognition

CoRR(2023)

引用 0|浏览22
暂无评分
摘要
Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate speakers and recognize each of them with a single-speaker ASR system. End-to-end models process overlapped speech directly in a single, powerful neural network. This work proposes a middle-ground approach that leverages explicit speech separation similarly to the modular approach but also incorporates mixture speech information directly into the ASR module in order to mitigate the propagation of errors made by the speech separator. We also explore a way to exchange cross-speaker context information through a layer that combines information of the individual speakers. Our system is optimized through separate and joint training stages and achieves a relative improvement of 7% in word error rate over a purely modular setup on the SMS-WSJ task.
更多
查看译文
关键词
joint speech separation,mixture,recognition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要