Chenda Li
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
A new framework called Geo-DConv is proposed to make multi-channel speech enhancement systems adaptable to diverse microphone array geometries by leveraging microphone coordinates.
This paper proposes a token-based generative speech separation framework that models multi-talker mixtures with speech language models.
Papers
SLM-SS: Token-Based Speech Separation with Speech Language Models
Chenda Li, Tianhua Li, Yiming Chen, Wei Wang +3 more
This paper proposes a token-based generative speech separation framework that models multi-talker mixtures with speech language models.