Work

M-MoE: Mixture of Mixture-of-Expert Model for CTC-based Streaming Multilingual ASR

Year: 2025

Type: conference-paper

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10887679

Authors: Songjun Cao, Xiong Wang, Yike Zhang, Xiaoming Zhang, Long Ma

Institution: Tencent (China)

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4408345957

FWCI: 1.977

Cites: 34

Cited by: 2

Related to: 10