Picture for Zhi-Hao Lai

Zhi-Hao Lai

Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding

Add code
May 23, 2023
Figure 1 for Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding
Figure 2 for Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding
Figure 3 for Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding
Figure 4 for Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding
Viaarxiv icon