research
∙
07/26/2023
Say Goodbye to RNN-T Loss: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition
RNN-T models are widely used in ASR, which rely on the RNN-T loss to ach...
share
research
∙
05/24/2023
InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition
The local and global features are both essential for automatic speech re...
research
∙
05/23/2023
Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding
Attention-based encoder-decoder (AED) models have shown impressive perfo...
research
∙
09/14/2021