Co-occurring keywords · papers mentioning both
end-to-end speech recognition
(3)
character error rate
(2)
multi-accent recognition
(1)
layer-adaptive fusion
(1)
multi-channel processing
(1)
on-device speech recognition
(1)
transformer transducer
(1)
long-context speech recognition
(1)
multi-channel transformer transducer
(1)
context-expanded transformer
(1)
Papers
Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition
Interspeech 2024
Advanced Long-Context End-to-End Speech Recognition Using Context-Expanded Transformers
Interspeech 2021
Multi-Channel Transformer Transducer for Speech Recognition
Interspeech 2021