Automatic speech recognition (ASR) based on transducers is widely used. ...
Audio codec models are widely used in audio communication as a crucial
t...
Sequence-to-Sequence (seq2seq) tasks transcribe the input sequence to a
...
Despite the rapid progress in automatic speech recognition (ASR) researc...
Dominant researches adopt supervised training for speaker extraction, wh...
In automatic speech recognition (ASR) research, discriminative criteria ...
Despite the rapid progress of end-to-end (E2E) automatic speech recognit...
Recently, End-to-End (E2E) frameworks have achieved remarkable results o...
Transformer-based self-supervised models are trained as feature extracto...
LSTM language model is an essential component of industrial ASR systems....