Transformer-based end-to-end speech recognition has achieved great succe...
The objective of this work is to develop a speaker recognition model to ...
This paper proposes a method for improved CTC inference with searched
in...
RNN-Transducer has been one of promising architectures for end-to-end
au...
Non-autoregressive (NAR) models simultaneously generate multiple outputs...
Deploying an end-to-end automatic speech recognition (ASR) model on
mobi...
We present a simple and efficient auxiliary loss function for automatic
...