Conformer models maintain a large number of internal states, the vast
ma...
Unsupervised pre-training is now the predominant approach for both text ...
We summarize the results of a host of efforts using giant automatic spee...
Building ASR models across many language families is a challenging multi...
End-to-end (E2E) models have shown to outperform state-of-the-art
conven...
Streaming automatic speech recognition (ASR) aims to emit each hypothesi...
Streaming automatic speech recognition (ASR) aims to emit each hypothesi...
In automatic speech recognition (ASR), model pruning is a widely adopted...
Recently Transformer and Convolution neural network (CNN) based models h...
Convolutional neural networks (CNN) have shown promising results for
end...