Machine learning model weights and activations are represented in
full-p...
For on-device automatic speech recognition (ASR), quantization aware tra...
The recurrent neural network transducer (RNN-T) is a prominent streaming...
We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme...
Dialogue act classification (DAC) is a critical task for spoken language...
Recent years have seen significant advances in end-to-end (E2E) spoken
l...