We propose a novel 2-stage sub 8-bit quantization aware training algorit...
Traditional goal-oriented dialogue systems rely on various components su...
Large scale machine learning (ML) systems such as the Alexa automatic sp...
This is a report of our lessons learned building acoustic models from 1
...
The use of spatial information with multiple microphones can improve
far...
Conventional far-field automatic speech recognition (ASR) systems typica...
Statistical TTS systems that directly predict the speech waveform have
r...
Accurate on-device keyword spotting (KWS) with low false accept and fals...
We propose a max-pooling based loss function for training Long Short-Ter...