activity
20182022
most citedPsychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding

30 citations · 33 across the 4 of their papers we have counts for

collaborators
Showing 2022Show all

1 paper · 1 filter

cs.SD2022

Sub-8-bit quantization for on-device speech recognition: a regularization-free approach

Kai Zhen, Martin Radfar, Hieu Duy Nguyen +3

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Amon…