no code implementations • 19 Nov 2021 • Prabhat Pandey, Sergio Duarte Torres, Ali Orkan Bayer, Ankur Gandhe, Volker Leutnant
The rescoring model with attention to lattices achieves 4-5% relative word error rate reduction over first-pass and 6-8% with attention to both lattices and acoustic features.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4