Streaming Speech-to-Confusion Network Speech Recognition

no code implementations • 2 Jun 2023 • Denis Filimonov, Prabhat Pandey, Ariya Rastrow, Ankur Gandhe, Andreas Stolcke

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Lattention: Lattice-attention in ASR rescoring

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) +3