Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling release_g54avqptmfa3xl3gr73mqkicwa

by Prashanth Gurunath Shivakumar, Haoqi Li, Kevin Knight, Panayiotis Georgiou

Released as a article .

2019  

Abstract

Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example pruning words due to acoustics using short-term context, prior to rescoring with long-term context based on linguistics. In this work we model ASR as a phrase-based noisy transformation channel and propose an error correction system that can learn from the aggregate errors of all the independent modules constituting the ASR and attempt to invert those. The proposed system can exploit long-term context using a neural network language model and can better choose between existing ASR output possibilities as well as re-introduce previously pruned or unseen (out-of-vocabulary) phrases. It provides corrections under poorly performing ASR conditions without degrading any accurate transcriptions; such corrections are greater on top of out-of-domain and mismatched data ASR. Our system consistently provides improvements over the baseline ASR, even when baseline is further optimized through recurrent neural network language model rescoring. This demonstrates that any ASR improvements can be exploited independently and that our proposed system can potentially still provide benefits on highly optimized ASR. Finally, we present an extensive analysis of the type of errors corrected by our system.
In text/plain format

Archived Files and Locations

application/pdf  424.3 kB
file_yut4dpr4xjgplfkswm7qy2mb6m
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-03-28
Version   v2
Language   en ?
arXiv  1802.02607v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 8fcba830-7800-4a49-9b46-89c61c644fa9
API URL: JSON