ASR Error Correction and Domain Adaptation Using Machine Translation
Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch is still an issue for many such parties that want to use thi...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an
increasingly viable service for companies of any size building speech-based
products. While these ASR systems are trained on large amounts of data, domain
mismatch is still an issue for many such parties that want to use this service
as-is leading to not so optimal results for their task. We propose a simple
technique to perform domain adaptation for ASR error correction via machine
translation. The machine translation model is a strong candidate to learn a
mapping from out-of-domain ASR errors to in-domain terms in the corresponding
reference files. We use two off-the-shelf ASR systems in this work: Google ASR
(commercial) and the ASPIRE model (open-source). We observe 7% absolute
improvement in word error rate and 4 point absolute improvement in BLEU score
in Google ASR output via our proposed method. We also evaluate ASR error
correction via a downstream task of Speaker Diarization that captures speaker
style, syntax, structure and semantic improvements we obtain via ASR
correction. |
---|---|
DOI: | 10.48550/arxiv.2003.07692 |