Crossmodal ASR Error Correction with Discrete Speech Units

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yuanchao, Chen, Pinzhen, Bell, Peter, Lai, Catherine
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929499135803392
author Li, Yuanchao
Chen, Pinzhen
Bell, Peter
Lai, Catherine
author_facet Li, Yuanchao
Chen, Pinzhen
Bell, Peter
Lai, Catherine
contents ASR remains unsatisfactory in scenarios where the speaking style diverges from that used to train ASR systems, resulting in erroneous transcripts. To address this, ASR Error Correction (AEC), a post-ASR processing approach, is required. In this work, we tackle an understudied issue: the Low-Resource Out-of-Domain (LROOD) problem, by investigating crossmodal AEC on very limited downstream data with 1-best hypothesis transcription. We explore pre-training and fine-tuning strategies and uncover an ASR domain discrepancy phenomenon, shedding light on appropriate training schemes for LROOD data. Moreover, we propose the incorporation of discrete speech units to align with and enhance the word embeddings for improving AEC quality. Results from multiple corpora and several evaluation metrics demonstrate the feasibility and efficacy of our proposed AEC approach on LROOD data as well as its generalizability and superiority on large-scale data. Finally, a study on speech emotion recognition confirms that our model produces ASR error-robust transcripts suitable for downstream applications.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16677
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Crossmodal ASR Error Correction with Discrete Speech Units
Li, Yuanchao
Chen, Pinzhen
Bell, Peter
Lai, Catherine
Audio and Speech Processing
Computation and Language
Sound
ASR remains unsatisfactory in scenarios where the speaking style diverges from that used to train ASR systems, resulting in erroneous transcripts. To address this, ASR Error Correction (AEC), a post-ASR processing approach, is required. In this work, we tackle an understudied issue: the Low-Resource Out-of-Domain (LROOD) problem, by investigating crossmodal AEC on very limited downstream data with 1-best hypothesis transcription. We explore pre-training and fine-tuning strategies and uncover an ASR domain discrepancy phenomenon, shedding light on appropriate training schemes for LROOD data. Moreover, we propose the incorporation of discrete speech units to align with and enhance the word embeddings for improving AEC quality. Results from multiple corpora and several evaluation metrics demonstrate the feasibility and efficacy of our proposed AEC approach on LROOD data as well as its generalizability and superiority on large-scale data. Finally, a study on speech emotion recognition confirms that our model produces ASR error-robust transcripts suitable for downstream applications.
title Crossmodal ASR Error Correction with Discrete Speech Units
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2405.16677