Segmenting Subtitles for Correcting ASR Segmentation Errors
Abstract
Typical ASR systems segment the input audio into utterances using purely acoustic information, which may not resemble the sentence-like units that are expected by conventional machine translation (MT) systems for Spoken Language Translation. In this work, we propose a model for correcting the acoustic segmentation of ASR models for low-resource languages to improve performance on downstream tasks. We propose the use of subtitles as a proxy dataset for correcting ASR acoustic segmentation, creating synthetic acoustic utterances by modeling common error modes. We train a neural tagging model for correcting ASR acoustic segmentation and show that it improves downstream performance on MT and audio-document cross-language information retrieval (CLIR).
Cite
@article{arxiv.2104.07868,
title = {Segmenting Subtitles for Correcting ASR Segmentation Errors},
author = {David Wan and Chris Kedzie and Faisal Ladhak and Elsbeth Turcan and Petra Galuščáková and Elena Zotkina and Zhengping Jiang and Peter Bell and Kathleen McKeown},
journal= {arXiv preprint arXiv:2104.07868},
year = {2021}
}