Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition

Yash Jain, David M. Chan, Pranav Dheram, Aparna Khare, Olabanji Shonibare, Venkatesh Ravichandran, Shalini Ghosh

Abstract
Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks. Existing multi-modal pre-training methods for the ASR task have primarily focused on single-stage pre-training where a single unsupervised task is used for pre-training followed by fine-tuning on the downstream task. In this work, we introduce a novel method combining multi-modal and multi-task unsupervised pre-training with a translation-based supervised mid-training approach. We empirically demonstrate that such a multi-stage approach leads to relative word error rate (WER) improvements of up to 38.45% over baselines on both Librispeech and SUPERB. Additionally, we share several important findings for choosing pre-training methods and datasets.
Anthology ID:
2024.lrec-main.1045
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
11969–11980
Language:
URL:
https://aclanthology.org/2024.lrec-main.1045
DOI:
Bibkey:
Cite (ACL):
Yash Jain, David M. Chan, Pranav Dheram, Aparna Khare, Olabanji Shonibare, Venkatesh Ravichandran, and Shalini Ghosh. 2024. Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11969–11980, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition (Jain et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1045.pdf
PDF Search