Multi-Modal Retrieval For Large Language Model Based Speech Recognition

Aditya Gourav, Jari Kolehmainen, Prashanth Shivakumar, Yile Gu, Grant Strimel, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko

Abstract
Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other modalities in retrieval as well for applications across the wide spectrum of machine learning tasks and data types. In this work, we propose multi-modal retrieval with two approaches: kNN-LM and cross-attention techniques. We demonstrate the effectiveness of our retrieval approaches empirically by applying them to automatic speech recognition tasks with access to external information. Under this setting, we show that speech-based multi-modal retrieval outperforms text based retrieval, and yields up to improvement in word error rate over the multi-modal language model baseline. Furthermore, we achieve state-of-the-art recognition results on the Spoken-Squad question answering dataset.
Anthology ID:
2024.findings-acl.262
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4435–4446
Language:
URL:
https://aclanthology.org/2024.findings-acl.262
DOI:
10.18653/v1/2024.findings-acl.262
Bibkey:
Cite (ACL):
Aditya Gourav, Jari Kolehmainen, Prashanth Shivakumar, Yile Gu, Grant Strimel, Ankur Gandhe, Ariya Rastrow, and Ivan Bulyko. 2024. Multi-Modal Retrieval For Large Language Model Based Speech Recognition. In Findings of the Association for Computational Linguistics ACL 2024, pages 4435–4446, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Multi-Modal Retrieval For Large Language Model Based Speech Recognition (Gourav et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.262.pdf
PDF Search