Retrieve and Copy: Scaling ASR Personalization to Large Catalogs
Sai Muralidhar Jayanthi, Devang Kulshreshtha, Saket Dingliwal, Srikanth Ronanki, Sravan Bodapati
Abstract
Personalization of automatic speech recognition (ASR) models is a widely studied topic because of its many practical applications. Most recently, attention-based contextual biasing techniques are used to improve the recognition of rare words and/or domain specific entities. However, due to performance constraints, the biasing is often limited to a few thousand entities, restricting real-world usability. To address this, we first propose a “Retrieve and Copy” mechanism to improve latency while retaining the accuracy even when scaled to a large catalog. We also propose a training strategy to overcome the degradation in recall at such scale due to an increased number of confusing entities. Overall, our approach achieves up to 6% more Word Error Rate reduction (WERR) and 3.6% absolute improvement in F1 when compared to a strong baseline. Our method also allows for large catalog sizes of up to 20K without significantly affecting WER and F1-scores, while achieving at least 20% inference speedup per acoustic frame.- Anthology ID:
- 2023.emnlp-industry.60
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Mingxuan Wang, Imed Zitouni
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 631–639
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-industry.60
- DOI:
- 10.18653/v1/2023.emnlp-industry.60
- Cite (ACL):
- Sai Muralidhar Jayanthi, Devang Kulshreshtha, Saket Dingliwal, Srikanth Ronanki, and Sravan Bodapati. 2023. Retrieve and Copy: Scaling ASR Personalization to Large Catalogs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 631–639, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Retrieve and Copy: Scaling ASR Personalization to Large Catalogs (Jayanthi et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2023.emnlp-industry.60.pdf