Abstract
On-device automatic speech recognition systems face several challenges compared to server-based systems. They have to meet stricter constraints in terms of speed, disk size and memory while maintaining the same accuracy. Often they have to serve several ap- plications with different distributions at once, such as communicating with a virtual assistant and speech-to-text. The simplest solution to serve multiple applications is to build application-specific (language) models, but this leads to an increase in memory. Therefore, we explore different data- and architecture-driven language modeling approaches to build a single application-agnostic model. We propose two novel feed-forward architectures that find an optimal trade off between different on-device constraints. In comparison to the application-specific solution, one of our novel approaches reduces the disk size by half, while maintaining speed and accuracy of the original model.- Anthology ID:
- 2023.acl-industry.25
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 268–275
- Language:
- URL:
- https://aclanthology.org/2023.acl-industry.25
- DOI:
- Cite (ACL):
- Markus Nussbaum-thom, Lyan Verwimp, and Youssef Oualil. 2023. Application-Agnostic Language Modeling for On-Device ASR. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 268–275, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Application-Agnostic Language Modeling for On-Device ASR (Nussbaum-thom et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2023.acl-industry.25.pdf