Sasindran, Z and Yelchuri, H and Tamma, PV and Rao, P (2023) MobileASR: A resource-aware on-device learning framework for user voice personalization applications on mobile phones. In: 3rd International Conference on AI-ML Systems, AIMLSystems 2023, 25 October 2023 through 28 October 2023, Bangalore.
|
PDF
acm_int_con_pro_ser_2023.pdf - Published Version Download (2MB) | Preview |
Abstract
We describe a comprehensive methodology for developing user-voice personalized automatic speech recognition (ASR) models by effectively training models on mobile phones, allowing user data and models to be stored and used locally. To achieve this, we propose a resource-aware sub-model-based training approach that considers the RAM, and battery capabilities of mobile phones. By considering the evaluation metric and resource constraints of the mobile phones, we are able to perform efficient training and halt the process accordingly. To simulate real users, we use speakers with various accents. The entire on-device training and evaluation framework was then tested on various mobile phones across brands. We show that fine-tuning the models and selecting the right hyperparameter values is a trade-off between the lowest achievable performance metric, on-device training time, and memory consumption. Overall, our methodology offers a comprehensive solution for developing personalized ASR models while leveraging the capabilities of mobile phones, and balancing the need for accuracy with resource constraints. © 2023 ACM.
| Item Type: | Conference Paper |
|---|---|
| Publication: | ACM International Conference Proceeding Series |
| Publisher: | Association for Computing Machinery |
| Additional Information: | The copyright for this article belongs to authors. |
| Keywords: | Cellular telephones; Economic and social effects; Random access storage, Automatic speech recognition; Learning frameworks; Model Adaptation; On-device personalization; On-device training; Personalizations; Recognition models; Resource aware; Resource Constraint; Stopping criterion, Speech recognition |
| Department/Centre: | Division of Electrical Sciences > Electronic Systems Engineering (Formerly Centre for Electronic Design & Technology) |
| Date Deposited: | 22 Aug 2024 06:17 |
| Last Modified: | 22 Aug 2024 06:17 |
| URI: | http://eprints.iisc.ac.in/id/eprint/85497 |
Actions (login required)
 |
View Item |
