Report
Unified Modeling of Multi-Domain Multi-Device ASR Systems
| العنوان: | Unified Modeling of Multi-Domain Multi-Device ASR Systems |
|---|---|
| المؤلفون: | Mitra, Soumyajit, Ray, Swayambhu Nath, Padi, Bharat, Sen, Arunasish, Bilgi, Raghavendra, Arsikere, Harish, Ghosh, Shalini, Srinivasamurthy, Ajay, Garimella, Sri |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | Modern Automatic Speech Recognition (ASR) systems often use a portfolio of domain-specific models in order to get high accuracy for distinct user utterance types across different devices. In this paper, we propose an innovative approach that integrates the different per-domain per-device models into a unified model, using a combination of domain embedding, domain experts, mixture of experts and adversarial training. We run careful ablation studies to show the benefit of each of these innovations in contributing to the accuracy of the overall unified model. Experiments show that our proposed unified modeling approach actually outperforms the carefully tuned per-domain models, giving relative gains of up to 10% over a baseline model with negligible increase in the number of parameters. Comment: We will update the paper completely with our latest experiments and analysis |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2205.06655 |
| رقم الانضمام: | edsarx.2205.06655 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |