
There is a more recent version of this eprint available. Click here to view it.
Farooq, M.U. orcid.org/0000-0002-6610-0923, Ahmad, R. and Hain, T. orcid.org/0000-0003-0939-3464 (Submitted: 2023) MUST: a multilingual student-teacher learning approach for low-resource speech recognition. [Preprint - arXiv] (Submitted)
Abstract
Student-teacher learning or knowledge distillation (KD) has been previously used to address data scarcity issue for training of speech recognition (ASR) systems. However, a limitation of KD training is that the student model classes must be a proper or improper subset of the teacher model classes. It prevents distillation from even acoustically similar languages if the character sets are not same. In this work, the aforementioned limitation is addressed by proposing a MUltilingual Student-Teacher (MUST) learning which exploits a posteriors mapping approach. A pre-trained mapping model is used to map posteriors from a teacher language to the student language ASR. These mapped posteriors are used as soft labels for KD learning. Various teacher ensemble schemes are experimented to train an ASR model for low-resource languages. A model trained with MUST learning reduces relative character error rate (CER) up to 9.5% in comparison with a baseline monolingual ASR.
Metadata
Item Type: | Preprint |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 The Author(s). This preprint is made available under a Creative Commons Attribution 4.0 International License. (https://creativecommons.org/licenses/by/4.0/) |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 07 Aug 2025 16:07 |
Last Modified: | 07 Aug 2025 16:07 |
Status: | Submitted |
Identification Number: | 10.48550/arXiv.2310.18865 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:230205 |
Available Versions of this Item
- MUST: a multilingual student-teacher learning approach for low-resource speech recognition. (deposited 07 Aug 2025 16:07) [Currently Displayed]