Meng, Yan and Mihajlik, Péter (2024) Assessing the Efficacy of Adapters in Cross-Language Transfer Learning For Low-Resource Automatic Speech Recognition. INFOCOMMUNICATIONS JOURNAL, 16 (4). pp. 2-9. ISSN 2061-2079
|
Text
InfocomJournal_2024_4_1.pdf - Published Version Download (745kB) | Preview |
Abstract
In recent years, the application of adapter modules in large language models proved to be successful in reducing computing and memory costs during fine-tuning. In our paper, we apply adapters to the field of automatic speech recognition. Specifically, we add adapters to different pre-trained speech recognition models to evaluate their efficiency in cross-language transfer learning. In this study, the evaluations are extended to GPU memory consumption, training duration, and recognition accuracy. By comparing the effects of adapters added to different models, we further explore the impact of whether the foundational model was (pre-) trained in the target language.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Adapters, Whisper, Conformer, Fast Conformer, Cross-lingual transfer learning, speech recognition |
| Subjects: | P Language and Literature / nyelvészet és irodalom > P0 Philology. Linguistics / filológia, nyelvészet Q Science / természettudomány > QA Mathematics / matematika > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány Q Science / természettudomány > QA Mathematics / matematika > QA76 Computer software / programozás |
| SWORD Depositor: | MTMT SWORD |
| Depositing User: | MTMT SWORD |
| Date Deposited: | 13 Jan 2025 17:33 |
| Last Modified: | 13 Jan 2025 17:33 |
| URI: | https://real.mtak.hu/id/eprint/213405 |
Actions (login required)
 |
Edit Item |
