تقرير
Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR
العنوان: | Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR |
---|---|
المؤلفون: | Khassanov, Yerbolat, Chen, Zhipeng, Chen, Tianfeng, Chong, Tze Yuang, Li, Wei, Zhang, Jun, Lu, Lu, Wang, Yuxuan |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Computation and Language |
الوصف: | This paper addresses challenges in integrating new languages into a pre-trained multilingual automatic speech recognition (mASR) system, particularly in scenarios where training data for existing languages is limited or unavailable. The proposed method employs a dual-pipeline with low-rank adaptation (LoRA). It maintains two data flow pipelines-one for existing languages and another for new languages. The primary pipeline follows the standard flow through the pre-trained parameters of mASR, while the secondary pipeline additionally utilizes language-specific parameters represented by LoRA and a separate output decoder module. Importantly, the proposed approach minimizes the performance degradation of existing languages and enables a language-agnostic operation mode, facilitated by a decoder selection strategy. We validate the effectiveness of the proposed method by extending the pre-trained Whisper model to 19 new languages from the FLEURS dataset Comment: 5 pages, 2 figures, 4 tables |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2406.07842 |
رقم الأكسشن: | edsarx.2406.07842 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |