تقرير
Investigating Decoder-only Large Language Models for Speech-to-text Translation
العنوان: | Investigating Decoder-only Large Language Models for Speech-to-text Translation |
---|---|
المؤلفون: | Huang, Chao-Wei, Lu, Hui, Gong, Hongyu, Inaguma, Hirofumi, Kulikov, Ilia, Mavlyutov, Ruslan, Popuri, Sravya |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
الوصف: | Large language models (LLMs), known for their exceptional reasoning capabilities, generalizability, and fluency across diverse domains, present a promising avenue for enhancing speech-related tasks. In this paper, we focus on integrating decoder-only LLMs to the task of speech-to-text translation (S2TT). We propose a decoder-only architecture that enables the LLM to directly consume the encoded speech representation and generate the text translation. Additionally, we investigate the effects of different parameter-efficient fine-tuning techniques and task formulation. Our model achieves state-of-the-art performance on CoVoST 2 and FLEURS among models trained without proprietary data. We also conduct analyses to validate the design choices of our proposed model and bring insights to the integration of LLMs to S2TT. Comment: Accepted to Interspeech 2024 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2407.03169 |
رقم الأكسشن: | edsarx.2407.03169 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |