تقرير
PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems
| العنوان: | PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems |
|---|---|
| المؤلفون: | Mitsui, Kentaro, Mitsuda, Koh, Wakatsuki, Toshiaki, Hono, Yukiya, Sawada, Kei |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response requires the prior generation of a written response, and (2) speech sequences are significantly longer than text sequences. This study addresses these issues by extending the input and output sequences of the language model to support the parallel generation of text and speech. Our experiments on spoken question answering tasks demonstrate that our approach improves latency while maintaining the quality of response content. Additionally, we show that latency can be further reduced by generating speech in multiple sequences. Demo samples are available at https://rinnakk.github.io/research/publications/PSLM. Comment: 8 pages, 4 figures, 4 tables, demo samples: https://rinnakk.github.io/research/publications/PSLM |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2406.12428 |
| رقم الأكسشن: | edsarx.2406.12428 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |