Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
/ Authors
Ye Bai, Jingping Chen, Jitong Chen, Wei Chen, Zhuo Chen, Chen Ding, Linhao Dong, Qianqian Dong, Yujiao Du, Kepan Gao
and 45 more authors
Lu Gao, Yi Guo, Minglun Han, Ting Han, Wenchao Hu, Xinying Hu, Yuxiang Hu, Deyu Hua, Lu Huang, Ming Huang, Youjia Huang, Jishuo Jin, Fanliu Kong, Zongwei Lan, Tianyue Li, Xiaoyang Li, Zeyang Li, Zehua Lin, Rui Liu, Shouda Liu, Lu Lu, Yi-Han Lu, Jing-Xia Ma, Sheng Ma, Yulin Pei, Chen Shen, Tian Tan, Xiaogang Tian, Ming Tu, Boyuan Wang, Hao Wang, Yuping Wang, Yuxuan Wang, H. Xia, Rui Xia, Shu-Yang Xie, Hong-Gen Xu, Menglin Yang, Bihong Zhang, Jun Zhang, Wanyi Zhang, Yang Zhang, Yawei Zhang, Yi-Jing Zheng, Ming Zou
/ Abstract
Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLMs by inputting continuous speech representations together with contextual information into the LLM. Through stage-wise large-scale training and the elicitation of context-aware capabilities in LLM, Seed-ASR demonstrates significant improvement over end-to-end models on comprehensive evaluation sets, including multiple domains, accents/dialects and languages. Additionally, Seed-ASR can be further deployed to support specific needs in various scenarios without requiring extra language models. Compared to recently released large ASR models, Seed-ASR achieves 10%-40% reduction in word (or character, for Chinese) error rates on Chinese and English public test sets, further demonstrating its powerful performance.
Journal: ArXiv