7 papers
Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR
Yuan Xie, Jiaqi Song, Xianliang Wang +3
Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achiev…
NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
Yuan Xie, Jiaqi Song, Guang Qiu +9
Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a mainstream paradigm in recent years. Although existing LLM-based ASR models demonstrat…
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
Yuan Xie, Jiaqi Song, Guang Qiu +4
Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a dominant paradigm. Although recent LLM-based ASR models have shown promising performan…
HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention
Yufei Xu, Fanxu Meng, Fan Jiang +11
Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a…
DHI: Leveraging Diverse Hallucination Induction for Enhanced Contrastive Factuality Control in Large Language Models
Jiani Guo, Xiangke Zeng, Jie Wu +1
Large language models (LLMs) frequently produce inaccurate or fabricated information, known as "hallucinations," which compromises their reliability. Existing approaches often trai…
SongSage: A Large Musical Language Model with Lyric Generative Pre-training
Jiani Guo, Jiajia Li, Jie Wu +3
Large language models have achieved significant success in various domains, yet their understanding of lyric-centric knowledge has not been fully explored. In this work, we first i…