4 papers · 1 filter
TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
Qingshun She, Jing Peng, Yangui Fang +2
This work investigates bidirectional Mamba (BiMamba) for unified streaming and non-streaming automatic speech recognition (ASR). Dynamic chunk size training enables a single model…
MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
Junjie Li, Jing Peng, Yangui Fang +2
LLM-based ASR overcomes multilingual data scarcity by projecting speech representations into the LLM space to leverage its robust semantic and reasoning capabilities. However, whil…
TASU: Text-Only Alignment for Speech Understanding
Jing Peng, Yi Yang, Xu Li +5
Recent advances in Speech Large Language Models (Speech LLMs) have paved the way for unified architectures across diverse speech understanding tasks. However, prevailing alignment…
BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction
Haoran Wang, Jiatong Shi, Jinchuan Tian +3
Neural audio codecs have recently enabled high-fidelity reconstruction at high compression rates, especially for speech. However, speech and non-speech audio exhibit fundamentally…