7 papers · 1 filter
Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning
Wenjie Tian, Mingchen Shao, Bingshen Mu +8
Audio-visual speech recognition (AVSR) is an extension of ASR that incorporates visual signals. Current AVSR approaches primarily focus on lip motion, largely overlooking rich cont…
WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem
Chengyou Wang, Mingchen Shao, Jingbin Hu +11
Speech processing for low-resource dialects remains a fundamental challenge in developing inclusive and robust speech technologies. Despite its linguistic significance and large sp…
Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
Mingchen Shao, Bingshen Mu, Chengyou Wang +4
Speech large language models (SLLMs) built on speech encoders, adapters, and LLMs demonstrate remarkable multitask understanding performance in high-resource languages such as Engl…
OSUM-EChat: Enhancing End-to-End Empathetic Spoken Chatbot via Understanding-Driven Spoken Dialogue
Xuelong Geng, Qijie Shao, Hongfei Xue +20
Empathy is crucial in enabling natural interactions within spoken dialogue systems, allowing machines to recognize and respond appropriately to paralinguistic cues such as age, gen…
Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR
Mingchen Shao, Xinfa Zhu, Chengyou Wang +6
Despite remarkable achievements, automatic speech recognition (ASR) in low-resource scenarios still faces two challenges: high-quality data scarcity and high computational demands.…
OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
Xuelong Geng, Kun Wei, Qijie Shao +18
Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable compreh…