collaborators

17 papers

eess.AS2026

The SLT 2026 SmartGlasses Challenge: Benchmarking Egocentric Multi-Talker Speech Recognition and Understanding with Audio-Language Models

Dehui Gao, Zhixian Zhao, Zhennan Lin +14

Recent advances in large language models (LLMs) and multimodal LLMs (MLLMs) have created new opportunities for wearable speech interfaces, with smart glasses providing an egocentri…

eess.AS2026

Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models

Zhixian Zhao, Shuiyuan Wang, Wenjie Tian +3

While Audio Language Models (ALMs) demonstrate strong semantic understanding, they struggle with complex affective interactions. Specifically, textual semantic dominance often over…

eess.AS2026

S2Accompanist: A Semantic-Aware and Structure-Guided Diffusion Model for Music Accompaniment Generation

Huakang Chen, Wenkai Cheng, Guobin Ma +7

High-fidelity text-to-music generation typically relies on massive proprietary datasets and immense computational resources. Existing models often struggle to generate coherent pur…

eess.AS2026

Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model

Guojian Li, Zhixian Zhao, Zhennan Lin +9

While speech Large Language Models (LLMs) excel at conventional tasks like basic speech recognition, they lack fine-grained, multi-dimensional perception. This deficiency is eviden…

eess.AS2026

Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge

Chengyou Wang, Hongfei Xue, Guojian Li +6

Full-duplex interaction, where speakers and listeners converse simultaneously, is a key element of human communication often missing from traditional spoken dialogue systems. These…

eess.AS2026

HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models

Shuiyuan Wang, Zhixian Zhao, Hongfei Xue +5

Evaluating the emotional intelligence (EI) of audio language models (ALMs) is critical. However, existing benchmarks mostly rely on synthesized speech, are limited to single-turn i…