collaborators

6 papers

cs.CL2026

Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models

Yu-Xiang Lin, Cheng-Han Chiang, Hung-yi Lee

In this paper, we show that when spoken language models (SLMs) are instructed to speak in a specific speaking style at the beginning of a multi-turn conversation, they cannot maint…

cs.CL2026

STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models

Cheng-Han Chiang, Xiaofei Wang, Linjie Li +7

Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking proc…

cs.CL2025

SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models

Cheng-Han Chiang, Xiaofei Wang, Linjie Li +7

Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from i…

eess.AS2025

Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding

Tzu-wen Hsu, Ke-Han Lu, Cheng-Han Chiang +1

Large Audio-Language Models (LALMs) can take audio and text as the inputs and answer questions about the audio. While prior LALMs have shown strong performance on standard benchmar…

eess.AS2025

Audio-Aware Large Language Models as Judges for Speaking Styles

Cheng-Han Chiang, Xiaofei Wang, Chung-Ching Lin +8

Audio-aware large language models (ALLMs) can understand the textual and non-textual information in the audio input. In this paper, we explore using ALLMs as an automatic judge to…

cs.CL2025

TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge

Cheng-Han Chiang, Hung-yi Lee, Michal Lukasik

The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, where a numerical assessment is assigned by an LLM to the input text following scoring…