4 papers
Sell More, Play Less: Benchmarking LLM Realistic Selling Skill
Xuanbo Su, Wenhao Hu, Haibo Su +4
Sales dialogues require multi-turn, goal-directed persuasion under asymmetric incentives, which makes them a challenging setting for large language models (LLMs). Yet existing dial…
CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation
Huan Shen, Yingao Wang, Shangkun Huang +2
Turn-taking modeling is fundamental to spoken dialogue systems, yet its evaluation remains fragmented and often limited to binary boundary detection under narrow interaction settin…
LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling
Xiaoyu Fan, Huizhi Xie, Wei Zou +1
Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech t…
CLAR: CIF-Localized Alignment for Retrieval-Augmented Speech LLM-Based Contextual ASR
Shangkun Huang, Huan Shen, Wei Zou +1
Speech LLM-based ASR often struggles with named entities and long-tail words due to strong internal language-model priors. Retrieval-augmented biasing can help, but its effectivene…