9 papers
Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment
Kuang Wang, Lai Wei, Ping Lin +8
Speech Language Models (SLMs) exhibit strong semantic understanding, yet often fail to translate this capacity into expressive acoustic realization, producing speech with flattened…
Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems
Siyuan Liu, Jiahui Xu, Feng Jiang +6
Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradig…
CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation
Rui Ke, Jiahui Xu, Shenghao Yang +3
Theme detection is a fundamental task in user-centric dialogue systems, aiming to identify the latent topic of each utterance without relying on predefined schemas. Unlike intent i…
Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles
Kuang Wang, Xianfei Li, Shenghao Yang +3
User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language…
Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations
Li Zhou, Hao Jiang, Junjie Li +4
Explicit structural information has been proven to be encoded by Graph Neural Networks (GNNs), serving as auxiliary knowledge to enhance model capabilities and improve performance…
Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models
Ziche Liu, Rui Ke, Yajiao Liu +2
Data selection for fine-tuning large language models (LLMs) aims to choose a high-quality subset from existing datasets, allowing the trained model to outperform baselines trained…