activity
20242026
most citedChronological Thinking in Full-Duplex Spoken Dialogue Language Models

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing eess.ASShow all

6 papers · 1 filter

eess.AS2026

Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning

Yuxin Li, Donghang Wu, Guan-Ting Lin +4

Recent full-duplex spoken dialogue models have demonstrated compelling progress toward human-like interaction, enabling agents to respond with low latency, produce backchannels, an…

eess.AS2026

The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

Donghang Wu, Tianyu Zhang, Yuxin Li +4

During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always man…

eess.AS2026

Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency

Guan-Ting Lin, Chen Chen, Zhehuai Chen +1

We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use. Unlike prior work, our d…

eess.AS2025

From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology

Haoyang Li, Yuchen Hu, Chen Chen +3

Deep neural network (DNN)-based speech enhancement (SE) usually uses conventional activation functions, which lack the expressiveness to capture complex multiscale structures neede…

eess.AS2025

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

Jixun Yao, Hexin Liu, Chen Chen +3

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic informati…

eess.AS2025

SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis

Helin Wang, Meng Yu, Jiarui Hai +5

In this paper, we introduce SSR-Speech, a neural codec autoregressive model designed for stable, safe, and robust zero-shot textbased speech editing and text-to-speech synthesis. S…