2025/06/01 by Qichao Wang, Wang, Qichao, Ziqiao Meng +15 · 10 citations
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #Context (archaeology) #Exploit #FOS: Computer and information sciences #FOS: Electrical engineering #Generative grammar #Generative model #Inference #Language model #Language understanding #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and dialogue systems #Spoken language #Topic Modeling #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2506.00975
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the development of several SLMs that demonstrate promising results in this area. However, current approaches have yet to fully exploit dual-channel speech data, which inherently captures the structure and dynamics of human conversation. In this work, we systematically explore the use of dual-channel speech data in the context of modern large language models, and introduce a novel generative modeling paradigm, Next-Token-Pair Prediction (NTPP), to enable speaker-independent dual-channel spoken dialogue learning using decoder-only architectures for the first time. We evaluate our approach on standard benchmarks, and empirical results show that our proposed method, NTPP, significantly improves the conversational abilities of SLMs in terms of turn-taking prediction, response coherence, and naturalness. Moreover, compared to existing methods, NTPP achieves substantially lower inference latency, highlighting its practical efficiency for real-time applications.