This work combines boundary interpretation and controlled reconstruction analysis by comparing predicted boundaries with linguistic and acoustic references and finds that boundary meaning depends on the underlying speech representation.
Han Wang, Jia-Qi Li, Ying Shen et al.· 0 citations
EvoAudio is proposed, a recursive self-improvement system for audio understanding that is the first to evolve the model, waveforms, questions, and difficulty in one closed loop.
While Chain-of-Thought (CoT) reasoning has improved the capability of language models, directly applying it to Spoken Language Models (SLMs) may introduce long silent intervals under the serial"think-then-speak"paradigm, disrupting real-time spoken interaction. To address this issue, we propose an asynchronous think-al...
Junyi Ao, Kainan Peng, Mingbo Ma et al.· 0 citations
Decoupled-Live-ProsodyJudge (D-LPJ), a cost-effective pairwise evaluator distilled from Gemini into Qwen3-Omni, and a novel span-local GRPO strategy that applies normalized advantages strictly to their corresponding rationale spans.
Zi-Fan Guan, Long-Yu Lu, Ju-Nan Zhang et al.· 0 citations
CoReLoop is proposed, which enables controlled recurrent refinement through loop-specific LoRA and lightweight modules that adapt recurrent inputs, regulate state updates, and align refined representations with the frozen classifier.
Kun-Yu Feng, Yu-Xiang Wang, Li Wang et al.· 2 citations
Prompt-conditioned piano MIDI-to-Music rendering aims to faithfully render target notes while reproducing the timbre of a reference recording. Existing approaches primarily follow two paradigms: autoregressive (AR) modeling and flow matching (or diffusion). Discrete-codec AR models provide causal temporal modeling, but...
Tffic-Audio is presented, a general speech deepfake detection system designed for comprehensive evaluation environment that achieves a pooled EER of 1.454% on the 14 test sets of Speech-DF-Arena, outperforming all currently public systems on the leaderboard.
Wan Lin, Li Wang, Jin-Dong Wang et al.· arXiv.org· 1 citation
ParaBridge is proposed, an on-policy self-distillation method that turns a brittle inference-time scaffold into stable model behavior and generalizes to unseen paralinguistic cues, transfers from safety-oriented training to empathy-oriented dialogue, and works on a different SLM backbone.
Yuxiang Wang, Qin-Ke Ni, Sheng-Bo Cai et al.· arXiv.org· 2 citations
RecurTrace introduces Loop Memory Attention, which lets each looped layer attend to its own states from previous iterations along the loop-time axis, so the model can revisit earlier computations instead of relying on the latest state alone.
Yu-Xiang Wang, Kun-Yu Feng, Ying-Da Shen et al.· 7 citations
The VoxPrivacy benchmark, the large-scale training set, the fine-tuned model to foster the development of safer and more context-aware SLMs, and a viable path forward are demonstrated: by fine-tuning on a new 4,000-hour training set, improve privacy-preserving abilities while maintaining robustness.