activity
20242026
collaborators

20 papers

cs.SD2026

SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision

Rongshen He, Xinyu Liang, Dekun Chen +3

Long-form streaming speech-to-speech translation (S2ST) requires incremental, unbounded translation under strict latency constraints. Existing methods typically suffer from sentenc…

cs.SD2026

FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates

Jiaqi Li, Chaoren Wang, Xiaohai Tian +9

Spoken language models (SLMs) extend LLMs to speech input and output. Existing SLMs represent speech at fixed frame rates (e.g., 25 or 12.5 Hz), ignoring the time-varying informati…

cs.SD2026

VoxSafeBench: Not Just What Is Said, but Who, How, and Where

Yuxiang Wang, Hongyu Liu, Yijiang Xu +9

As speech language models (SLMs) transition from personal devices into shared, multi-user environments, their responses must account for far more than the words alone. Who is speak…

cs.SD2026

MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora

Tao Feng, Yuxiang Wang, Yuancheng Wang +5

Voice imitation aims to transform source speech to match a reference speaker's timbre and speaking style while preserving linguistic content. A straightforward approach is to train…

cs.SD2026

NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation

Qinke Ni, Huan Liao, Dekun Chen +2

While recent text-to-speech (TTS) systems increasingly integrate nonverbal vocalizations (NVs), their evaluations lack standardized metrics and reliable ground-truth references. To…

cs.SD2026

Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation

Xueyao Zhang, Junan Zhang, Yuancheng Wang +5

Controllable human voice generation, particularly for expressive domains like singing, remains a significant challenge. This paper introduces Vevo2, a unified framework for control…