4 papers
VoiceWeaver: Staged Learning of Structured Controls for Expressive Speech and Sound-Event Generation
Xiaosu Su, Yun Cao, Yiping Ni +1
Adding expressive and environmental controls to a speech generator requires learning heterogeneous attributes without losing earlier capabilities. VoiceWeaver addresses this proble…
Temporal Anchors and Editing Sensitivity in Partial Speech Spoofing: A Controlled Study
Xiaosu Su, Yun Cao, Yiping Ni +1
Partial-spoof detectors must reject synthetic content while accepting benign edits. We diagnose temporal anchors and boundary-consistency training using frozen WavLM features, nonl…
CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation
Xiaosu Su, Zihan Sun, Peilei Jia +1
Voice design from natural language descriptions is emerging as a new task in text-to-speech multimodal generation, aiming to synthesize speech with target timbre and speaking style…
GAIS: Frame-Level Gated Audio-Visual Integration with Semantic Variance-Scaled Perturbation for Text-Video Retrieval
Bowen Yang, Yun Cao, Chen He +1
Text-to-video retrieval requires precise alignment between language and temporally rich audio-video signals. However, existing methods often emphasize visual cues while underutiliz…