1 citations · 1 across the 14 of their papers we have counts for
7 papers · 1 filter
Rethinking Length-Based Training: Batch Composition and Loss Normalization in Speech Token Language Models
Hongjin Song, Runwu Shi, Weiqiao Shan +4
Short-to-long training is a simple curriculum for speech models, but its gains can be difficult to interpret. In speech token language models, length-based training can change the…
Exploring Efficient Waveform Diffusion Models for Foley Sound Generation
Runwu Shi, Chang Li, Jiahui Li +7
Recent advances in diffusion models have enabled high-fidelity Foley sound generation directly in the waveform space. Existing waveform diffusion models primarily rely on time-doma…
From Sign Language Generation to Humanoid Execution: Vision-Language Guided Retargeting with Collision Mitigation
Nabeela Khan, Bowen Wu, Runwu Shi +5
Recent sign language generation (SLG) systems increasingly output dense 3D body representations, which better preserve full-body kinematics and geometry for downstream embodiment o…
Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
Runwu Shi, Yujin Wang, Hongjin Song +8
Classifier-free guidance (CFG) is widely used in flow-matching-based zero-shot text-to-speech (TTS), where generation is conditioned on text content and a speech prompt. Standard C…
What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study
Yaozhong Kang, Jiang Wang, Runwu Shi +3
Neural networks outperform classical GCC-PHAT for Time-Difference-of-Arrival (TDOA) estimation in noise and reverberation, yet their internal strategy remains unexplored. To uncove…
Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments
Jiang Wang, Runwu Shi, Yaozhong Kang +3
Sound source distance estimation (SDE) is a critical capability in human-robot interaction. An inappropriate interaction distance not only reduces the reliability of speech acquisi…
Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data
Ragib Amin Nihal, Benjamin Yen, Runwu Shi +2
Training data for bioacoustics is scattered across taxa, regions, and institutions. Centralizing it all is often infeasible. We show that independently fine-tuned BEATs encoders ca…