works on

From the 1 of 14 linked papers with an AI index.

activity
20242026
collaborators

14 papers

eess.AS2026

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…

cs.RO2026

S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information

Kaneyoshi Hiratsuka, Benjamin Yen, Ryosuke Kojima

The paper presents acoustic-aware manipulation tasks where robots use sound cues to locate and identify objects, and introduces the S2A2 multimodal imitation learning framework tha…

cs.RO2026

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…

cs.SD2026

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…

cs.SD2026

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…

cs.SD2026

Weakly Supervised Detection and Temporal Localization of Whale Calls in Long-Duration Bioacoustic Data

Ragib Amin Nihal, Benjamin Yen, Runwu Shi +2

Passive acoustic monitoring (PAM) systems generate continuous recordings spanning months, yet automated bioacoustic analysis of whale calls requires two separate annotation efforts…