Zhizheng Wu

EigeNet introduces a geometry-informed multi-modal Transformer framework to achieve state-of-the-art few-shot novel view Room Impulse Response (RIR) prediction by effectively integrating spatial geometry and multi-view acoustic context.

This paper introduces Speaker Anonymization (SA) as a novel perturbation mechanism for zero-shot voice conversion, balancing timbre leakage and prosodic utility while enabling strictly causal, zero-lookahead networks.

This paper introduces a training recipe for sentence-level and long-form streaming speech-to-speech translation using only 2k hours of paired cross-lingual data and auxiliary supervision.