2 papers
eess.AS2026
CSAVocoder: A Causal Spatial Audio Vocoder Towards Real-Time Spatial Audio Generation
Zhiyuan Zhu, Han Wang, Wenxiang Guo +4
Spatial audio vocoders are able to convert mel-spectrograms produced by generative models into spatial audio waveforms. Most neural vocoders are designed for monaural audio, and di…
cs.SD2025
MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
Wenxiang Guo, Changhao Pan, Zhiyuan Zhu +16
Humans rely on multisensory integration to perceive spatial environments, where auditory cues enable sound source localization in three-dimensional space. Despite the critical role…