Heming Wang

This record appears to blend work from multiple distinct research areas, most notably speech and audio processing—including speech enhancement, speech extraction, and spatial audio coding using diffusion-based machine learning models—alongside unrelated topics like circuit design, energy storage, and biomedical proteomics. The speech-related work focuses on using AI models to clean up, edit, and encode speech signals, which is relevant to applications like hearing aids, teleconferencing, and voice assistants.

Publication output grew from none in the late 2010s to a peak around 2022-2023, followed by a decline in 2024-2026, suggesting a burst of activity rather than sustained steady growth.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026