Vahid Ahmadi Kalkhorani

This researcher works on speech and audio processing, particularly methods that combine audio and visual information to separate overlapping speakers, enhance noisy speech, and improve automatic speech recognition (ASR). An earlier line of work, now less active, involved engineering topics like building air quality and cooling systems using metal-organic framework materials. The more recent and dominant focus is on deep learning models (e.g., 'CrossNet' architectures) for tasks like isolating a target speaker's voice from background noise or other talkers, using both audio and video (e.g., lip movement) cues.

Publication output has grown from essentially none before 2021 to a steady stream of several papers per year since 2022, suggesting an active and increasing research pace in recent years.

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