Speech and Acoustics: speech enhancement, speech separation, voice activity detection, speech dereverberation, robust speech recognition, speaker diarization, speech emotion recognition, acoustic scene classification, sound event localization and detection

Computer Vision: handwriting recognition, text detection, OCR, math equation recognition, object detection in aerial images

Multimodality: audio-visual emotion recognition, audio-visual speech enhancement, audio-visual voice activity detection, scene text visual question answering