Shlomo DubnovView profile
Professor
Shlomo Dubnov is a Professor in the Department of Music at the University of California, San Diego. With an h-index of 36 and over 4,803 citations, his research spans the intersection of music, audio processing, and machine learning, making significant contributions to music information retrieval, sound synthesis, and speech recognition technologies. Dr. Dubnov's primary research interests focus on Music Technology and Audio Signal Processing , with particular expertise in: Machine learning applications for music and audio analysis Sound texture synthesis and modeling Music improvisation systems and computational creativity Audio adversarial examples and security Pitch tracking in noisy environments Multimodal learning for audio-text alignment His recent work demonstrates a strong trend toward applying transformer architectures and contrastive learning techniques to audio processing tasks, with publications in top conferences like IEEE International Conference on Acoustics, Speech, and Language Processing. Dr. Dubnov's research bridges theoretical music concepts with practical audio engineering applications, creating innovative solutions for music generation, analysis, and security. Dr. Dubnov has established productive collaborations with researchers across disciplines, particularly with: G. Assayag (102 Publications • 2,475 Citations) - music technology and improvisation systems Taylor Berg-Kirkpatrick (31 Publications • 1,459 Citations) - machine learning applications K. Chen (18 Publications • 1,150 Citations) - audio transformer models Cheng-i Wang (21 Publications • 305 Citations) - music information retrieval His work is supported by grants focused on advancing the state-of-the-art in music technology, audio processing, and machine learning applications for creative domains. Dr. Dubnov leads research in the Music Technology laboratory at UC San Diego, where his team develops innovative systems for music analysis, synthesis, and human-computer interaction in musical contexts. The lab focuses on creating intelligent systems that can understand, generate, and interact with musical content in real-time applications.











