3 papers
eess.AS2026
Designed Vocalizations Dataset: Sound-Designed Human and Animal Voices for Non-human Voice Conversion
Seolhee Lee, Minsu Kang, Yangsun Lee +3
Advances in AI-based voice conversion have enabled a wide range of media applications, including films, audiobooks, and games. However, most research and public benchmarks still fo…
eess.AS2025
When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds
Minsu Kang, Seolhee Lee, Choonghyeon Lee +1
Human to non-human voice conversion (H2NH-VC) transforms human speech into animal or designed vocalizations. Unlike prior studies focused on dog-sounds and 16 or 22.05kHz audio tra…
cs.SD2024
PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text
Hayeon Bang, Eunjin Choi, Megan Finch +4
While piano music has become a significant area of study in Music Information Retrieval (MIR), there is a notable lack of datasets for piano solo music with text labels. To address…