Tomohiko Nakamura

Contemporary A Cappella and Vocal Percussion Processing

jaCappella corpus wordmark with flowing vocal lines

We study separation and synthesis of contemporary a cappella vocal ensembles, supported by the separately recorded vocal parts and annotations in the jaCappella corpus. As a distinct but related research direction in vocal music processing, we develop and evaluate conversion from drum sounds to vocal percussion, including real-time systems.

Demo Corpus website

Related Publications

  • Yuma Narahata, Tomohiko Nakamura, Yuki Saito, and Hiroshi Saruwatari, “Lead vocal separation from vocal ensemble mixtures using phoneme alignment,” in Proceedings of Asia Pacific Signal and Information Processing Association Annual Summit and Conference, Nov. 2026.
  • Rinka Nobukawa, Makito Kitamura, Tomohiko Nakamura, Shinnosuke Takamichi, and Hiroshi Saruwatari, “Drum-to-vocal percussion sound conversion and its evaluation methodology,” in Proceedings of Asia Pacific Signal and Information Processing Association Annual Summit and Conference, Oct. 2025, pp. 198–203.
  • Rinka Nobukawa, Tomohiko Nakamura, Shinnosuke Takamichi, and Hiroshi Saruwatari, “Real-time drum-to-vocal percusssion sound conversion system,” in Late Breaking Session, International Society for Music Information Retrieval Conference, Sept. 2025.
  • Hiroaki Hyodo, Shinnosuke Takamichi, Tomohiko Nakamura, Junya Koguchi, and Hiroshi Saruwatari, “DNN-based ensemble singing voice synthesis with interactions between singers,” in Proceedings of IEEE Spoken Language Technology Workshop, Dec. 2024, pp. 660–667.
  • Tomohiko Nakamura, Shinnosuke Takamichi, Naoko Tanji, Satoru Fukayama, and Hiroshi Saruwatari, “jaCappella corpus: A Japanese a cappella vocal ensemble corpus,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, June 2023.