The purpose of this study is to reproduce the interaction between human singers. When human singers sing together, each singer does not sing alone but controls his/her own singing voice so that it harmonizes with that of the other singer. In other words, there is an interaction between human singers and their singing, and this interaction brings about a unified singing voice and appreciation experience by a group of human singers. On the other hand, AI singers (computers with singing voice synthesizing functions) do not have such interaction functions. When a group of human and AI singers sing together, the human singer has no other choice but to unilaterally match the AI singer. In addition, there is no interaction between AI singers and human singers. Therefore, in this study, we research and develop a singing voice synthesis technology that has a singing interaction function.
@inproceedings{nakamura26speasip_auditory-feedback-emotion,abbr_publisher={情報処理学会 音声言語処理研究会},booktitle={情報処理学会 音声言語処理研究会},title={Altered auditory feedbackに基づく感情誘導における音声特徴量弁別閾の調査},author={颯, 中村 and 航希, 福田 and 慎之介, 高道 and 龍, 大畑},year={2026},month=mar,}
AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences
Minoru Kishi , Ryosuke Sakai , Shinnosuke Takamichi , Yusuke Kanamori , and Yuki Okamoto
In Proceedings of Audio-Centric AI: Towards Real-World Multimodal Reasoning and Application Use Cases (Audio-AAAI) , Jan 2026
@inproceedings{kishi26aaai_audiobertscore,abbr_publisher={Proceedings of Audio-Centric AI: Towards Real-World Multimodal Reasoning and Application Use Cases (Audio-AAAI)},booktitle={Proceedings of Audio-Centric AI: Towards Real-World Multimodal Reasoning and Application Use Cases (Audio-AAAI)},title={AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences},author={Kishi, Minoru and Sakai, Ryosuke and Takamichi, Shinnosuke and Kanamori, Yusuke and Okamoto, Yuki},year={2026},month=jan,}
@inproceedings{sakai25mus_perceptual-inconsistency,abbr_publisher={情報処理学会 音楽情報科学研究会},booktitle={情報処理学会 音楽情報科学研究会},title={知覚感情の不整合：人間が作曲した音楽，音楽を記述したテキスト，テキスト楽音合成による音楽の比較},author={瞭介, 阪井 and 航希, 福田 and 嶺佑, 松下 and 慎之介, 高道 and あい子, 植村},year={2025},}
@inproceedings{nobukawa25mus_drum-to-vocal,abbr_publisher={情報処理学会 音楽情報科学研究会},booktitle={情報処理学会 音楽情報科学研究会},title={変分オートエンコーダによるドラムからボーカルパーカッションへの楽器音変換と評価},author={凜佳, 信川 and 優輝士, 北村 and 友彦, 中村 and 慎之介, 高道 and 洋, 猿渡},year={2025},}
Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology
@inproceedings{nobukawa25apsipa_drum-to-vocalpercussion,abbr_publisher={Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)},booktitle={Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)},title={Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology},author={Nobukawa, Rinka and Kitamura, Makito and Nakamura, Tomohiko and Takamichi, Shinnosuke and Saruwatari, Hiroshi},year={2025},month=oct,}
@inproceedings{kishi25muslp_envsound-generation-eval,abbr_publisher={情報処理学会 音声言語処理研究会},booktitle={情報処理学会 音声言語処理研究会},title={環境音埋め込みベクトル系列の類似度に基づく環境音生成の自動評価},author={秀, 岸 and 瞭介, 阪井 and 慎之介, 高道 and 勇介, 金森 and 悠希, 岡本},year={2025},month=jun,}
@inproceedings{take25speasip_egotts-dialogue,abbr_publisher={情報処理学会 音声言語処理研究会},booktitle={情報処理学会 音声言語処理研究会},title={音環境に適応する音声合成能力を搭載した音声対話システムの構築と実証実験に基づく検討},author={伯寒, 武 and 慎之介, 高道 and 健太郎, 関 and 洋, 猿渡},year={2025},}
Real-Time Drum-to-Vocal Percussion Sound Conversion System
@inproceedings{nobukawa25ismir_drum-to-vocal,abbr_publisher={International Society for Music Information Retrieval Late‑Breaking/Demo Session},booktitle={International Society for Music Information Retrieval Late‑Breaking/Demo Session},title={Real-Time Drum-to-Vocal Percussion Sound Conversion System},author={Nobukawa, Rinka and Nakamura, Tomohiko and Takamichi, Shinnosuke and Saruwatari, Hiroshi},year={2025},month=sep,}
@inproceedings{take24asjs_audio-effect,abbr_publisher={日本音響学会春季研究発表会},booktitle={日本音響学会春季研究発表会},title={複数のオーディオエフェクトが適用された楽音に対するエフェクトチェイン推定と原音復元},author={伯寒, 武 and 研斗, 渡邉 and 貴之, 中塚 and Cheng, Tian and 倫靖, 中野 and 真孝, 後藤 and 慎之介, 高道 and 洋, 猿渡},year={2024},memo={本研究は科研費 21H04900, 22H03639，23H03418， JST 創発的研究支援事業 JP23KJ0828，ムーンショット JPMJPS2011 の助成を受けたものです}}
DNN-based ensemble singing voice synthesis with interactions between singers
@inproceedings{hyodo24slt_chorus,abbr_publisher={Proceedings of IEEE Spoken Language Technology Workshop (SLT)},booktitle={Proceedings of IEEE Spoken Language Technology Workshop (SLT)},title={DNN-based ensemble singing voice synthesis with interactions between singers},author={Hyodo, Hiroaki and Takamichi, Shinnosuke and Nakamura, Tomohiro and Koguchi, Junya and Saruwatari, Hiroshi},year={2024}}
@inproceedings{hyodo24asja_duet-timing,abbr_publisher={日本音響学会秋季研究発表会},booktitle={日本音響学会秋季研究発表会},title={二重唱の歌い出しタイミングに対する同時性知覚の刺激閾調査},author={弘明, 兵藤 and 慎之介, 高道 and 洋, 猿渡},year={2024}}
@inproceedings{nakamura23mus_jacappella-v2,abbr_publisher={情報処理学会 音楽情報科学研究会},booktitle={情報処理学会 音楽情報科学研究会},title={{jaCappella}コーパスv2：重唱分離・合成のための日本語アカペラ重唱コーパスの拡張},author={友彦, 中村 and 慎之介, 高道 and 尚子, 丹治 and 覚, 深山 and 洋, 猿渡},year={2023},}