Biography

Satoru Fukayama is a Senior Researcher at the National Institute of Advanced Industrial Science and Technology (AIST), Japan. CV : [pdf] Google Scholar : [Link]

Selected Publications

  1. Singer Diarization for Polyphonic Music with Unison Singing, Hitoshi Suda, Daisuke Saito, Satoru Fukayama, Tomoyasu Nakano, Masataka Goto, IEEE-ACM Transaction on Audio Speech and Language Processing, vol. 30, pp. 1531-1545, 2022 doi: 10.1109/TASLP.2022.3166262.

  2. Automatic melody harmonization with triad chords: A comparative study, Yin-Cheng Yeh, Wen-Yi Hsiao, Satoru Fukayama, Tetsuro Kitahara, Benjamin Genchel, Hao-Min Liu, Hao-Wen Dong, Yian Chen, Terence Leong, Yi-Hsuan Yang, Journal of New Music Research, vol. 50, issue 1, pp. 37-51, Jan. 2021

  3. Contour-Preserving Melody Conversion, Satoru Fukayama, Masataka Goto, International Computer Music Conference 2021 (ICMC2021), pp.172-177, 2021

  4. Melody harmonisation with interpolated probabilistic models, Stanislaw. Raczynski, Satoru Fukayama, Emmanuel Vincent, Journal of New Music Research, vol. 42, issue 3, pp. 223-235, Oct. 2013

  5. Assistance for Novice Users on Creating Songs from Japanese Lyrics, Satoru Fukayama, Daisuke Saito, Shigeki Sagayama, Proceedings of ICMC, pp.441-446, Sep. 2012

Research Projects

Music Generation

  • Generating Melody, Chords, Drum Track with Probabilistic Models

  • Melody Harmonization

  • Automatic Arrangement (Piano, Guitar, String Quartet, Chorus, Jazzification)

  • Expressive Performance Rendering

  • Composing Japanese Songs from Lyrics

Dance Motion Processing

  • Pose Estimation

  • Query-by-Dancing

  • Dance Motion Editing

  • Automated Choreography

Lyrics Generation

  • Lyrics Language Models

  • Lyrics Writing Support Interfaces

  • A Melody-conditioned Lyrics Language Model, Kento Watanabe, Yuichiroh Matsubayashi, Satoru Fukayama, Masataka Goto, Kentaro Inui, Tomoyasu Nakano, Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018), pp. 163-172, June 2018.

  • Modeling Storylines in Lyrics, Kento watanabe, Yuichiroh Matsubayashi, Kentaro Inui, Satoru Fukayama, Tomoyasu Nakano, Masataka Goto, IEICE Transaction on Information and Systems, Vol. E101.D, No. 4, pp. 1167-1179, 2018.

  • LyriSys: An Interactive Support System for Writing Lyrics Based on Topic Transition, Kento Watanabe, Yuichiro Matsubayashi, Kentaro Inui, Tomoyasu Nakano, Satoru Fukayama, Masataka Goto, Proceedings of the International Conference on Intelligent User Interfaces (ACM IUI2017), pp.559-563, Mar. 2017

  • Modeling Discourse Segments in Lyrics Using Repeated Patterns, Kento Watanabe, Yuichiro Matsubayashi, Naho Orita, Naoaki Okazaki, Kentaro Inui, Satoru Fukayama, Tomoyasu Nakano, Smith Jordan, Masataka Goto, Proceedings of the 26th International Conference on Computational Linguistics (COLING2016), pp.1959-1969, Dec. 2016

Music Information Retrieval

  • Singer diarization

  • Beat tracking

  • Recommendation

  • Transcription

  • Active music listening interfaces

  • Singer Diarization for Polyphonic Music with Unison Singing, Hitoshi Suda, Daisuke Saito, Satoru Fukayama, Tomoyasu Nakano, Masataka Goto, IEEE-ACM Transaction on Audio Speech and Language Processing, vol. 30, pp. 1531-1545, 2022 doi: 10.1109/TASLP.2022.3166262.

  • Joint Beat and Downbeat Tracking Based on CRNN Models and a Comparison of Using Different Context Ranges in Convolutional Layers, Tian Cheng, Satoru Fukayama, Masataka Goto, International Computer Music Conference 2020, (paper published in 2020, presentation postponed to 2021).

  • ABCPRec: Adaptively Bridging Consumer and Producer Roles for User-Generated Content Recommendation, Kosetsu Tsukuda, Satoru Fukayama, Masataka Goto, 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (ACM SIGIR 2019), pp. 1197-1200, July 2019.

  • Automatic Singing Transcription based on Encoder-Decoder Recurrent Neural Networks with a Weakly-Supervised Attention Mechanism, Ryo Nishikimi, Eita Nakamura, Satoru Fukayama, Masataka Goto, Kazuyoshi Yoshii, 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP2019), pp. 161-165, May 2019.

  • Joint Transcription of Lead, Bass, and Rhythm Guitars based on a Factorial Hidden Semi-Markov Model, Kentaro Shibata, Ryo Nishikimi, Satoru Fukayama, Masataka Goto, Eita Nakamura, Katsutoshi Itoyama, Kazuyoshi Yoshii, 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP2019), pp. 236-240, May 2019.

  • Listener Anonymizer: Camouflaging Play Logs to Preserve User’s Demographic Anonymity, Kosetsu Tsukuda, Satoru Fukayama, Masataka Goto, The 19th International Society for Music Information Retrieval Conference (ISMIR 2018), pp. 687-694, Sep. 2018.

  • Instrudive: A Music Visualization System Based on Automatically Recognized Instrumentation, Takumi Takahashi, Satoru Fukayama, Masataka Goto, The 19th International Society for Music Information Retrieval Conference (ISMIR 2018), pp. 561-568, Sep. 2018.

  • Comparing RNN Parameters for Melodic Similarity, Tian Cheng, Satoru Fukayama, Masataka Goto, The 19th International Society for Music Information Retrieval Conference (ISMIR 2018), pp. 763-770, Sep. 2018.

  • Convolving Gaussian Kernels for RNN-based Beat Tracking, Tian Cheng, Satoru Fukayama, Masataka Goto, The 26th European Signal Processing Conference (EUSIPCO 2018), pp. 1919-1923, Sep. 2018.

  • ChordScanner: Browsing Chord Progressions based on Musical Typicality and Intra-Composer Consistency, Hiromi Nakamura, Tomoyasu Nakano, Satoru Fukayama, Masataka Goto, The 43rd International Computer Music Conference (ICMC 2018), pp. 250-255, Aug. 2018.

  • The CrossSong Puzzle: Developing a Logic Puzzle for Musical Thinking, Jordan B. L. Smith, Jun Kato, Satoru Fukayama, Graham Percival, Masataka Goto, Journal of New Music Research, vol. 46, issue 3, pp.213-228, Mar. 2017

  • Music Emotion Recognition with adaptive aggregation of Gaussian Process Regressors, Satoru Fukayama, Masataka Goto, Proceedings of the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP2016), pp.71-75, Mar. 2016

  • CrossSongPuzzle: Generating and Unscrambling Music Mashups with Real-time Interactivity, Smith Jordan, Graham Percival, Jun Kato, Masataka Goto, Satoru Fukayama, Proceedings of the 12th Sound and Music Computing Conference (SMC2015), pp.61-67, Jul. 2015

Speech / Multimedia Processing

  • Speech Emotion Recognition

  • Exploiting Fine-tuning of Self-supervised Learning Models for Improving Bi-modal Sentiment Analysis and Emotion Recognition, Wei Yang, Satoru Fukayama, Panikos Heracleous, Jun Ogata, Interspeech (to appear), 2022

  • Applying Generative Adversarial Networks and Vision Transformers in Speech Emotion Recognition, Panikos Heracleous, Satoru Fukayama, Jun Ogata, Yasser Mohammad, HCI International (to appear), 2022

  • Audio-Visual Object Removal in 360-Degree Videos, Ryo Shimamura, Feng Qi, Yuki Koyama, Takayuki Nakatsuka, Satoru Fukayama, Masahiro Hamasaki, Masataka Goto, Shigeo Morishima, The Visual Computer, 36, pp. 2117–2128, Jul. 2020