Laboratory of Content-oriented Computational Culture & Arts

関西大学総合情報学部 文化芸術計算機科学研究室

2nd Workshop on Sound and Music Computing for Entertainment

Program on Oct. 6th

09:00 – 09:05 Opening Remarks

Prof. Tetsuro Kitahara (WG14.10 Chair)

WS Papers Presentations

09:05 – 09:20
1. Audio-based Countermelody Generation for Karaoke Practice

Kota Fukuda and Tetsuro Kitahara

09:20 – 09:35
2. TimbreStellar: timbre retrieval beyond instrument categories (from WiP papers at the main conference)

Miyu Yoneda, Ryosuke Yamanishi, Takayuki Itoh

09:35 – 09:50
3. Photographic Reverberation: Translating Long-Exposure Visuals into Spatial Reverb

Shaoyun Chu and Yasuo Kuhara

09:50 – 10:05
4. VD-Deck: Algorithmic Visual Generation Based on Mathematical Audio Analysis in DJ Performances

Yujie Huang and Yasuo Kuhara

10:05 – 10:20
5. Half Cadence in Lambek Calculus

Satoshi Tojo and Matteo Bizzarri


WS Keynote

10:30 – 11:30
Reverse correlation: a simple procedure to incorporate perceptual information into sound and music computing

While generative techniques to synthetize speech and music signals have greatly improved, these techniques are still massively based on datasets of production data (speech as it is spoken, music as it is played) and struggle to incorporate information about perception. However, production and perception do not always agree: for instance, when people address interlocutors that are non-native in their language, they tend to produce speech that is slower and more articulated, but perception research suggests that these features may in fact be detrimental to speech comprehension (Aoki & Zellou, J. Phonetics, 2024). In this talk, I will review a simple experimental technique from the field of cognitive psychology, reverse correlation, which allows to automatically identify generative parameters which optimize how sounds are perceived, rather than produced. I will give examples of applications in the domain of music, speech synthesis as well as audiovisual interactions, and discuss the link with AI explainability.

Dr. JJ Aucouturier

JJ Aucouturier is a senior CNRS researcher (directeur de recherche CNRS) at the FEMTO-ST Institute in Besançon, France. Trained as a signal processing engineer (Supélec, 2001), JJA holds a PhD in Computer Science (Université Pierre et Marie Curie, 2006), and completed several postdoctoral fellowships in dynamical systems and later in cognitive neuroscience in Japan (University of Tokyo, 2006–2008; RIKEN Brain Science Institute, 2008–2011) and in France (LEAD UMR5022, Université de Bourgogne, 2011–2012). From 2014 to 2020, he was the PI of the ERC Stg CREAM project and led the Music Neuroscience project team (https://neuro-team-femto.github.io/cream) at the Sciences and Technologies of Music and Sound laboratory (STMS UMR 9912) at IRCAM in Paris. In January 2021, he joined the Control & Robotics department of FEMTO-ST to develop a research project at the intersection of dynamical systems and neuroscience, with clinical applications in neurology (sleep, coma, stroke) and psychiatry (https://neuro-team-femto.github.io). Since January 2024, he has also been a nominated member of the Scientific Council of the CNRS Institute of Computer Sciences (INS2I) and a member of CID51 (Mathematical, Computer, and Physical Modeling for Life Sciences) of the National Committee for Scientific Research (CoNRS).

Open Discussions

11:30 – 11:55 Discussions among participants

11:55 – 12:00 Closing Remarks

Prof. Ryosuke Yamanishi (WG14.10 Vice-Chair)


Call for papers

Sound and music are essential components of entertainment experiences, including games, interactive media, live performances, virtual environments, film, animation, and dance. Recent advances in Sound and Music Computing (SMC) have opened new possibilities for creating, analyzing, transforming, and personalizing such experiences.

The 2nd Workshop on Sound and Music Computing for Entertainment (SMC4E 2026) aims to bring together researchers, practitioners, and creators working at the intersection of sound and music computing and entertainment computing in IFIP-ICEC2026. The workshop provides a forum to discuss state-of-the-art methods, emerging applications, and future visions of entertainment enhanced by sound and music technologies.

In conjunction with IFIP – International Conference on Entertainment Computing 2026: https://icec2026.cnam.fr/index.html

Topics of Interest

We welcome contributions on topics including, but not limited to:

  • music information retrieval for entertainment applications
  • musical audio signal processing
  • sound source separation and remixing for interactive experiences
  • automatic music generation and accompaniment
  • adaptive and interactive game audio
  • generative audio and sound design
  • singing voice synthesis and transformation
  • voice conversion and voice generation for entertainment
  • speech and audio technologies for streaming and live performance
  • AI-based tools for music creation and performance
  • multimodal entertainment systems involving sound and music
  • user experience, creativity support, and audience engagement through sound and music
  • artistic, design, and industry perspectives on SMC for entertainment

The workshop especially encourages submissions that explore how recent developments in machine learning, generative AI, and audio technologies can create new forms of entertainment, new modes of participation, and new audience experiences.

Workshop Format and Participants

The workshop will consist of paper presentations and discussions with participants and organizers. It will also provide an opportunity to exchange ideas on future research directions and on collaborations between academia and industry in this area. The workshop is planned as a half-day event. The workshop will be held exclusively in person. 

The workshop is intended for researchers, developers, artists, and practitioners interested in the use of sound and music technologies in entertainment content and experiences. Participants in the ICEC2026 main conference will be able to attend this WS free of charge.

Submission and Presentation Format

Our WS will have two types of submission and presentation format: 1) originally for our WS, and 2) introducing your paper accepted to the main conference. 

1. Originally for our WS

We invite short papers describing:

  • original research,
  • work in progress,
  • system demonstrations,
  • case studies. 

Submissions should clearly explain their relevance to both Sound and Music Computing and Entertainment Computing. 

If you intend to present your work just in our workshop, please submit your paper here: https://easychair.org/conferences/?conf=icec20260
(Please, select our WS4 – 2nd Workshop on Sound and Music Computing for Entertainment)

Deadline: May 20th, 2026 May 30th, 2026 (extended)
The required format for all papers is the Springer LNCS format.
Papers Length (short): max 6 pages (excluding references)

The paper submitted via EasyChair and accepted by our WS will be included in the WS volume of the ICEC2026 proceedings, LNCS, Springer.

2. Introducing your paper accepted to the main conference

If your paper, i.e., full, WiP, or IES tracks, is accepted to the main conference of ICEC2026, we welcome you to introduce the work in our workshop. You can briefly present your work and promote it during the main sessions.  We expect to provide a detailed discussion of your research on the paper accepted to the main conference, for participants especially interested in sound and music computing. 

In this case, please put the required information and upload the PDF of your accepted paper via this form: https://forms.gle/RE31AeXrj3xJg4pv9

Deadline: May 30th, 2026 June 12th, 2026 (extended) July 3rd (extended)
The paper will be included in the main conference volume of the ICEC2026 proceedings. NOTE: You do not need to enter the information and upload the PDF through this form if you intend to present your work as a type of “Originally for our WS.” 

Organizers

Tetsuro Kitahara, Prof. at Nihon University, Japan
(IFIP TC14.10 SMC Chair)
Ryosuke Yamanishi, Prof. at Kansai University, Japan
(IFIP TC14.10 SMC Vice-Chair)

Contact: smc4e@ccca-lab.net