SUNTORY TOKUCHA MUSIC / SUNTORY

AI Music Generation Based on User Data

2021

  • suntory project image 220415-1536x1026
  • suntory project image 220415-1536x1026

Suntory’s “TOKUCHA MUSIC” is a music maker where AI generates original music based on the user’s specified daily meals. We have provided our original AI music generation system for this project.

A survey by Suntory in the fall of 2020 showed that in the new lifestyle triggered by the pandemic, people are becoming more conscious of their diet compared to 2019. Using an AI music generation system, we proposed to give users awareness of the opportunity to be healthy in a fun and unique way through music.

This system is based on our original deep learning model and can generate multi-track music with drums, melody, bass line, and harmony based on conditions such as pitch height, note density, chord progression, and balance between consonance and dissonance. If the user has a nutritional imbalance, the system will generate dissonant music with minor chords. On the contrary, if the user has a healthy meal, it will create happy and up-tempo music. Since the users can choose from about 2,000 different meals, they can repeatedly enjoy the countless variations of music generated by the AI.

This project is an interesting example of AI-based sonification and "musicification" of data. It is impossible for human composers to generate countless variations of music based on specific data inputs. These abilities are a unique feature of our AI music generation system.

- 食事内容を基にAIが作曲、栄養バランスが良ければ「いい曲」に? サントリーが新サービス

Client

SUNTORY/サントリー食品インターナショナル(株)

Credits

Creative Direction: Takashi Kawashima(Studio Kawashima) Technical Direction/Machine Learning: Nao Tokui(Qosmo) Art Director: Yuki Sakurai(Metamosphere inc.) Planning: Ryosuke Sone(Dentsu Craft Tokyo) Produce: Maho Tada(Dentsu Craft Tokyo),Jun Kato(Dentsu Craft Tokyo),Kikuko Ando(Dentsu Craft Tokyo) Project Management: Tatsuya Maniwa(Dentsu Craft Tokyo),Sakiko Yasue(Qosmo), Yumi Takahashi(Qosmo) Audio Development: Robin Jungers(Qosmo) Machine Learning: Christopher Mitcheltree(Qosmo) Technical Direction: Hiroyoshi Murata(Dentsu Craft Tokyo) Front Engineering: Eiki Kurokawa(Dentsu Craft Tokyo),Atsushi Asakura(Dentsu Craft Tokyo),Yuki Tanabe(Dentsu Craft Tokyo) Direction Support: Kei Sato(Dentsu Craft Tokyo) Backend Engineering: Hajime Sasaki(MountPosition Inc. ) Sound Design/Sound Produce: Masayuki Noda(invisible design lab) Design: Ikuko Komamoto(Dentsu Creative X) Copy Writing: Keiko Taguchi(Dentsu Creative X),Shiho Sasaki(Dentsu Creative X),Yui Mamiya(Dentsu Creative X)

Product

This project uses Qosmo Music & Sound AI. Music Generation