On Time-frequency Scattering and Computer Music
This work addresses the problem of enhancing AI tools for music creators, though it appears incremental as it extends an existing method to a new application domain.
The paper demonstrates that time-frequency scattering, a transformation mimicking human auditory processing, can be applied to contemporary music creation, building on its existing success in tasks like automatic speech transcription and sound recognition.
Time-frequency scattering is a mathematical transformation of sound waves. Its core purpose is to mimick the way the human auditory system extracts information from its environment. In the context of improving the artificial intelligence of sounds, it has found succesful applications in automatic speech transcription as well as the recognition of urban sounds and musical sounds. In this article, we show that time-frequency scattering can also be useful for applications in contemporary music creations.