Applied AI Pod
Developing Creativity with AI & DL for Sound & Audio, with Valerio Velardo, E28
Episode Summary
Creativity and Artificial Intelligence music in all of its forms, with Valerio Velardo. Valerio is both a domain and technology expert that researched, taught, developed new technology in the space, built a startup and consulting firm around it. A musician at core, and AI for sound and audio engineer building The Sound of AI community day to day (the largest community in the world on AI, music, audio, and signal processing). Studied music and astrophysics at Bachelor's degree level. > Master's degrees in music composition, conducting and piano performance. > PhD in Music and Artificial Intelligence. Add on top contributions in the AI music space like: Developer of an AI music system that simulates a society of virtual songwriters, which generate rock songs and evolve their compositional style. Composer of dozens of pieces for piano, orchestra, video games and films. Adaptive music advocate. OR AI music consultant, data scientist, and programmer. Founded 2 startups, launched the leading academic journal and conference in music and AI, published research in international academic journals. AND expect an amazing episode that gives so much food for both mind and soul. It's all things music and audio. Jump in!
Episode Notes
- 2:10 - Using AI to augment and reshape creativity in a modern world. Psychological creativity and story creativity - can an AI model help AI music artists, today, get off their creative blocks?
- 12:15 - Attempt to define ‘good’ music, using a cognitive music literature background.
- 17:00 - Are we better or worse off, for AI in audio/music? Is it sustainable for the effort input and cost, impact and efficiency output?
- 22:35 - ‘Deep Nostalgia” from myheritage initiative, and GPT-J - looking for strengths in the two approaches.
- 29:25 - The Sound of AI community - a HuggingFace version for audio?
- 31:15 - Train a DL - CNN sound classifier built with Pytorch and torchaudio on the Urban Sound 8k dataset.
- 35:00 - Is deep learning a dead end for artificial intelligence?
- 38:05 - Could someone that is a pure tech profile ever be in such an intersection in sync with the artistic world? Is it a pre-req to be domain savvy to build AI audio solutions?
- 42:10 - Helping music tech companies with a focus on audio (voice, speech, sound), the experience so far.
- 49:45 - Hard problems to solve when dealing with AI audio - Top three.
- 56:50 - First piece of music composed by a machine.
References: