AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
LARC: A Multi-Modal Foundation Model for Music
The chapter discusses the introduction of LARC, a multi-model foundation model for music that can describe tempo, provide captions, and reason about music. It explores potential applications of the model and raises questions about the merging of music and spoken audio. The chapter also touches upon Spotify's collaboration with the University of Washington on AI integration and the potential of using language models for time series prediction.