Audio Intelligence

Audio intelligence research at Spotify is advancing the state of the art in understanding music at scale to enhance how it is created, identified and consumed. We build bridges from raw audio to description, similarity, recommendation and music creation by developing machine listening technologies and synthesis algorithms. These power the next-generation of differentiating products and experiences, blurring the line between creators and consumers. Examples of active research areas in audio intelligence include information retrieval, source separation, auto tagging, auto mixing, mashups, sound modeling, vocals characterization, and music promotion.

Latest Audio Intelligence Publications

August 2023 | Interspeech

Lightweight and Efficient Spoken Language Identification of Long-form Audio

Winstead Zhu, Md Iftekhar Tanveer, Yang Janet Liu, Seye Ojumu, Rosie Jones

June 2023 | ICASSP

Contrastive Learning-based Audio to Lyrics Alignment for Multiple Languages

Simon Durand, Daniel Stoller, Sebastian Ewert

September 2022 | Interspeech

Unsupervised Speaker Diarization that is Agnostic to Language Overlap Aware and Free of Tuning

M Iftekhar Tanveer, Diego Casabuena, Jussi Karlgren, Rosie Jones