Spotify

Spotify Research is part of Spotify R&D, the technology engine that drives everything you love about the Spotify app. Spotify Research is dedicated to extending the state of the art in audio. With over 15 years of experience, Spotify Research is working on the hardest problems using a broad range of AI methods to understand listeners, creators, the content in the Spotify catalog, and the streaming business. Research areas include matching content and listeners, extracting signals from the audio catalog using natural language understanding and multimedia information retrieval methods, evaluation and algorithmic responsibility.

Project Showcase

Basic Pitch

Basic Pitch is a Python library for Automatic Music Transcription (AMT), using lightweight neural network developed by Spotify's Audio Intelligence Lab. It's small, easy-to-use, pip install-able and npm install-able via its sibling repo or can be accessed at basicpitch.io. Basic Pitch may be simple, but it is far from "basic"! basic-pitch is efficient and its multipitch support, ability to generalize across instruments, and note accuracy competes with much larger and more resource-hungry AMT systems.

Datasets

Datasets Spotify has a few datasets to explore. A highlight is the Spotify Podcast Dataset consisting of over 100,000 episodes each in English and Portuguese from different podcast shows on Spotify. The dataset is available for research purposes. We released the podcast dataset more widely to facilitate research on podcasts through the lens of speech and audio technology, natural language processing, information retrieval, and linguistics. The dataset contains over 100,000 hours of audio, and over 1 billion transcribed words.

Jobs

We are hiring! Find roles open:

• Spotify Research
• All of Spotify