Artificial Intelligence

Google’s new AI can hear a snippet of song—and then keep on playing

MIT Technology Review
November 22, 2022
Download PDF


The technique, called AudioLM, generates naturalistic sounds without the need for human annotation.

A new AI system can create natural-sounding speech and music after being prompted with a few seconds of audio.

AudioLM, developed by Google researchers, generates audio that fits the style of the prompt, including complex sounds like piano music, or people speaking, in a way that is almost indistinguishable from the original recording. The technique shows promise for speeding up the process of training AI to generate audio, and it could eventually be used to auto-generate music to accompany videos.

(You can listen to all of the examples here.)

AI-generated audio is commonplace: voices on home assistants like Alexa use natural language processing. AI music systems like OpenAI’s Jukebox have already generated impressive results, but most existing techniques need people to prepare transcriptions and label text-based training data, which takes a lot of time and human labor. Jukebox, for example, uses text-based data to generate song lyrics.

Read more here.

MIT Technology Review
MIT Technology Review

Founded at the Massachusetts Institute of Technology in 1899, MIT Technology Review is a world-renowned, independent media company whose insight, analysis, reviews, interviews and live events explain the newest technologies and their commercial, social and political impacts. MIT Technology Review derives authority from its relationship to the world's foremost technology institution and from its editors' deep technical knowledge, capacity to see technologies in their broadest context, and unequaled access to leading innovators and researchers. The mission of MIT Technology Review is to make technology a greater force for good by bringing about better-informed, more conscious technology decisions through authoritative, influential, and trustworthy journalism.

Become a Member