Discussion

• @keunwoochoi Keunwoo Choi on x

  whoa, this is bigger than ChatGPT to me. google almost solved music generation, i'd say. https://google-research.github.io/ ...

• @arankomatsuzaki Aran Komatsuzaki on x

  MusicLM: Generating Music From Text Presents MusicLM, a model for generating high-fidelity music from text. MusicLM generates music at 24 kHz that remains consistent over several minutes. proj: https://google-research.github.io/ ... abs: https://arxiv.org/... data: https://www.ka…

• @terrorproforma @terrorproforma on x

  It's 2033. You wake feeling fresh as an AI has optimised your hormones, blood sugar & body temp to give you a perfect night sleep. Music is playing, AI made, personalised to tune your mood to prepare for the day. You'll need it after all, today is the day you go to Mars. https://…

• @rrherr @rrherr on x

  @keunwoochoi The last sentence of the paper though 😭 “we have no plans to release models at this point”

• @tomdavenport Tom Davenport on x

  This stuff is moving fast. IMO this is about more than composition. A junior producer could describe sounds for a synth, rather than have to buy equipment to produce it, or learn complicated tools like Reaktor. https://twitter.com/...

• @honualx Alexandre Défossez on x

  The dignity of audio scientists finally restored after a short time with a vision based SOTA in music gen 🥲 Great work released by Google Brain with @neilzegh @antoine_caillon @jesseengel among others. https://google-research.github.io/ ... https://twitter.com/...

• @glenngabe Glenn Gabe on x

  What an interesting world we will live in soon :) -> Google details MusicLM, an AI model that generates high-fidelity music from text descriptions trained on a dataset of 280K hours of music. But based on ethical challenges, Google won't release it: https://techcrunch.com/... htt…

• @giffmana Lucas Beyer on x

  MusicLM really is impressive: https://google-research.github.io/ ... This one instantly lowered my heart-rate as I started playing it :) https://google-research.github.io/ ... https://twitter.com/...

• @keunwoochoi Keunwoo Choi on x

  really well done, from SoundStream and AudioLM through MuLan to MusicLM 👏👏 the overall structure of MusicLM = MuLan + AudioLM = MuLan + w2v-BERT + SoundStream https://twitter.com/...

• @mathemagic1an Jay Hack on x

  “MusicLM: Generating Music from Text” https://google-research.github.io/ ... Impressed to see the quality of autogenerated vocals has gone way up! Sounds real but in a foreign language. https://twitter.com/...

• @genekogan Gene Kogan on x

  MusicLM is wild. Very realistic and versatile, can condition on text, images, and other audio. Coolest feature: hum or whistle a melody, input some text (e.g. “string quartet") and it spits out a string quartet playing that melody! https://google-research.github.io/ ...

• @itsandrewgao Andrew Gao on x

  Google's Text to Music model is really cool. They're kind of a “sleeping giant” it seems and have been making big moves in relative silence. Imagen, PaLM, now this. https://google-research.github.io/ ...

• @keunwoochoi Keunwoo Choi on x

  + they released MusicCaps dataset (5521 music-text pair) which they used as an eval set. https://www.kaggle.com/....

• @keunwoochoi Keunwoo Choi on x

  to recap, i find the whole roadmap really, really brilliant. - because there's MuLan, they could use audio-only dataset. - because there's SoundStream, the music generation task was simplified to token generation, not waveform generation.

• @bentossell Ben Tossell on x

  MusicLM: Generating Music From Text (sound on 📣) project page: https://google-research.github.io/ ... arXiv: https://arxiv.org/... https://twitter.com/...

• @dadabots @dadabots on x

  The melody conditioning examples are AMAZING definitely want to add this to dance diffusion https://twitter.com/...