[R] Google AudioLM produces amazing quality continuation of voice and piano prompts

LM-based; in contrast to other recent audio generation experiments which worked from transcribed text or midi notes, AudioLM works directly based on the audio signal, resulting in outstanding consistency and high fidelity sound.

Google blog post from yesterday: [https://ai.googleblog.com/2022/10/audiolm-language-modeling-approach-to.html](https://ai.googleblog.com/2022/10/audiolm-language-modeling-approach-to.html)

Demo clip on Youtube: [https://www.youtube.com/watch?v=\_xkZwJ0H9IU](https://www.youtube.com/watch?v=_xkZwJ0H9IU)

Paper: [https://arxiv.org/abs/2209.03143](https://arxiv.org/abs/2209.03143)

Abstract:

>We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts audio generation as a language modeling task in …

audiolm google machinelearning quality voice