AudioLM
An audio language model developed by Google that uses an autoregressive architecture to discretize audio into token sequences. It is designed to generate semantically coherent long audio segments.
Timeline (last 90 days)
Representative models in the text-to-audio domain include Meta's AudioGen, Google's AudioLM and AudioPaLM, and Stability AI's Stable Audio.
Autoregressive approaches such as AudioLM discretize audio into token sequences and predict the next audio unit step by step, making them better suited for generating long segments with semantic coherence.
All Facts (2)
Representative models in the text-to-audio domain include Meta's AudioGen, Google's AudioLM and AudioPaLM, and Stability AI's Stable Audio.
50%UnverifiedAutoregressive approaches such as AudioLM discretize audio into token sequences and predict the next audio unit step by step, making them better suited for generating long segments with semantic coherence.
50%