In Brief
Google introduces MusicLM, a model for generating high-fidelity music from text descriptions.
MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption.
The model can generate music in a variety of genres, including classical, jazz, and rock.
The Trust Project is a worldwide group of news organizations working to establish transparency standards.
Google introduces MusicLM, a model for generating high-fidelity music from text descriptions such as “a calming violin melody backed by a distorted guitar riff.” MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes.
Google experiments show that MusicLM outperforms previous systems, both in audio quality and adherence to the text description. Moreover, it demonstrates that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption. To support future research, we publicly release MusicCaps, a dataset composed of 5.5k music-text pairs with rich text descriptions provided by human experts.
| Related article: Text-to-3D: Google has developed a neural network that generates 3D models from text descriptions |
The MusicLM model has been trained on a large corpus of musical scores, which has allowed the AI to learn the structure of music. The model can generate music in a variety of genres, including classical, jazz, and rock. In addition, the AI model can create new, original compositions.
The MusicLM model is an important development in the field of AI-generated music. The model represents a significant advance over previous models, which were limited to shorter pieces of music or only capable of generating simple melodies. The new model opens up the possibility of using AI to generate long, complex pieces of music, which could be used in movies, video games, or other media.
The new AI model can generate long music generations of up to five minutes.
The AI model can create music using captions from games and movies.
In addition, the AI model can generate music using images as input.
Read more about AI in the music industry:
Disclaimer
Any data, text, or other content on this page is provided as general market information and not as investment advice. Past performance is not necessarily an indicator of future results.
