Text2midi: Generating Symbolic Music from Captions
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911008097828864 |
|---|---|
| author | Bhandari, Keshav Roy, Abhinaba Wang, Kyra Puri, Geeta Colton, Simon Herremans, Dorien |
| author_facet | Bhandari, Keshav Roy, Abhinaba Wang, Kyra Puri, Geeta Colton, Simon Herremans, Dorien |
| contents | This paper introduces text2midi, an end-to-end model to generate MIDI files from textual descriptions. Leveraging the growing popularity of multimodal generative approaches, text2midi capitalizes on the extensive availability of textual data and the success of large language models (LLMs). Our end-to-end system harnesses the power of LLMs to generate symbolic music in the form of MIDI files. Specifically, we utilize a pretrained LLM encoder to process captions, which then condition an autoregressive transformer decoder to produce MIDI sequences that accurately reflect the provided descriptions. This intuitive and user-friendly method significantly streamlines the music creation process by allowing users to generate music pieces using text prompts. We conduct comprehensive empirical evaluations, incorporating both automated and human studies, that show our model generates MIDI files of high quality that are indeed controllable by text captions that may include music theory terms such as chords, keys, and tempo. We release the code and music samples on our demo page (https://github.com/AMAAI-Lab/Text2midi) for users to interact with text2midi. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16526 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Text2midi: Generating Symbolic Music from Captions Bhandari, Keshav Roy, Abhinaba Wang, Kyra Puri, Geeta Colton, Simon Herremans, Dorien Sound Artificial Intelligence Computation and Language Audio and Speech Processing This paper introduces text2midi, an end-to-end model to generate MIDI files from textual descriptions. Leveraging the growing popularity of multimodal generative approaches, text2midi capitalizes on the extensive availability of textual data and the success of large language models (LLMs). Our end-to-end system harnesses the power of LLMs to generate symbolic music in the form of MIDI files. Specifically, we utilize a pretrained LLM encoder to process captions, which then condition an autoregressive transformer decoder to produce MIDI sequences that accurately reflect the provided descriptions. This intuitive and user-friendly method significantly streamlines the music creation process by allowing users to generate music pieces using text prompts. We conduct comprehensive empirical evaluations, incorporating both automated and human studies, that show our model generates MIDI files of high quality that are indeed controllable by text captions that may include music theory terms such as chords, keys, and tempo. We release the code and music samples on our demo page (https://github.com/AMAAI-Lab/Text2midi) for users to interact with text2midi. |
| title | Text2midi: Generating Symbolic Music from Captions |
| topic | Sound Artificial Intelligence Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2412.16526 |