Jukebox: A Generative Model for Music
We introduce Jukebox, a model that generates music with singing in the raw audio domain. We tackle the long context of raw audio using a multi-scale VQ-VAE to compress it to discrete codes, and modeling those using autoregressive Transformers. We show that the combined model at scale can generate high-fidelity and diverse songs with coherence up to multiple minutes. We can condition on artist and genre to steer the musical and vocal style, and on unaligned lyrics to make the singing more controllable. We are releasing thousands of non cherry-picked samples at https://jukebox.openai.com, along with model weights and code at https://github.com/openai/jukebox
Code (12)
Tasks
modelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Novel Audio Representation for Music Genre Identification in MIR
For Music Information Retrieval downstream tasks, the most common audio representation is time-frequency-based, such as Mel spectrograms. In order to identify musical genres, this study explores the possibilities of a ne…
Information RetrievalMusic Information RetrievalQuantizationRetrievalCodified audio language modeling learns useful representations for music information retrieval
We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for downstream MIR tasks. Specifically, we explore representations from Jukebox (Dhariwal…
Emotion RecognitionGenre classificationInformation RetrievalKey Detection+7Unsupervised Source Separation By Steering Pretrained Music Models
We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generation model is conditioned on an input mixt…
Audio GenerationAudio Source SeparationMusic GenerationMusic Tagging+1Transfer Learning with Jukebox for Music Source Separation
In this work, we demonstrate how a publicly available, pre-trained Jukebox model can be adapted for the problem of audio source separation from a single mixed audio channel. Our neural network architecture, which is usin…
Audio Source SeparationMusic Source SeparationTransfer LearningMelody transcription via generative pre-training
Despite the central role that melody plays in music perception, it remains an open challenge in music information retrieval to reliably detect the notes of the melody present in an arbitrary music recording. A key challe…
Chord RecognitionInformation RetrievalMusic Information RetrievalRetrieval