Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures

In this paper, we tackle the task of musical stem retrieval. Given a musical mix, it consists in retrieving a stem that would fit with it, i.e., that would sound pleasant if played together. To do so, we introduce a new method based on Joint-Embedding Predictive Architectures, where an encoder and a predictor are jointly trained to produce latent representations of a context and predict latent representations of a target. In particular, we design our predictor to be conditioned on arbitrary instruments, enabling our model to perform zero-shot stem retrieval. In addition, we discover that pretraining the encoder using contrastive learning drastically improves the model's performance. We validate the retrieval performances of our model using the MUSDB18 and MoisesDB datasets. We show that it significantly outperforms previous baselines on both datasets, showcasing its ability to support more or less precise (and possibly unseen) conditioning. We also evaluate the learned embeddings on a beat tracking task, demonstrating that they retain temporal structure and local information.

Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation

Autoregressive models are typically applied to sequences of discrete tokens, but recent research indicates that generating sequences of continuous embeddings in an autoregressive manner is also feasible. However, such Continuous Autoregressive Models (CAMs) can suffer from a decline in generation quality over extended sequences due to error accumulation during inference. We introduce a novel method to address this issue by injecting random noise into the input embeddings during training. This procedure makes the model robust against varying error levels at inference. We further reduce error accumulation through an inference procedure that introduces low-level noise. Experiments on musical audio generation show that CAM substantially outperforms existing autoregressive and non-autoregressive approaches while preserving audio quality over extended sequences. This work paves the way for generating continuous embeddings in a purely autoregressive setting, opening new possibilities for real-time and interactive generative applications.

Improving Musical Accompaniment Co-creation via Diffusion Transformers

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the underlying autoencoder to a stereo-capable model with superior fidelity and replace the latent U-Net with a Diffusion Transformer. Additionally, we refine text prompting by training a cross-modality predictive network to translate text-derived CLAP embeddings to audio-derived CLAP embeddings. Finally, we improve inference speed by training the latent model using a consistency framework, achieving competitive quality with fewer denoising steps. Our model is evaluated against the original Diff-A-Riff variant using objective metrics in ablation experiments, demonstrating promising advancements in all targeted areas. Sound examples are available at: https://sonycslparis.github.io/improved_dar/.

The evolution of inharmonicity and noisiness in contemporary popular music

Much of Western classical music uses instruments based on acoustic resonance. Such instruments produce harmonic or quasi-harmonic sounds. On the other hand, since the early 1970s, popular music has largely been produced in the recording studio. As a result, popular music is not bound to be based on harmonic or quasi-harmonic sounds. In this study, we use modified MPEG-7 features to explore and characterise the way in which the use of noise and inharmonicity has evolved in popular music since 1961. We set this evolution in the context of other broad categories of music, including Western classical piano music, Western classical orchestral music, and musique concr\`ete. We propose new features that allow us to distinguish between inharmonicity resulting from noise and inharmonicity resulting from interactions between relatively discrete partials. When the history of contemporary popular music is viewed through the lens of these new features, we find that the period since 1961 can be divided into three phases. From 1961 to 1972, there was a steady increase in inharmonicity but no significant increase in noise. From 1972 to 1986, both inharmonicity and noise increased. Then, since 1986, there has been a steady decrease in both inharmonicity and noise to today's popular music which is significantly less noisy but more inharmonic than the music of the sixties. We relate these observed trends to the development of music production practice over the period and illustrate them with focused analyses of certain key artists and tracks.

Music2Latent: Consistency Autoencoders for Latent Audio Compression

Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage training procedures, slow iterative sampling, or low reconstruction quality. We introduce Music2Latent, an audio autoencoder that overcomes these limitations by leveraging consistency models. Music2Latent encodes samples into a compressed continuous latent space in a single end-to-end training process while enabling high-fidelity single-step reconstruction. Key innovations include conditioning the consistency model on upsampled encoder outputs at all levels through cross connections, using frequency-wise self-attention to capture long-range frequency dependencies, and employing frequency-wise learned scaling to handle varying value distributions across frequencies at different noise levels. We demonstrate that Music2Latent outperforms existing continuous audio autoencoders in sound quality and reconstruction accuracy while achieving competitive performance on downstream MIR tasks using its latent representations. To our knowledge, this represents the first successful attempt at training an end-to-end consistency autoencoder model.

Controlling Surprisal in Music Generation via Information Content Curve Matching

In recent years, the quality and public interest in music generation systems have grown, encouraging research into various ways to control these systems. We propose a novel method for controlling surprisal in music generation using sequence models. To achieve this goal, we define a metric called Instantaneous Information Content (IIC). The IIC serves as a proxy function for the perceived musical surprisal (as estimated from a probabilistic model) and can be calculated at any point within a music piece. This enables the comparison of surprisal across different musical content even if the musical events occur in irregular time intervals. We use beam search to generate musical material whose IIC curve closely approximates a given target IIC. We experimentally show that the IIC correlates with harmonic and rhythmic complexity and note density. The correlation decreases with the length of the musical context used for estimating the IIC. Finally, we conduct a qualitative user study to test if human listeners can identify the IIC curves that have been used as targets when generating the respective musical material. We provide code for creating IIC interpolations and IIC visualizations on https://github.com/muthissar/iic.

Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation

This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel Joint-Embedding Predictive Architecture (JEPA) trained on a multi-track dataset using a self-supervised learning approach. Our model comprises two networks: an encoder and a predictor, which are jointly trained to predict the embeddings of compatible stems from the embeddings of a given context, typically a mix of several instruments. Training a model in this manner allows its use in estimating stem compatibility - retrieving, aligning, or generating a stem to match a given mix - or for downstream tasks such as genre or key estimation, as the training paradigm requires the model to learn information related to timbre, harmony, and rhythm. We evaluate our model's performance on a retrieval task on the MUSDB18 dataset, testing its ability to find the missing stem from a mix and through a subjective user study. We also show that the learned embeddings capture temporal alignment information and, finally, evaluate the representations learned by our model on several downstream tasks, highlighting that they effectively capture meaningful musical features.

Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models

Recent advancements in deep generative models present new opportunities for music production but also pose challenges, such as high computational demands and limited audio quality. Moreover, current systems frequently rely solely on text input and typically focus on producing complete musical pieces, which is incompatible with existing workflows in music production. To address these issues, we introduce "Diff-A-Riff," a Latent Diffusion Model designed to generate high-quality instrumental accompaniments adaptable to any musical context. This model offers control through either audio references, text prompts, or both, and produces 48kHz pseudo-stereo audio while significantly reducing inference time and memory usage. We demonstrate the model's capabilities through objective metrics and subjective listening tests, with extensive examples available on the accompanying website: sonycslparis.github.io/diffariff-companion/

Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning

This paper addresses the problem of self-supervised general-purpose audio representation learning. We explore the use of Joint-Embedding Predictive Architectures (JEPA) for this task, which consists of splitting an input mel-spectrogram into two parts (context and target), computing neural representations for each, and training the neural network to predict the target representations from the context representations. We investigate several design choices within this framework and study their influence through extensive experiments by evaluating our models on various audio classification benchmarks, including environmental sounds, speech and music downstream tasks. We focus notably on which part of the input data is used as context or target and show experimentally that it significantly impacts the model's quality. In particular, we notice that some effective design choices in the image domain lead to poor performance on audio, thus highlighting major differences between these two modalities.

Bass Accompaniment Generation via Latent Diffusion

The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the core of our method are audio autoencoders that efficiently compress audio waveform samples into invertible latent representations, and a conditional latent diffusion model that takes as input the latent encoding of a mix and generates the latent encoding of a corresponding stem. To provide control over the timbre of generated samples, we introduce a technique to ground the latent space to a user-provided reference style during diffusion sampling. For further improving audio quality, we adapt classifier-free guidance to avoid distortions at high guidance strengths when generating an unbounded latent space. We train our model on a dataset of pairs of mixes and matching bass stems. Quantitative experiments demonstrate that, given an input mix, the proposed system can generate basslines with user-specified timbres. Our controllable conditional audio generation framework represents a significant step forward in creating generative AI tools to assist musicians in music production.