arXiv subjects

György Fazekas

Publications and source records attributed to György Fazekas.

At least 19 recordsLinked to original sources

arXiv2026

Fast Diffusion-GAN Model for Generating Symbolic Music with Emotions

Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progress has been made on using diffusion models to generate symbolic music since this class of generative models struggles with discrete data while its iterative sampling process is computationally expensive. In this work, we propose a diffusion model integrated with a Generative Adversarial Network, aiming to mitigate the slow sampling drawback of diffusion models applied to symbolic music generation. We enable the use of diffusion model by representing symbolic music as image-like pianorolls with velocity values instead of discrete event tokens and then used a Variational Autoencoder to obtain their latent representations to train the proposed diffusion model. Our results demonstrate the successful control of our diffusion model to generate symbolic music with a desired emotion. Our model uses merely 15 denoising diffusion steps to produce high-quality music, while most diffusion models for symbolic music generation require hundreds or thousands of steps.

cs.SD↗

arXiv2026

Self-Representation Alignment in Diffusion Models for Video Background Music Generation

Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learned in the diffusion models' denoising process are insufficiently meaningful, which can hinder the generation performance. To address this, we propose a novel diffusion U-Net architecture enhanced by explicitly aligning the weaker representation from the earlier layer conditioned on higher noise with the better representation from the later layer conditioned on lower noise during training, which we use for the challenging multimodal task of video background music generation. Our diffusion U-Net Self-Representation Alignment (U-SRA) employs an alignment loss to effectively guide our diffusion model to learn good internal representations, thereby enabling it to produce higher-quality symbolic music conditioned on video features. We employ a cross-attention mechanism to synchronize music with video segments. Experiments on a benchmark video-music dataset demonstrate that the proposed U-SRA approach for video background music generation surpasses the state-of-the-art across key evaluation metrics, including video-music alignment and overall music quality.

cs.AI↗

arXiv2026

Unsupervised Instantaneous Phase and Frequency Tracking by Inverse Voice Synthesis

Knowledge-driven neural vocoders struggle to learn reliable fundamental frequency end-to-end, because spectral objectives provide weak supervision of periodic structure and lack phase information. We address this with a source-filter model whose alias-free additive source makes the instantaneous phase of the glottal cycle explicit; differentiating it yields the instantaneous frequency, and thus $F_0$, without an external tracker. Waveform error supervises only the deterministic harmonic path, while a spectral loss covers the full signal. On M4Singer and LM-SSD, the reconstruction is phase-aligned, reaching a signal-to-reconstruction-error ratio of 8.1 dB, while neural baselines remain negative. However, GOLF, given an external $F_0$, still reaches lower spectral distortion. On LM-SSD, the recovered $F_0$ attains the highest overall accuracy of any method tested, including supervised neural pitch trackers applied off the shelf, and the glottal closure instants come within 0.53 points of REAPER's identification rate, without any $F_0$ label.

eess.AS↗

arXiv2026

Pitch Smoothing Using Relative Interval Networks

Pitch tracking systems typically couple a per-frame fundamental frequency ($F_0$) estimator with a temporal smoothing stage to obtain continuous trajectories. Conventional Viterbi smoothers enforce first-order continuity but lack long-term temporal awareness and could lock into octave errors across corrupted frames. We propose Relative Interval Networks (RIN), a trajectory smoothing framework that reconciles per-frame pitch estimates with data-driven multi-hop pitch differences. We extract robust relative pitch intervals across arbitrary frame offsets using Variable-Q Transform cross-correlation. We formulate pitch smoothing as an $L_1$-norm optimization problem and prove its equivalence to a minimum cost circulation problem, solved efficiently via linear programming. Evaluations across speech, singing, and instrumental datasets show that RIN substantially improves weak estimators, matches or outperforms Viterbi decoding at a comparable computational cost, and provides superior robustness under certain acoustic degradation.

eess.AS↗

arXiv2026

Steering dense music retrieval with open-vocabulary concept discovery

Controllable music retrieval lets users find music that is, for example, more ambient, less distorted, or without guitar while preserving the other semantic content of an original seed query. Sparse autoencoders (SAEs) are a promising interface for this kind of concept-level control, but a key problem remains: given a free-form text concept, which sparse features should be edited? In shared multimodal embedding spaces, standard attribution methods often select neurons that match the concept's wording but not the audio examples that express it. This leads to weak or unstable edits: relevant features are missed when concepts are distributed across neurons, while others are selected due to text alignment rather than audio-side structure. We address this with a lightweight, training-free method that recovers a sparse set of audio features whose decoded representation reconstructs the target concept while remaining consistent with audio-space geometry. This reframes concept attribution as a sparse inversion problem rather than a text-side neuron-ranking heuristic. The method requires neither paired audio-text supervision nor SAE retraining. We evaluate this approach in steerable music retrieval and show that the recovered supports align more closely with concept-bearing audio examples and achieve a stronger trade-off between edit strength and preservation than alignment baselines, enabling more precise concept amplification and suppression with reduced drift on preservation metrics.

cs.SD↗

arXiv2025

Accelerating Automatic Differentiation of Direct Form Digital Filters

We introduce a general formulation for automatic differentiation through direct form filters, yielding a closed-form backpropagation that includes initial condition gradients. The result is a single expression that can represent both the filter and its gradients computation while supporting parallelism. C++/CUDA implementations in PyTorch achieve at least 1000x speedup over naive Python implementations and consistently run fastest on the GPU. For the low-order filters commonly used in practice, exact time-domain filtering with analytical gradients outperforms the frequency-domain method in terms of speed. The source code is available at https://github.com/yoyolicoris/philtorch.

eess.SY↗

arXiv2025

Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior

Style Transfer with Inference-Time Optimisation (ST-ITO) is a recent approach for transferring the applied effects of a reference audio to an audio track. It optimises the effect parameters to minimise the distance between the style embeddings of the processed audio and the reference. However, this method treats all possible configurations equally and relies solely on the embedding space, which can result in unrealistic configurations or biased outcomes. We address this pitfall by introducing a Gaussian prior derived from the DiffVox vocal preset dataset over the parameter space. The resulting optimisation is equivalent to maximum-a-posteriori estimation. Evaluations on vocal effects transfer on the MedleyDB dataset show significant improvements across metrics compared to baselines, including a blind audio effects estimator, nearest-neighbour approaches, and uncalibrated ST-ITO. The proposed calibration reduces the parameter mean squared error by up to 33% and more closely matches the reference style. Subjective evaluations with 16 participants confirm the superiority of our method in limited data regimes. This work demonstrates how incorporating prior knowledge at inference time enhances audio effects transfer, paving the way for more effective and realistic audio processing systems.

cs.SD↗

arXiv2025

Sound Matching an Analogue Levelling Amplifier Using the Newton-Raphson Method

Automatic differentiation through digital signal processing algorithms for virtual analogue modelling has recently gained popularity. These algorithms are typically more computationally efficient than black-box neural networks that rely on dense matrix multiplications. Due to their differentiable nature, they can be integrated with neural networks and jointly trained using gradient descent algorithms, resulting in more efficient systems. Furthermore, signal processing algorithms have significantly fewer parameters than neural networks, allowing the application of the Newton-Raphson method. This method offers faster and more robust convergence than gradient descent at the cost of quadratic storage. This paper presents a method to emulate analogue levelling amplifiers using a feed-forward digital compressor with parameters optimised via the Newton-Raphson method. We demonstrate that a digital compressor can successfully approximate the behaviour of our target unit, the Teletronix LA-2A. Different strategies for computing the Hessian matrix are benchmarked. We leverage parallel algorithms for recursive filters to achieve efficient training on modern GPUs. The resulting model is made into a VST plugin and is open-sourced at https://github.com/aim-qmul/4a2a.

eess.AS↗

arXiv2025

DiffVox: A Differentiable Model for Capturing and Analysing Vocal Effects Distributions

This study introduces a novel and interpretable model, DiffVox, for matching vocal effects in music production. DiffVox, short for ``Differentiable Vocal Fx", integrates parametric equalisation, dynamic range control, delay, and reverb with efficient differentiable implementations to enable gradient-based optimisation for parameter estimation. Vocal presets are retrieved from two datasets, comprising 70 tracks from MedleyDB and 365 tracks from a private collection. Analysis of parameter correlations reveals strong relationships between effects and parameters, such as the high-pass and low-shelf filters often working together to shape the low end, and the delay time correlating with the intensity of the delayed signals. Principal component analysis reveals connections to McAdams' timbre dimensions, where the most crucial component modulates the perceived spaciousness while the secondary components influence spectral brightness. Statistical testing confirms the non-Gaussian nature of the parameter distribution, highlighting the complexity of the vocal effects space. These initial findings on the parameter distributions set the foundation for future research in vocal effects modelling and automatic mixing. Our source code and datasets are accessible at https://github.com/SonyResearch/diffvox.

cs.SD↗

arXiv2025

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models

Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems controllable and interactive for users. In text-music retrieval, the ambiguity of freeform language creates a many-to-many mapping, often resulting in inflexible or unsatisfying results. We introduce Generative Diffusion Retriever (GDR), a novel framework that leverages diffusion models to generate queries in a retrieval-optimized latent space. This enables controllability through generative tools such as negative prompting and denoising diffusion implicit models (DDIM) inversion, opening a new direction in retrieval control. GDR improves retrieval performance over contrastive teacher models and supports retrieval in audio-only latent spaces using non-jointly trained encoders. Finally, we demonstrate that GDR enables effective post-hoc manipulation of retrieval behavior, enhancing interactive control for text-music retrieval tasks.

cs.SD↗

arXiv2025

SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding

Joint embedding spaces have significantly advanced music understanding and generation by linking text and audio through multimodal contrastive learning. However, these approaches face large memory requirement limitations due to relying on large batch sizes to effectively utilize negative samples. Further, multimodal joint embedding spaces suffer from a modality gap wherein embeddings from different modalities lie in different manifolds of the embedding space. To address these challenges, we propose Siamese Language-Audio Pretraining (SLAP), a novel multimodal pretraining framework that allows learning powerful representations without negative samples. SLAP adapts the Bootstrap Your Own Latent (BYOL) paradigm for multimodal audio-text training, promoting scalability in training multimodal embedding spaces. We illustrate the ability of our model to learn meaningful relationships between music and text -- specifically, we show that SLAP outperforms CLAP on tasks such as text-music retrieval and zero-shot classification. We also observe competitive downstream performance on several MIR tasks, including with larger or supervised models (genre and instrument classification, auto-tagging). Additionally, our approach has attractive properties, such as a quantifiably reduced modality gap and improved robustness to batch size variations on retrieval performance. Finally, its novel formulation unlocks large-scale training on a single GPU through gradient accumulation.

cs.SD↗

arXiv2025

Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching

Many audio synthesizers can produce the same signal given different parameter configurations, meaning the inversion from sound to parameters is an inherently ill-posed problem. We show that this is largely due to intrinsic symmetries of the synthesizer, and focus in particular on permutation invariance. First, we demonstrate on a synthetic task that regressing point estimates under permutation symmetry degrades performance, even when using a permutation-invariant loss function or symmetry-breaking heuristics. Then, viewing equivalent solutions as modes of a probability distribution, we show that a conditional generative model substantially improves performance. Further, acknowledging the invariance of the implicit parameter distribution, we find that performance is further improved by using a permutation equivariant continuous normalizing flow. To accommodate intricate symmetries in real synthesizers, we also propose a relaxed equivariance strategy that adaptively discovers relevant symmetries from data. Applying our method to Surge XT, a full-featured open source synthesizer used in real world audio production, we find our method outperforms regression and generative baselines across audio reconstruction metrics.

cs.SD↗

arXiv2025

Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation

The recent surge in the popularity of diffusion models for image synthesis has attracted new attention to their potential for generation tasks in other domains. However, their applications to symbolic music generation remain largely under-explored because symbolic music is typically represented as sequences of discrete events and standard diffusion models are not well-suited for discrete data. We represent symbolic music as image-like pianorolls, facilitating the use of diffusion models for the generation of symbolic music. Moreover, this study introduces a novel diffusion model that incorporates our proposed Transformer-Mamba block and learnable wavelet transform. Classifier-free guidance is utilised to generate symbolic music with target chords. Our evaluation shows that our method achieves compelling results in terms of music quality and controllability, outperforming the strong baseline in pianoroll generation. Our code is available at https://github.com/jinchengzhanggg/proffusion.

cs.SD↗

arXiv2024

Leave-One-EquiVariant: Alleviating invariance-related information loss in contrastive music representations

Contrastive learning has proven effective in self-supervised musical representation learning, particularly for Music Information Retrieval (MIR) tasks. However, reliance on augmentation chains for contrastive view generation and the resulting learnt invariances pose challenges when different downstream tasks require sensitivity to certain musical attributes. To address this, we propose the Leave One EquiVariant (LOEV) framework, which introduces a flexible, task-adaptive approach compared to previous work by selectively preserving information about specific augmentations, allowing the model to maintain task-relevant equivariances. We demonstrate that LOEV alleviates information loss related to learned invariances, improving performance on augmentation related tasks and retrieval without sacrificing general representation quality. Furthermore, we introduce a variant of LOEV, LOEV++, which builds a disentangled latent space by design in a self-supervised manner, and enables targeted retrieval based on augmentation related attributes.

cs.SD↗

arXiv2024

Composers' Evaluations of an AI Music Tool: Insights for Human-Centred Design

We present a study that explores the role of user-centred design in developing Generative AI (GenAI) tools for music composition. Through semi-structured interviews with professional composers, we gathered insights on a novel generative model for creating variations, highlighting concerns around trust, transparency, and ethical design. The findings helped form a feedback loop, guiding improvements to the model that emphasised traceability, transparency and explainability. They also revealed new areas for innovation, including novel features for controllability and research questions on the ethical and practical implementation of GenAI models.

cs.SD↗

arXiv2024

Exploring Transformer-Based Music Overpainting for Jazz Piano Variations

This paper explores transformer-based models for music overpainting, focusing on jazz piano variations. Music overpainting generates new variations while preserving the melodic and harmonic structure of the input. Existing approaches are limited by small datasets, restricting scalability and diversity. We introduce VAR4000, a subset of a larger dataset for jazz piano performances, consisting of 4,352 training pairs. Using a semi-automatic pipeline, we evaluate two transformer configurations on VAR4000, comparing their performance with the smaller JAZZVAR dataset. Preliminary results show promising improvements in generalisation and performance with the larger dataset configuration, highlighting the potential of transformer models to scale effectively for music overpainting on larger and more diverse datasets.

cs.SD↗

arXiv2024

Zero-Shot Duet Singing Voices Separation with Diffusion Models

In recent studies, diffusion models have shown promise as priors for solving audio inverse problems. These models allow us to sample from the posterior distribution of a target signal given an observed signal by manipulating the diffusion process. However, when separating audio sources of the same type, such as duet singing voices, the prior learned by the diffusion process may not be sufficient to maintain the consistency of the source identity in the separated audio. For example, the singer may change from one to another occasionally. Tackling this problem will be useful for separating sources in a choir, or a mixture of multiple instruments with similar timbre, without acquiring large amounts of paired data. In this paper, we examine this problem in the context of duet singing voices separation, and propose a method to enforce the coherency of singer identity by splitting the mixture into overlapping segments and performing posterior sampling in an auto-regressive manner, conditioning on the previous segment. We evaluate the proposed method on the MedleyVox dataset and show that the proposed method outperforms the naive posterior sampling baseline. Our source code and the pre-trained model are publicly available at https://github.com/iamycy/duet-svs-diffusion.

eess.AS↗

arXiv2024

Time-of-arrival Estimation and Phase Unwrapping of Head-related Transfer Functions With Integer Linear Programming

In binaural audio synthesis, aligning head-related impulse responses (HRIRs) in time has been an important pre-processing step, enabling accurate spatial interpolation and efficient data compression. The maximum correlation time delay between spatially nearby HRIRs has previously been used to get accurate and smooth alignment by solving a matrix equation in which the solution has the minimum Euclidean distance to the time delay. However, the Euclidean criterion could lead to an over-smoothing solution in practice. In this paper, we solve the smoothing issue by formulating the task as solving an integer linear programming problem equivalent to minimising an $L^1$-norm. Moreover, we incorporate 1) the cross-correlation of inter-aural HRIRs, and 2) HRIRs with their minimum-phase responses to have more reference measurements for optimisation. We show the proposed method can get more accurate alignments than the Euclidean-based method by comparing the spectral reconstruction loss of time-aligned HRIRs using spherical harmonics representation on seven HRIRs consisting of human and dummy heads. The extra correlation features and the $L^1$-norm are also beneficial in extremely noisy conditions. In addition, this method can be applied to phase unwrapping of head-related transfer functions, where the unwrapped phase could be a compact feature for downstream tasks.

cs.SD↗