arXiv subjects

Pavel Rajmic

Publications and source records attributed to Pavel Rajmic.

At least 19 recordsLinked to original sources

arXiv2026

Audio Inpainting in Time-Frequency Domain with Phase-Aware Prior

We address the problem of time-frequency audio inpainting, where the goal is to fill missing spectrogram portions with consistent information. Despite recent advances, existing approaches still face limitations in both reconstruction quality and computational efficiency. To bridge this gap, we propose a method that utilizes a phase-aware signal prior which exploits estimates of the instantaneous frequency. An optimization problem is formulated and solved using the generalized Chambolle-Pock algorithm. The proposed method is evaluated against other time-frequency inpainting methods, specifically a deep-prior audio inpainting neural network, the autoregression-based approach known as Janssen-TF, and a sparsity-driven baseline. For short gap durations, the proposed approach achieves superior SNR, while performing comparably to Janssen-TF on larger gaps. In terms of perceptual quality (both objective and subjective), the proposed method consistently outperforms existing methods across all gap lengths. In addition, the reconstructions are obtained with a substantially reduced computational cost compared to alternative methods.

eess.AS↗

arXiv2026

Music Restoration via Latent Operator Optimization and Diffusion Model Priors

Music restoration seeks to recover a clean signal from an observed recording degraded by an unknown effect, distortion, or corruption. Existing systems often rely on paired training data and distortion-specific supervision, which limits their use when the forward process is not known in advance. We propose LOUDAR (Latent-space Optimization of Unknown Distortion for Audio Restoration) a general-purpose restoration method that operates in the latent space of a pretrained audio autoencoder and models the unknown distortion as a learnable latent operator. At inference time, LOUDAR alternates between estimating the clean latent variable and updating the latent operator parameters. An unconditional latent diffusion model provides a prior over clean audio and regularizes this inference by steering the latent estimate toward the manifold of clean recordings. Because the degradation model is adapted per input, the approach is broadly applicable across diverse restoration problems. We evaluate LOUDAR on singing voice effect removal and restoration, as well as guitar distortion removal, and show that it consistently improves over degraded inputs and is competitive with supervised and unsupervised baselines in waveform and latent domains.

eess.AS↗

arXiv2026

Audio dequantization using instantaneous frequency

We present a dequantization method that employs a phase-aware regularizer, originally successfully applied in an audio inpainting problem. The method promotes a temporal continuity of sinusoidal components in time-frequency representation of the audio signal, and avoids energy loss artifacts commonly encountered with l1-based regularization approaches. The proposed method is called the Phase-Aware Audio Dequantizer (PHADQ). The method is evaluated against the state-of-the-art using the SDR and PEMO-Q ODG objective metrics, and a~subjective MUSHRA-like test.

eess.AS↗

arXiv2025

Regularized autoregressive modeling and its application to audio signal reconstruction

Autoregressive (AR) modeling is invaluable in signal processing, in particular in speech and audio fields. Attempts in the literature can be found that regularize or constrain either the time-domain signal values or the AR coefficients, which is done for various reasons, including the incorporation of prior information or numerical stabilization. Although these attempts are appealing, an encompassing and generic modeling framework is still missing. We propose such a framework and the related optimization problem and algorithm. We discuss the computational demands of the algorithm and explore the effects of various improvements on its convergence speed. In the experimental part, we demonstrate the usefulness of our approach on the audio declipping and dequantization problems. We compare its performance against state-of-the-art methods and demonstrate the competitiveness of the proposed method in declipping musical signals, and its superiority in declipping speech. The evaluation includes a heuristic algorithm of generalized linear prediction (GLP), a strong competitor which has only been presented as a patent and is new in the scientific community.

eess.AS↗

arXiv2025

A MATLAB toolbox for Computation of Speech Transmission Index (STI)

The speech transmission index (STI) is a popular simple metric for the prediction of speech intelligibility when speech is passed through a transmission channel. Computation of STI from acoustic measurements is described in the IEC 60268-16:2020 standard. Though, reliable implementations of STI are not publicly accessible and are frequently limited to the use with a proprietary measurement hardware. We present a Matlab STI implementation of both the direct and indirect approaches according to the standard, including the shortened STIPA protocol. The suggested implementation meets prescribed requirements, as evidenced by tests on reference signals. Additionally, we conducted a verification measurement in comparison to a commercial measurement device. Our software comes with open source code.

eess.AS↗

arXiv2025

Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approaches

Accurately estimating nonlinear audio effects without access to paired input-output signals remains a challenging problem. This work studies unsupervised probabilistic approaches for solving this task. We introduce a method, novel for this application, based on diffusion generative models for blind system identification, enabling the estimation of unknown nonlinear effects using black- and gray-box models. This study compares this method with a previously proposed adversarial approach, analyzing the performance of both methods under different parameterizations of the effect operator and varying lengths of available effected recordings. Through experiments on guitar distortion effects, we show that the diffusion-based approach provides more stable results and is less sensitive to data availability, while the adversarial approach is superior at estimating more pronounced distortion effects. Our findings contribute to the robust unsupervised blind estimation of audio effects, demonstrating the potential of diffusion models for system identification in music technology.

eess.AS↗

arXiv2025

Tweaking autoregressive methods for inpainting of gaps in audio signals

A novel variant of the Janssen method for audio inpainting is presented and compared to other popular audio inpainting methods based on autoregressive (AR) modeling. Both conceptual differences and practical implications are discussed. The experiments demonstrate the importance of the choice of the AR model estimator, window/context length, and model order. The results show the superiority of the proposed gap-wise Janssen approach using objective metrics, which is confirmed by a listening test.

eess.AS↗

arXiv2025

Janssen 2.0: Audio Inpainting in the Time-frequency Domain

The paper focuses on inpainting missing parts of an audio signal spectrogram, i.e., estimating the lacking time-frequency coefficients. The autoregression-based Janssen algorithm, a state-of-the-art for the time-domain audio inpainting, is adapted for the time-frequency setting. This novel method, termed Janssen-TF, is compared with the deep-prior neural network approach using both objective metrics and a subjective listening test, proving Janssen-TF to be superior in all the considered measures.

eess.AS↗

arXiv2025

Dequantization of a signal from two parallel quantized observations

We propose a technique of signal acquisition using a combination of two devices with different sampling rates and quantization accuracies. Subsequent processing involving sparsity regularization enables us to reconstruct the signal at such a sampling frequency and with such a bit depth that was not possible using the two devices independently. Objective and subjective tests show the superiority of the proposed method in comparison with alternatives.

eess.SP↗

arXiv2023

Improving DCE-MRI through unfolded low-rank + sparse optimisation

A method for perfusion imaging with DCE-MRI is developed based on two popular paradigms: the low-rank + sparse model for optimisation-based reconstruction, and the deep unfolding. A learnable algorithm derived from a proximal algorithm is designed with emphasis on simplicity and interpretability. The resulting deep network is trained and evaluated using a simulated measurement of a rat with a brain tumor, showing large performance gain over the classical low-rank + sparse baseline. Moreover, quantitative perfusion analysis is performed based on the reconstructed sequence, proving that even training based on a simple pixel-wise error can lead to significant improvement of the quality of the perfusion maps.

eess.SP↗

arXiv2023

Multiple Hankel matrix rank minimization for audio inpainting

Sasaki et al. (2018) presented an efficient audio declipping algorithm, based on the properties of Hankel-structure matrices constructed from time-domain signal blocks. We adapt their approach to solving the audio inpainting problem, where samples are missing in the signal. We analyze the algorithm and provide modifications, some of them leading to an improved performance. Overall, it turns out that the new algorithms perform reasonably well for speech signals but they are not competitive in the case of music signals.

eess.AS↗

arXiv2022

Audio Declipping with (Weighted) Analysis Social Sparsity

We develop the analysis (cosparse) variant of the popular audio declipping algorithm of Siedenburg et al. (2014). Furthermore, we extend both the old and the new variants by the possibility of weighting the time-frequency coefficients. We examine the audio reconstruction performance of several combinations of weights and shrinkage operators. The weights are shown to improve the reconstruction quality in some cases; however, the best scores achieved by the non-weighted methods are not surpassed with the help of weights. Yet, the analysis Empirical Wiener (EW) shrinkage was able to reach the quality of a computationally more expensive competitor, the Persistent Empirical Wiener (PEW). Moreover, the proposed analysis variant incorporating PEW slightly outperforms the synthesis counterpart in terms of an auditorily motivated metric.

eess.AS↗

arXiv2021

Audio declipping performance enhancement via crossfading

Some audio declipping methods produce waveforms that do not fully respect the physical process of clipping, which is why we refer to them as inconsistent. This letter reports what effect on perception it has if the solution by inconsistent methods is forced consistent by postprocessing. We first propose a simple sample replacement method, then we identify its main weaknesses and propose an improved variant. The experiments show that the vast majority of inconsistent declipping methods significantly benefit from the proposed approach in terms of objective perceptual metrics. In particular, we show that the SS PEW method based on social sparsity combined with the proposed method performs comparable to top methods from the consistent class, but at a computational cost of one order of magnitude lower.

eess.AS↗

arXiv2021

Audio Dequantization Using (Co)Sparse (Non)Convex Methods

The paper deals with the hitherto neglected topic of audio dequantization. It reviews the state-of-the-art sparsity-based approaches and proposes several new methods. Convex as well as non-convex approaches are included, and all the presented formulations come in both the synthesis and analysis variants. In the experiments the methods are evaluated using the signal-to-distortion ratio (SDR) and PEMO-Q, a perceptually motivated metric.

eess.AS↗

arXiv2021

A survey and an extensive evaluation of popular audio declipping methods

Dynamic range limitations in signal processing often lead to clipping, or saturation, in signals. The task of audio declipping is estimating the original audio signal, given its clipped measurements, and has attracted much interest in recent years. Audio declipping algorithms often make assumptions about the underlying signal, such as sparsity or low-rankness, and about the measurement system. In this paper, we provide an extensive review of audio declipping algorithms proposed in the literature. For each algorithm, we present assumptions that are made about the audio signal, the modeling domain, and the optimization algorithm. Furthermore, we provide an extensive numerical evaluation of popular declipping algorithms, on real audio data. We evaluate each algorithm in terms of the Signal-to-Distortion Ratio, and also using perceptual metrics of sound quality. The article is accompanied by a repository containing the evaluated methods.

eess.AS↗

arXiv2020

Approximal operator with application to audio inpainting

In their recent evaluation of time-frequency representations and structured sparsity approaches to audio inpainting, Lieb and Stark (2018) have used a particular mapping as a proximal operator. This operator serves as the fundamental part of an iterative numerical solver. However, their mapping is improperly justified. The present article proves that their mapping is indeed a proximal operator, and also derives its proper counterpart. Furthermore, it is rationalized that Lieb and Stark's operator can be understood as an approximation of the proper mapping. Surprisingly, in most cases, such an approximation (referred to as the approximal operator) is shown to provide even better numerical results in audio inpainting compared to its proper counterpart, while being computationally much more effective.

eess.AS↗

arXiv2020

Audio Inpainting: Revisited and Reweighted

We deal with the problem of sparsity-based audio inpainting, i.e. filling in the missing segments of audio. A consequence of the approaches based on mathematical optimization is the insufficient amplitude of the signal in the filled gaps. Remaining in the framework based on sparsity and convex optimization, we propose improvements to audio inpainting, aiming at compensating for such an energy loss. The new ideas are based on different types of weighting, both in the coefficient and the time domains. We show that our propositions improve the inpainting performance in terms of both the SNR and ODG.

eess.AS↗

arXiv2020

Flexible framework for audio reconstruction

The paper presents a unified, flexible framework for the tasks of audio inpainting, declipping, and dequantization. The concept is further extended to cover analogous degradation models in a transformed domain, e.g. quantization of the signal's time-frequency coefficients. The task of reconstructing an audio signal from degraded observations in two different domains is formulated as an inverse problem, and several algorithmic solutions are developed. The viability of the presented concept is demonstrated on an example where audio reconstruction from partial and quantized observations of both the time-domain signal and its time-frequency coefficients is carried out.

eess.AS↗