Download Grey-Box Modelling of Dynamic Range Compression This paper explores the digital emulation of analog dynamic range compressors, proposing a grey-box model that uses a combination of traditional signal processing techniques and machine learning. The main idea is to use the structure of a traditional digital compressor in a machine learning framework, so it can be trained end-to-end to create a virtual analog model of a compressor from data. The complexity of the model can be adjusted, allowing a trade-off between the model accuracy and computational cost. The proposed model has interpretable components, so its behaviour can be controlled more readily after training in comparison to a black-box model. The result is a model that achieves similar accuracy to a black-box baseline, whilst requiring less than 10% of the number of operations per sample at runtime.
Download Realistic Gramophone Noise Synthesis Using a Diffusion Model This paper introduces a novel data-driven strategy for synthesizing gramophone noise audio textures. A diffusion probabilistic model is applied to generate highly realistic quasiperiodic noises. The proposed model is designed to generate samples of length equal to one disk revolution, but a method to generate plausible periodic variations between revolutions is also proposed. A guided approach is also applied as a conditioning method, where an audio signal generated with manually-tuned signal processing is refined via reverse diffusion to improve realism. The method has been evaluated in a subjective listening test, in which the participants were often unable to recognize the synthesized signals from the real ones. The synthetic noises produced with the best proposed unconditional method are statistically indistinguishable from real noise recordings. This work shows the potential of diffusion models for highly realistic audio synthesis tasks.
Download A Diffusion-Based Generative Equalizer for Music Restoration This paper presents a novel approach to audio restoration, focusing on the enhancement of low-quality music recordings, and in particular historical ones. Building upon a previous algorithm called BABE, or Blind Audio Bandwidth Extension, we introduce BABE-2, which presents a series of improvements. This research broadens the concept of bandwidth extension to generative equalization, a task that, to the best of our knowledge, has not been previously addressed for music restoration. BABE-2 is built around an optimization algorithm utilizing priors from diffusion models, which are trained or fine-tuned using a curated set of high-quality music tracks. The algorithm simultaneously performs two critical tasks: estimation of the filter degradation magnitude response and hallucination of the restored audio. The proposed method is objectively evaluated on historical piano recordings, showing an enhancement over the prior version. The method yields similarly impressive results in rejuvenating the works of renowned vocalists Enrico Caruso and Nellie Melba. This research represents an advancement in the practical restoration of historical music. Historical music restoration examples are available at: research.spa.aalto.fi/publications/papers/dafx-babe2/.
Download RIR2FDN: An Improved Room Impulse Response Analysis and Synthesis This paper seeks to improve the state-of-the-art in delay-networkbased analysis-synthesis of measured room impulse responses (RIRs). We propose an informed method incorporating improved energy decay estimation and synthesis with an optimized feedback delay network. The performance of the presented method is compared against an end-to-end deep-learning approach. A formal listening test was conducted where participants assessed the similarity of reverberated material across seven distinct RIRs and three different sound sources. The results reveal that the performance of these methods is influenced by both the excitation sounds and the reverberation conditions. Nonetheless, the proposed method consistently demonstrates higher similarity ratings compared to the end-to-end approach across most conditions. However, achieving an indistinguishable synthesis of measured RIRs remains a persistent challenge, underscoring the complexity of this problem. Overall, this work helps improve the sound quality of analysis-based artificial reverberation.
Download Sitrano: A Matlab App for Sines-Transients-Noise Decomposition of Audio Signals Decomposition of sounds into their sinusoidal, transient, and noise
components is an active research topic and a widely-used tool in
audio processing. Multiple solutions have been proposed in recent
years, using time–frequency representations to identify either horizontal and vertical structures or orientations and anisotropy in the
spectrogram of the sound. In this paper, we present SiTraNo: an
easy-to-use MATLAB application with a graphic user interface for
audio decomposition that enables visualization and access to the
sinusoidal, transient, and noise classes, individually. This application allows the user to choose between different well-known separation methods to analyze an input sound file, to instantaneously
control and remix its spectral components, and to visually check
the quality of the separation, before producing the desired output
file. The visualization of common artifacts, such as birdies and
dropouts, is demonstrated. This application promotes experimenting with the sound decomposition process by observing the effect
of variations for each spectral component on the original sound
and by comparing different methods against each other, evaluating
the separation quality both audibly and visually. SiTraNo and its
source code are available on a companion website and repository.
Download Perceptual Decorrelator Based on Resonators Decorrelation filters transform mono audio into multiple decorrelated copies. This paper introduces a novel decorrelation filter design based on a resonator bank, which produces a sum of over a thousand exponentially decaying sinusoids. A headphone listening test was used to identify the minimum inter-channel time delays that perceptually match ERB-filtered coherent noise to corresponding incoherent noise. The decay rate of each resonator is set based on a group delay profile determined by the listening test results at its corresponding frequency. Furthermore, the delays from the test are used to refine frequency-dependent windowing in coherence estimation, which we argue represents the perceptually most accurate way of assessing interaural coherence. This coherence measure then guides an optimization process that adjusts the initial phases of the sinusoids to minimize the coherence between two instances of the resonator-based decorrelator. The delay results establish the necessary group delay per ERB for effective decorrelation, revealing higher-than-expected values, particularly at higher frequencies. For comparison, the optimization is also performed using two previously proposed group-delay profiles: one based on the period of the ERB band center frequency and another based on the maximum group-delay limit before introducing smearing. The results indicate that the perceptually informed profile achieves equal decorrelation to the latter profile while smearing less at high frequencies. Overall, optimizing the phase response of the proposed decorrelator yields significantly lower coherence compared to using a random phase.
Download Zero-Phase Sound via Giant FFT Given the speedy computation of the FFT in current computer
hardware, there are new possibilities for examining transformations for very long sounds. A zero-phase version of any audio
signal can be obtained by zeroing the phase angle of its complex
spectrum and taking the inverse FFT. This paper recommends additional processing steps, including zero-padding, transient suppression at the signal’s start and end, and gain compensation, to
enhance the resulting sound quality. As a result, a sound with the
same spectral characteristics as the original one, but with different temporal events, is obtained. Repeating rhythm patterns are
retained, however. Zero-phase sounds are palindromic in the sense
that they are symmetric in time. A comparison of the zero-phase
conversion to the autocorrelation function helps to understand its
properties, such as why the rhythm of the original sound is emphasized. It is also argued that the zero-phase signal has the same
autocorrelation function as the original sound. One exciting variation of the method is to apply the method separately to the real
and imaginary parts of the spectrum to produce a stereo effect. A
frame-based technique enables the use of the zero-phase conversion in real-time audio processing. The zero-phase conversion is
another member of the giant FFT toolset, allowing the modification of sampled sounds, such as drum loops or entire songs.
Download Dark Velvet Noise This paper proposes dark velvet noise (DVN) as an extension of the original velvet noise with a lowpass spectrum. The lowpass spectrum is achieved by allowing each pulse in the sparse sequence to have a randomized pulse width. The cutoff frequency is controlled by the density of the sequence. The modulated pulse-width can be implemented efficiently utilizing a discrete set of recursive running-sum filters, one for each unique pulse width. DVN may be used in reverberation algorithms. Typical room reverberation has a frequency-dependent decay, where the high frequencies decay faster than the low ones. A similar effect is achieved by lowering the density and increasing the pulse-width of DVN in time, thereby making the DVN suitable for artificial reverberation.
Download Granular analysis/synthesis of percussive drilling sounds This paper deals with the automatic and robust analysis, and the realistic and low-cost synthesis of percussive drilling like sounds. The two contributions are: a non-supervised removal of quasistationary background noise based on the Non-negative Matrix Factorization, and a granular method for analysis/synthesis of this drilling sounds. These two points are appropriate to the acoustical properties of percussive drilling sounds, and can be extended to other sounds with similar characteristics. The context of this work is the training of operators of working machines using simulators. Additionally, an implementation is explained.
Download Differentiable Feedback Delay Network for Colorless Reverberation Artificial reverberation algorithms often suffer from spectral coloration, usually in the form of metallic ringing, which impairs the perceived quality of sound. This paper proposes a method to reduce the coloration in the feedback delay network (FDN), a popular artificial reverberation algorithm. An optimization framework is employed entailing a differentiable FDN to learn a set of parameters decreasing coloration. The optimization objective is to minimize the spectral loss to obtain a flat magnitude response, with an additional temporal loss term to control the sparseness of the impulse response. The objective evaluation of the method shows a favorable narrower distribution of modal excitation while retaining the impulse response density. The subjective evaluation demonstrates that the proposed method lowers perceptual coloration of late reverberation, and also shows that the suggested optimization improves sound quality for small FDN sizes. The method proposed in this work constitutes an improvement in the design of accurate and high-quality artificial reverberation, simultaneously offering computational savings.