Andreas Brendel

Shrishti Saha Shetu, Emanuël A. P. Habets, Andreas Brendel

In this study, we conduct a comprehensive comparative analysis of generative and discriminative deep learning-based speech enhancement methods, specifically in noise reduction tasks. Our investigation focuses on evaluating their effectiveness under high and low signal-to-noise ratio conditions, considering both matched and mismatched training scenarios. We further investigate the impact of training data volume, model convergence speed, and interpret the performance differences in terms of objective results for the considered training paradigms. Additionally, we compare the complexity-performance trade-off and the practical viability of these approaches. To further strengthen the evaluation, we study the hallucination characteristics of generative approaches in terms of word error rate and phoneme similarity. The insights derived from this study provide empirical evidence to assist researchers and practitioners in understanding whether the perceptual gains of different approaches justify their computational cost in practical applications.

Pietro Foti, Andreas Brendel

Recently, neural speech codecs (NSCs) trained as generative models have shown superior performance compared to conventional codecs at low bitrates. Although most state-of-the-art NSCs are trained as Generative Adversarial Networks (GANs), Diffusion Models (DMs), a recent class of generative models, represent a promising alternative due to their superior performance in image generation relative to GANs. Consequently, DMs have been successfully applied for audio and speech coding among various other audio generation applications. However, the design of diffusion-based NSCs has not yet been explored in a systematic way. We address this by providing a comprehensive analysis of diffusion-based NSCs divided into three contributions. First, we propose a categorization based on the conditioning and output domains of the DM. This simple conceptual framework allows us to define a design space for diffusion-based NSCs and to assign a category to existing approaches in the literature. Second, we systematically investigate unexplored designs by creating and evaluating new diffusion-based NSCs within the conceptual framework. Finally, we compare the proposed models to existing GAN and DM baselines through objective metrics and subjective listening tests.

Michael Günther, Andreas Brendel, Walter Kellermann

In multichannel signal processing with distributed sensors, choosing the optimal subset of observed sensor signals to be exploited is crucial in order to maximize algorithmic performance and reduce computational load, ideally both at the same time. In the acoustic domain, signal cross-correlation is a natural choice to quantify the usefulness of microphone signals, i.e., microphone utility, for array processing, but its estimation requires that the uncoded signals are synchronized and transmitted between nodes. In resource-constrained environments like acoustic sensor networks, low data transmission rates often make transmission of all observed signals to the centralized location infeasible, thus discouraging direct estimation of signal cross-correlation. Instead, we employ characteristic features of the recorded signals to estimate the usefulness of individual microphone signals. In this contribution, we provide a comprehensive analysis of model-based microphone utility estimation approaches that use signal features and, as an alternative, also propose machine learning-based estimation methods that identify optimal sensor signal utility features. The performance of both approaches is validated experimentally using both simulated and recorded acoustic data, comprising a variety of realistic and practically relevant acoustic scenarios including moving and static sources.

Andreas Brendel, Johannes Zeitler, Walter Kellermann

Many spatial filtering algorithms used for voice capture in, e.g., teleconferencing applications, can benefit from or even rely on knowledge of Relative Transfer Functions (RTFs). Accordingly, many RTF estimators have been proposed which, however, suffer from performance degradation under acoustically adverse conditions or need prior knowledge on the properties of the interfering sources. While state-of-the-art RTF estimators ignore prior knowledge about the acoustic enclosure, audio signal processing algorithms for teleconferencing equipment are often operating in the same or at least a similar acoustic enclosure, e.g., a car or an office, such that training data can be collected. In this contribution, we use such data to train Variational Autoencoders (VAEs) in an unsupervised manner and apply the trained VAEs to enhance imprecise RTF estimates. Furthermore, a hybrid between classic RTF estimation and the trained VAE is investigated. Comprehensive experiments with real-world data confirm the efficacy for the proposed method.

Thomas Haubner, Andreas Brendel, Walter Kellermann

We present a novel end-to-end deep learning-based adaptation control algorithm for frequency-domain adaptive system identification. The proposed method exploits a deep neural network to map observed signal features to corresponding step-sizes which control the filter adaptation. The parameters of the network are optimized in an end-to-end fashion by minimizing the average normalized system distance of the adaptive filter. This avoids the need of explicit signal power spectral density estimation as required for model-based adaptation control and further auxiliary mechanisms to deal with model inaccuracies. The proposed algorithm achieves fast convergence and robust steady-state performance for scenarios characterized by high-level, non-white and non-stationary additive noise signals, abrupt environment changes and additional model inaccuracies.

Thomas Haubner, Mhd. Modar Halimeh, Andreas Brendel et al.

We introduce a synergistic approach to double-talk robust acoustic echo cancellation combining adaptive Kalman filtering with a deep neural network-based postfilter. The proposed algorithm overcomes the well-known limitations of Kalman filter-based adaptation control in scenarios characterized by abrupt echo path changes. As the key innovation, we suggest to exploit the different statistical properties of the interfering signal components for robustly estimating the adaptation step size. This is achieved by leveraging the postfilter near-end estimate and the estimation error of the Kalman filter. The proposed synergistic scheme allows for rapid reconvergence of the adaptive filter after abrupt echo path changes without compromising the steady state performance achieved by state-of-the-art approaches in static scenarios.

Gabriel F Miller, Andreas Brendel, Walter Kellermann et al.

In this paper, we consider the problem of acoustic source localization by acoustic sensor networks (ASNs) using a promising, learning-based technique that adapts to the acoustic environment. In particular, we look at the scenario when a node in the ASN is displaced from its position during training. As the mismatch between the ASN used for learning the localization model and the one after a node displacement leads to erroneous position estimates, a displacement has to be detected and the displaced nodes need to be identified. We propose a method that considers the disparity in position estimates made by leave-one-node-out (LONO) sub-networks and uses a Markov random field (MRF) framework to infer the probability of each LONO position estimate being aligned, misaligned or unreliable while accounting for the noise inherent to the estimator. This probabilistic approach is advantageous over naive detection methods, as it outputs a normalized value that encapsulates conditional information provided by each LONO sub-network on whether the reading is in misalignment with the overall network. Experimental results confirm that the performance of the proposed method is consistent in identifying compromised nodes in various acoustic conditions.

Thomas Haubner, Andreas Brendel, Mohamed Elminshawi et al.

We present a noise-robust adaptation control strategy for block-online supervised acoustic system identification by exploiting a noise dictionary. The proposed algorithm takes advantage of the pronounced spectral structure which characterizes many types of interfering noise signals. We model the noisy observations by a linear Gaussian Discrete Fourier Transform-domain state space model whose parameters are estimated by an online generalized Expectation-Maximization algorithm. Unlike all other state-of-the-art approaches we suggest to model the covariance matrix of the observation probability density function by a dictionary model. We propose to learn the noise dictionary from training data, which can be gathered either offline or online whenever the system is not excited, while we infer the activations continuously. The proposed algorithm represents a novel machine-learning based approach to noise-robust adaptation control which allows for faster convergence in applications characterized by high-level and non-stationary interfering noise signals and abrupt system changes.

Thomas Haubner, Andreas Brendel, Walter Kellermann

In this paper we present a novel algorithm for improved block-online supervised acoustic system identification in adverse noise scenarios by exploiting prior knowledge about the space of Room Impulse Responses (RIRs). The method is based on the assumption that the variability of the unknown RIRs is controlled by only few physical parameters, describing, e.g., source position movements, and thus is confined to a low-dimensional manifold which is modelled by a union of affine subspaces. The offsets and bases of the affine subspaces are learned in advance from training data by unsupervised clustering followed by Principal Component Analysis. We suggest to denoise the parameter update of any supervised adaptive filter by projecting it onto an optimal affine subspace which is selected based on a novel computationally efficient approximation of the associated evidence. The proposed method significantly improves the system identification performance of state-of-the-art algorithms in adverse noise scenarios.

Tobias Gburrek, Joerg Schmalenstroeer, Andreas Brendel et al.

We present an approach to deep neural network based (DNN-based) distance estimation in reverberant rooms for supporting geometry calibration tasks in wireless acoustic sensor networks. Signal diffuseness information from acoustic signals is aggregated via the coherent-to-diffuse power ratio to obtain a distance-related feature, which is mapped to a source-to-microphone distance estimate by means of a DNN. This information is then combined with direction-of-arrival estimates from compact microphone arrays to infer the geometry of the sensor network. Unlike many other approaches to geometry calibration, the proposed scheme does only require that the sampling clocks of the sensor nodes are roughly synchronized. In simulations we show that the proposed DNN-based distance estimator generalizes to unseen acoustic environments and that precise estimates of the sensor node positions are obtained.

Heinrich Loellmann, Andreas Brendel, Peter Vary et al.

This contribution presents four algorithms developed by the authors for single-channel fullband and subband T60 estimation within the ACE challenge. The blind estimation of the fullband reverberation time (RT) by maximum-likelihood (ML) estimation based on [15] is considered as baseline approach. An improvement of this algorithm is devised where an energy-weighted averaging of the upper subband RT estimates is performed using either a DCT or 1/3-octave filter-bank. The evaluation results show that this approach leads to a lower variance for the estimation error in comparison to the baseline approach at the price of an increased computational complexity. Moreover, a new algorithm to estimate the subband RT is devised, where the RT estimates for the lower octave subbands are extrapolated from the RT estimates of the upper subbands by means of a simple model for the frequency-dependency of the subband RT. The evaluation results of the ACE challenge reveal that this approach allows to estimate the subband RT with an estimation error which is in a similar range as for the presented fullband RT estimators.