arXiv subjects

Maximo Cobos

Publications and source records attributed to Maximo Cobos.

18 recordsLinked to original sources

arXiv2025

Real-Time Object Tracking with On-Device Deep Learning for Adaptive Beamforming in Dynamic Acoustic Environments

Advances in object tracking and acoustic beamforming are driving new capabilities in surveillance, human-computer interaction, and robotics. This work presents an embedded system that integrates deep learning-based tracking with beamforming to achieve precise sound source localization and directional audio capture in dynamic environments. The approach combines single-camera depth estimation and stereo vision to enable accurate 3D localization of moving objects. A planar concentric circular microphone array constructed with MEMS microphones provides a compact, energy-efficient platform supporting 2D beam steering across azimuth and elevation. Real-time tracking outputs continuously adapt the array's focus, synchronizing the acoustic response with the target's position. By uniting learned spatial awareness with dynamic steering, the system maintains robust performance in the presence of multiple or moving sources. Experimental evaluation demonstrates significant gains in signal-to-interference ratio, making the design well-suited for teleconferencing, smart home devices, and assistive technologies.

cs.SD↗

arXiv2025

Frequency-Invariant Beamforming in Elevation and Azimuth via Autograd and Concentric Circular Microphone Arrays

The use of planar and concentric circular microphone arrays in beamforming has gained attention due to their ability to optimize both azimuth and elevation angles, making them ideal for spatial audio tasks like sound source localization and noise suppression. Unlike linear arrays, which restrict steering to a single axis, 2D arrays offer dual-axis optimization, although elevation control remains challenging. This study explores the integration of autograd, an automatic differentiation tool, with concentric circular arrays to impose beamwidth and frequency invariance constraints. This enables continuous optimization over both angles while maintaining performance across a wide frequency range. We evaluate our method through simulations of beamwidth, white noise gain, and directivity across multiple frequencies. A comparative analysis is presented against standard and advanced beamformers, including delay-and-sum, modified delay-and-sum, a Jacobi-Anger expansion-based method, and a Gaussian window-based gradient descent approach. Our method achieves superior spatial selectivity and narrower mainlobes, particularly in the elevation axis at lower frequencies. These results underscore the effectiveness of our approach in enhancing beamforming performance for acoustic sensing and spatial audio applications requiring precise dual-axis control.

cs.SD↗

arXiv2025

Spike Encoding for Environmental Sound: A Comparative Benchmark

Spiking Neural Networks (SNNs) offer energy efficient processing suitable for edge applications, but conventional sensor data must first be converted into spike trains for neuromorphic processing. Environmental sound, including urban soundscapes, poses challenges due to variable frequencies, background noise, and overlapping acoustic events, while most spike based audio encoding research has focused on speech. This paper analyzes three spike encoding methods, Threshold Adaptive Encoding (TAE), Step Forward (SF), and Moving Window (MW) across three datasets: ESC10, UrbanSound8K, and TAU Urban Acoustic Scenes. Our multiband analysis shows that TAE consistently outperforms SF and MW in reconstruction quality, both per frequency band and per class across datasets. Moreover, TAE yields the lowest spike firing rates, indicating superior energy efficiency. For downstream environmental sound classification with a standard SNN, TAE also achieves the best performance among the compared encoders. Overall, this work provides foundational insights and a comparative benchmark to guide the selection of spike encoders for neuromorphic environmental sound processing.

cs.SD↗

arXiv2025

A Data-Driven Exploration of Elevation Cues in HRTFs: An Explainable AI Perspective Across Multiple Datasets

Precise elevation perception in binaural audio remains a challenge, despite extensive research on head-related transfer functions (HRTFs) and spectral cues. While prior studies have advanced our understanding of sound localization cues, the interplay between spectral features and elevation perception is still not fully understood. This paper presents a comprehensive analysis of over 600 subjects from 11 diverse public HRTF datasets, employing a convolutional neural network (CNN) model combined with explainable artificial intelligence (XAI) techniques to investigate elevation cues. In addition to testing various HRTF pre-processing methods, we focus on both within-dataset and inter-dataset generalization and explainability, assessing the model's robustness across different HRTF variations stemming from subjects and measurement setups. By leveraging class activation mapping (CAM) saliency maps, we identify key frequency bands that may contribute to elevation perception, providing deeper insights into the spectral features that drive elevation-specific classification. This study offers new perspectives on HRTF modeling and elevation perception by analyzing diverse datasets and pre-processing techniques, expanding our understanding of these cues across a wide range of conditions.

eess.SP↗

arXiv2023

Acoustic source localization in the spherical harmonics domain exploiting low-rank approximations

Acoustic signal processing in the spherical harmonics domain (SHD) is an active research area that exploits the signals acquired by higher order microphone arrays. A very important task is that concerning the localization of active sound sources. In this paper, we propose a simple yet effective method to localize prominent acoustic sources in adverse acoustic scenarios. By using a proper normalization and arrangement of the estimated spherical harmonic coefficients, we exploit low-rank approximations to estimate the far field modal directional pattern of the dominant source at each time-frame. The experiments confirm the validity of the proposed approach, with superior performance compared to other recent SHD-based approaches.

eess.AS↗

arXiv2021

TASK3 DCASE2021 Challenge: Sound event localization and detection using squeeze-excitation residual CNNs

Sound event localisation and detection (SELD) is a problem in the field of automatic listening that aims at the temporal detection and localisation (direction of arrival estimation) of sound events within an audio clip, usually of long duration. Due to the amount of data present in the datasets related to this problem, solutions based on deep learning have positioned themselves at the top of the state of the art. Most solutions are based on 2D representations of the audio (different spectrograms) that are processed by a convolutional-recurrent network. The motivation of this submission is to study the squeeze-excitation technique in the convolutional part of the network and how it improves the performance of the system. This study is based on the one carried out by the same team last year. This year, it has been decided to study how this technique improves each of the datasets (last year only the MIC dataset was studied). This modification shows an improvement in the performance of the system compared to the baseline using MIC dataset.

cs.SD↗

arXiv2021

Task 1A DCASE 2021: Acoustic Scene Classification with mismatch-devices using squeeze-excitation technique and low-complexity constraint

Acoustic scene classification (ASC) is one of the most popular problems in the field of machine listening. The objective of this problem is to classify an audio clip into one of the predefined scenes using only the audio data. This problem has considerably progressed over the years in the different editions of DCASE. It usually has several subtasks that allow to tackle this problem with different approaches. The subtask presented in this report corresponds to a ASC problem that is constrained by the complexity of the model as well as having audio recorded from different devices, known as mismatch devices (real and simulated). The work presented in this report follows the research line carried out by the team in previous years. Specifically, a system based on two steps is proposed: a two-dimensional representation of the audio using the Gamamtone filter bank and a convolutional neural network using squeeze-excitation techniques. The presented system outperforms the baseline by about 17 percentage points.

cs.SD↗

arXiv2021

Squeeze-Excitation Convolutional Recurrent Neural Networks for Audio-Visual Scene Classification

The use of multiple and semantically correlated sources can provide complementary information to each other that may not be evident when working with individual modalities on their own. In this context, multi-modal models can help producing more accurate and robust predictions in machine learning tasks where audio-visual data is available. This paper presents a multi-modal model for automatic scene classification that exploits simultaneously auditory and visual information. The proposed approach makes use of two separate networks which are respectively trained in isolation on audio and visual data, so that each network specializes in a given modality. The visual subnetwork is a pre-trained VGG16 model followed by a bidiretional recurrent layer, while the residual audio subnetwork is based on stacked squeeze-excitation convolutional blocks trained from scratch. After training each subnetwork, the fusion of information from the audio and visual streams is performed at two different stages. The early fusion stage combines features resulting from the last convolutional block of the respective subnetworks at different time steps to feed a bidirectional recurrent structure. The late fusion stage combines the output of the early fusion stage with the independent predictions provided by the two subnetworks, resulting in the final prediction. We evaluate the method using the recently published TAU Audio-Visual Urban Scenes 2021, which contains synchronized audio and video recordings from 12 European cities in 10 different scene classes. The proposed model has been shown to provide an excellent trade-off between prediction performance (86.5%) and system complexity (15M parameters) in the evaluation results of the DCASE 2021 Challenge.

cs.MM↗

arXiv2021

Fast Channel Estimation in the Transformed Spatial Domain for Analog Millimeter Wave Systems

Fast channel estimation in millimeter-wave (mmWave) systems is a fundamental enabler of high-gain beamforming, which boosts coverage and capacity. The channel estimation stage typically involves an initial beam training process where a subset of the possible beam directions at the transmitter and receiver is scanned along a predefined codebook. Unfortunately, the high number of transmit and receive antennas deployed in mmWave systems increase the complexity of the beam selection and channel estimation tasks. In this work, we tackle the channel estimation problem in analog systems from a different perspective than used by previous works. In particular, we propose to move the channel estimation problem from the angular domain into the transformed spatial domain, in which estimating the angles of arrivals and departures corresponds to estimating the angular frequencies of paths constituting the mmWave channel. The proposed approach, referred to as transformed spatial domain channel estimation (TSDCE) algorithm, exhibits robustness to additive white Gaussian noise by combining low-rank approximations and sample autocorrelation functions for each path in the transformed spatial domain. Numerical results evaluate the mean square error of the channel estimation and the direction of arrival estimation capability. TSDCE significantly reduces the first, while exhibiting a remarkably low computational complexity compared with well-known benchmarking schemes.

cs.IT↗

arXiv2020

Anomalous Sound Detection using unsupervised and semi-supervised autoencoders and gammatone audio representation

Anomalous sound detection (ASD) is, nowadays, one of the topical subjects in machine listening discipline. Unsupervised detection is attracting a lot of interest due to its immediate applicability in many fields. For example, related to industrial processes, the early detection of malfunctions or damage in machines can mean great savings and an improvement in the efficiency of industrial processes. This problem can be solved with an unsupervised ASD solution since industrial machines will not be damaged simply by having this audio data in the training stage. This paper proposes a novel framework based on convolutional autoencoders (both unsupervised and semi-supervised) and a Gammatone-based representation of the audio. The results obtained by these architectures substantially exceed the results presented as a baseline.

eess.AS↗

arXiv2020

Listen carefully and tell: an audio captioning system based on residual learning and gammatone audio representation

Automated audio captioning is machine listening task whose goal is to describe an audio using free text. An automated audio captioning system has to be implemented as it accepts an audio as input and outputs as textual description, that is, the caption of the signal. This task can be useful in many applications such as automatic content description or machine-to-machine interaction. In this work, an automatic audio captioning based on residual learning on the encoder phase is proposed. The encoder phase is implemented via different Residual Networks configurations. The decoder phase (create the caption) is run using recurrent layers plus attention mechanism. The audio representation chosen has been Gammatone. Results show that the framework proposed in this work surpass the baseline system in challenge results.

eess.AS↗

arXiv2020

Sound Event Localization and Detection using Squeeze-Excitation Residual CNNs

Sound Event Localization and Detection (SELD) is a problem related to the field of machine listening whose objective is to recognize individual sound events, detect their temporal activity, and estimate their spatial location. Thanks to the emergence of more hard-labeled audio datasets, deep learning techniques have become state-of-the-art solutions. The most common ones are those that implement a convolutional recurrent network (CRNN) having previously transformed the audio signal into multichannel 2D representation. The squeeze-excitation technique can be considered as a convolution enhancement that aims to learn spatial and channel feature maps independently rather than together as standard convolutions do. This is usually achieved by combining some global clustering operators, linear operators and a final calibration between the block input and its learned relationships. This work aims to improve the accuracy results of the baseline CRNN presented in DCASE 2020 Task 3 by adding residual squeeze-excitation (SE) blocks in the convolutional part of the CRNN. The followed procedure involves a grid search of the ratio parameter (used in the linear relationships) of the residual SE block, whereas the hyperparameters of the network remain the same as in the baseline. Experiments show that by simply introducing the residual SE blocks, the results obtained are able to improve the baseline considerably.

cs.SD↗

arXiv2020

Acoustic Scene Classification with Squeeze-Excitation Residual Networks

Acoustic scene classification (ASC) is a problem related to the field of machine listening whose objective is to classify/tag an audio clip in a predefined label describing a scene location (e. g. park, airport, etc.). Many state-of-the-art solutions to ASC incorporate data augmentation techniques and model ensembles. However, considerable improvements can also be achieved only by modifying the architecture of convolutional neural networks (CNNs). In this work we propose two novel squeeze-excitation blocks to improve the accuracy of a CNN-based ASC framework based on residual learning. The main idea of squeeze-excitation blocks is to learn spatial and channel-wise feature maps independently instead of jointly as standard CNNs do. This is usually achieved by some global grouping operators, linear operators and a final calibration between the input of the block and its obtained relationships. The behavior of the block that implements such operators and, therefore, the entire neural network, can be modified depending on the input to the block, the established residual configurations and the selected non-linear activations. The analysis has been carried out using the TAU Urban Acoustic Scenes 2019 dataset (https://zenodo.org/record/2589280) presented in the 2019 edition of the DCASE challenge. All configurations discussed in this document exceed the performance of the baseline proposed by the DCASE organization by 13\% percentage points. In turn, the novel configurations proposed in this paper outperform the residual configurations proposed in previous works.

cs.SD↗

arXiv2020

An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments

The problem of training with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning (DL) algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high number of samples. In the image domain, typical FSL applications include those related to face recognition. In the audio domain, music fraud or speaker recognition can be clearly benefited from FSL methods. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, using a limited number of samples. These sounds typically occur in domestic environments where many events corresponding to a wide variety of sound classes take place. Therefore, the detection of such alarms in a practical scenario can be considered an open-set recognition (OSR) problem. To address the lack of a dedicated public dataset for audio FSL, researchers usually make modifications on other available datasets. This paper is aimed at poviding the audio recognition community with a carefully annotated dataset (https://zenodo.org/record/3689288) for FSL in an OSR context comprised of 1360 clips from 34 classes divided into pattern sounds} and unwanted sounds. To facilitate and promote research on this area, results with state-of-the-art baseline systems based on transfer learning are also presented.

cs.SD↗

arXiv2020

Time Difference of Arrival Estimation from Frequency-Sliding Generalized Cross-Correlations Using Convolutional Neural Networks

The interest in deep learning methods for solving traditional signal processing tasks has been steadily growing in the last years. Time delay estimation (TDE) in adverse scenarios is a challenging problem, where classical approaches based on generalized cross-correlations (GCCs) have been widely used for decades. Recently, the frequency-sliding GCC (FS-GCC) was proposed as a novel technique for TDE based on a sub-band analysis of the cross-power spectrum phase, providing a structured two-dimensional representation of the time delay information contained across different frequency bands. Inspired by deep-learning-based image denoising solutions, we propose in this paper the use of convolutional neural networks (CNNs) to learn the time-delay patterns contained in FS-GCCs extracted in adverse acoustic conditions. Our experiments confirm that the proposed approach provides excellent TDE performance while being able to generalize to different room and sensor setups.

eess.AS↗

arXiv2019

Frequency-Sliding Generalized Cross-Correlation: A Sub-band Time Delay Estimation Approach

The generalized cross correlation (GCC) is regarded as the most popular approach for estimating the time difference of arrival (TDOA) between the signals received at two sensors. Time delay estimates are obtained by maximizing the GCC output, where the direct-path delay is usually observed as a prominent peak. Moreover, GCCs play also an important role in steered response power (SRP) localization algorithms, where the SRP functional can be written as an accumulation of the GCCs computed from multiple sensor pairs. Unfortunately, the accuracy of TDOA estimates is affected by multiple factors, including noise, reverberation and signal bandwidth. In this paper, a sub-band approach for time delay estimation aimed at improving the performance of the conventional GCC is presented. The proposed method is based on the extraction of multiple GCCs corresponding to different frequency bands of the cross-power spectrum phase in a sliding-window fashion. The major contributions of this paper include: 1) a sub-band GCC representation of the cross-power spectrum phase that, despite having a reduced temporal resolution, provides a more suitable representation for estimating the true TDOA; 2) such matrix representation is shown to be rank one in the ideal noiseless case, a property that is exploited in more adverse scenarios to obtain a more robust and accurate GCC; 3) we propose a set of low-rank approximation alternatives for processing the sub-band GCC matrix, leading to better TDOA estimates and source localization performance. An extensive set of experiments is presented to demonstrate the validity of the proposed approach.

eess.AS↗

arXiv2019

On the performance of residual block design alternatives in convolutional neural networks for end-to-end audio classification

Residual learning is a recently proposed learning framework to facilitate the training of very deep neural networks. Residual blocks or units are made of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or residual connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers that make up a residual block. While ResNet architectures for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, few works have adopted ResNet architectures so far for 1D audio classification tasks. Thus, the suitability of different residual block designs for raw audio classification is partly unknown. The purpose of this paper is to analyze and discuss the performance of several residual block implementations within a state-of-the-art CNN-based architecture for end-to-end audio classification using raw audio waveforms. For comparison purposes, we analyze as well the performance of the residual blocks under a similar 2D architecture using a conventional time-frequency audio represen-tation as input. The results show that the achieved accuracy is considerably dependent, not only on the specific residual block implementation, but also on the selected input normalization.

cs.SD↗

arXiv2019

CNN depth analysis with different channel inputs for Acoustic Scene Classification

Acoustic scene classification (ASC) has been approached in the last years using deep learning techniques such as convolutional neural networks or recurrent neural networks. Many state-of-the-art solutions are based on image classification frameworks and, as such, a 2D representation of the audio signal is considered for training these networks. Finding the most suitable audio representation is still a research area of interest. In this paper, different log-Mel representations and combinations are analyzed. Experiments show that the best results are obtained using the harmonic and percussive components plus the difference between left and right stereo channels, (L-R). On the other hand, it is a common strategy to ensemble different models in order to increase the final accuracy. Even though averaging different model predictions is a common choice, an exhaustive analysis of different ensemble techniques has not been presented in ASC problems. In this paper, geometric and arithmetic mean plus the Ordered Weighted Averaging (OWA) operator are studied as aggregation operators for the output of the different models of the ensemble. Finally, the work carried out in this paper is highly oriented towards real-time implementations. In this context, as the number of applications for audio classification on edge devices is increasing exponentially, we also analyze different network depths and efficient solutions for aggregating ensemble predictions.

cs.SD↗