Audio Signal Processing Techniques Research Articles

Unveiling relevant acoustic features for bird species automatic classification

The alarming rates of biodiversity loss has draw attention of the scientific community in developing quantitative characterization methods of the state of life variety, ecosystem and habitats. One way to address such aspects involves acoustically monitoring the bird population, given its relation with the health and status of the ecosystem. Automated computational tools can be adopted to enhance the processing and interpretation of birdsongs. The performance and reliability of the system heavily depends on the input features extracted from the acoustic recordings. Numerous acoustical features for characterizing birdsongs are reported in the literature, however the determination of the most relevant ones remains elusive. Moreover, literature evidences a marked focus on classification or detection performance, providing limited details on the set of features that contribute to high performance. This study investigates the problem of discerning relevant acoustical features when dealing with the automatic classification of eight Colombian bird species. We adopt different audio signal processing techniques, namely temporal, spectral, cepstral and chroma analyses, to construct a heterogeneous set of features. Feature selection is implemented using principal components analysis, ReliefF feature ranking, and genetic algorithms. By considering nearest neighbors classifiers, support vector machines, neural networks and bayesian classifiers, 49 distinct machine learning models are tested. Selection schemes are fine-tuned looking for maximizing the classification performance. Our results demonstrate that effective machine learning classification of bird species can be achieved by refining a heterogeneous set of features through feature selection. Consistently, our work identifies Mel frequency Cepstral coefficients, spectral decrease, and spectral rolloff point as the most recurrent features across various feature selection schemes. By incorporating these features in a heterogenous subset totaling a minimum of 19 features, classification performances above 95% can be achieved using a nearest neighbor classifier with the Manhattan distance. These findings are particularly notable as they are derived from processing field-noise corrupted acoustic recordings. The outcomes of this study yield potential acoustical features suitable for the characterization of birdsongs. In addition, our methodological design may serve as a reference for extending the assessment of new features and machine learning models, thereby contributing to the development of effective and feasible conservation tools.

Development of non-destructive system for estimating avocado quality parameters

México has established itself as a significant global exporter of avocados, owing to the surging demand for this highly sought-after fruit. In response to market requirements, the assurance of specific quality parameters during the harvesting and international transportation phases has become indispensable. However, the predominant techniques employed for the assessment of these critical quality attributes are often intrusive and labor-intensive, resulting in substantial economic losses. In this research, we propose a novel approach, Smart Platform for Avocado Inspection and Analysis (SPAIA), which leverages intelligent audio analysis to nondestructively estimate key avocado quality parameters. Our methodology comprises a multi-faceted process, encompassing the design and development of a specialized capture device, meticulous data collection, and the formulation of robust audio-based estimation and evaluation models. As a result, our research proposes new aFI, aFIsum indices from Audio Signal Processing (ASP) techniques, and a new spectrogram, a product of image processing techniques and Intelligent Audio Analysis (IAA). Finally, the non-destructive approach yielded remarkable results in the estimation of the avocado quality parameters Seed Weight (SW), Dry Matter Index (DMI), Ripeness State (RS) and Uniform Ripeness (UR). The best regression models achieved a Pearson’s correlation index of 0.988, while the classification models exhibited an accuracy of 0.960. These findings not only demonstrate the viability of SPAIA as an innovative tool but also highlight its potential to revolutionize the avocado industry by offering a more efficient and sustainable means of ensuring fruit quality throughout the entire production and distribution process.

Real-time swarming detection in honeybees: Leveraging audio signal processing and machine learning techniques

Acoustical signals play a significant role in honey bee communication across various behavioral contexts. One notable example is queen piping, which refers to the acoustic signals emitted by young queens during the swarming process. Specifically, emerged virgin queens emit a distinct acoustic signal known as “tooting.” Tooting signals typically consist of one or two pulses lasting approximately one second, characterized by an initial rise in both amplitude and frequency. Recognizing these signals is of utmost importance for beekeepers as it enables them to identify an imminent swarm, effectively manage the swarming process, and safeguard the colony. This paper proposes a novel method for online swarming detection in honey bees, leveraging audio signal collection, acoustical signal processing, and machine learning techniques. The experimental results demonstrate the effectiveness of the proposed system in accurately detecting swarming at its early stages. Notably, the system maintains a high level of accuracy even when confronted with environmental noise and other unfamiliar audio signals that could potentially corrupt the audio signal acquired from the beehive.

Classification of Normal and Abnormal Heart Sounds Using Empirical Mode Decomposition and First Order Statistic

Analysis of heart sound signals for automatic segmentation and classification has revealed in recent decades that it has the potential to detect pathology accurately in clinical applications. Various audio signal processing techniques have been used to reduce the subjectivity of heart sound analysis. This study aims to classify normal and abnormal heart sound signals. The feature extraction process was optimized by EMD and calculated using five first-order statistical parameters: mean, variance, kurtosis, skewness, and entropy. The classification system is optimized with a mutual information algorithm to select traits that can significantly improve system performance. In addition, the selection of the optimal system configuration also includes the k-fold cross-validation and kNN methods with k values ​​and the proper distance type. Based on the test results, the highest accuracy of 98.2% was obtained when the value of k = 1 and the type of cosine distance on kNN with a five-fold cross-validation system evaluation model.

Wave Digital Models of Piezoelectric Transducers for Audio Applications

The number of consumer electronics devices integrating piezoelectric (PE) transducers as flat-panel loudspeakers has recently experienced a steep increase. Being very thin, in fact, PE transducers well cope with the miniaturization process that characterizes the market. However, at the same time, their reduced dimensions cause the sound pressure level to be poor at low frequencies, impairing the overall acoustic response. In this article, we derive novel efficient discrete-time models of PE transducers in the wave digital (WD) domain such that they can be integrated in the future into signal processing algorithms for audio output enhancement. WD filters are, in fact, making headway among audio digital signal processing techniques based on circuit equivalent models thanks to their efficiency, robustness, and accuracy. Starting from circuital representations of the piezo constitutive equations, we derive both lumped and distributed models. In particular, we show how it is possible to implement the frequency-dependent elements characterizing Mason’s model in the WD domain, contrary to what can be done using mainstream SPICE-like simulators. Such WD implementations come in handy for the simulation and fast prototyping of PE systems, paving the way toward the design of model-based digital signal processing algorithms for enhancing the transducer acoustic performance.

An Integrated System of Artificial Intelligence and Signal Processing Techniques for the Sorting and Grading of Nuts

The existence of conversion industries to sort and grade hazelnuts with modern technology plays a vital role in export. Since most of the hazelnuts produced in Iran are exported to domestic and foreign markets without sorting and grading, it is necessary to have a well-functioning smart system to create added value, reduce waste, increase shelf life, and provide a better product delivery. In this study, a method is introduced to sort and grade hazelnuts by integrating audio signal processing and artificial neural network techniques. A system was designed and developed in which the produced sound, due to the collision of the hazelnut with a steel disk, was taken by the microphone placed under the steel disk and transferred to a PC via a sound card. Then, it was stored and processed by a program written in MATLAB software. A piezoelectric sensor and a circuit were used to eliminate additional ambient noise. The time-domain and wavelet domain features of the data were extracted using MATLAB software and were analyzed using Artificial Neural Network Toolbox. Seventy percent of the extracted data signals were used for training, 15% for validation, and the rest of the data was used to test the artificial neural network (Multilayer Perceptron network with Levenberg-Marquardt Learning algorithm). The model optimization and the number of neurons in the hidden layer were conducted based on mean square error (MSE) and prediction accuracy (PA). A total of 2400 hazelnuts were used to evaluate the system. The optimal neural network structure for sorting and grading hazelnuts was 4-21-3 (four neurons in input layers, 21 neurons in the hidden layer, and three outputs which are the desired classification). This neural network (NN) was used to classify hazelnut as big, small, hollow, or damaged. Results showed 96.1%, 89.3%, and 93.1% accuracy for big/small, hollow, or damaged hazelnuts were obtained, respectively.

Combining statistical models using modified spectral subtraction method for embedded system

Speech enhancement aims at improving the overall speech signal perceptual quality using different audio signal processing techniques. Filtering techniques, spectral restoration and model-based methods are the three fundamental classes of speech enhancement algorithms for noise reduction. With mobile devices increased usage, the demand for algorithms processing also increases. As the microphones that capture the voice of the speaker are at considerable distance in most of the devices, noise are getting added thereby degrading the quality of the speech signal. No single theorist's stone or minimization standard has been discovered so far for speech enhancement. In this work, we have combined the statistical models along with machine learning algorithm to improve the results thereby resulting in robust communication. Experimentation results on AURORA 2 database shows us improved results over the state of the art methods discussed in the literature.

Trends in audio signal feature extraction methods

Audio signal processing algorithms generally involves analysis of signal, extracting its properties, predicting its behaviour, recognizing if any pattern is present in the signal, and how a particular signal is correlated to another similar signals. Audio signal includes music, speech and environmental sounds. Over the last few decades, audio signal processing has grown significantly in terms of signal analysis and classification. And it has been proven that solutions of many existing issues can be solved by integrating the modern machine learning (ML) algorithms with the audio signal processing techniques. The performance of any ML algorithm depends on the features on which the training and testing is done. Hence feature extraction is one of the most vital part of a machine learning process. The aim of this study is to summarize the literature of the audio signal processing specially focusing on the feature extraction techniques. In this survey the temporal domain, frequency domain, cepstral domain, wavelet domain and time-frequency domain features are discussed in detail.

Music classification as a new approach for malware detection

Each year, a huge number of malicious programs are released which causes malware detection to become a critical task in computer security. Antiviruses use various methods for detecting malware, such as signature-based and heuristic-based techniques. Polymorphic and metamorphic malwares employ obfuscation techniques to bypass traditional detection methods used by antiviruses. Recently, the number of these malware has increased dramatically. Most of the previously proposed methods to detect malware are based on high-level features such as opcodes, function calls or program’s control flow graph (CFG). Due to new obfuscation techniques, extracting high-level features is tough, fallible and time-consuming; hence approaches using program’s bytes are quicker and more accurate. In this paper, a novel byte-level method for detecting malware by audio signal processing techniques is presented. In our proposed method, program’s bytes are converted to a meaningful audio signal, then Music Information Retrieval (MIR) techniques are employed to construct a machine learning music classification model from audio signals to detect new and unseen instances. Experiments evaluate the influence of different strategies converting bytes to audio signals and the effectiveness of the method.

이종 기기 간 음성통신을 위한 자동전환장치의 구현

무전기의 음성통신은 PTT(: Push To Talk)를 이용한 반이중(half-duplex) 방식으로, 송신 시 단일 통화선로를 점유한다. 전화와 무전기간, UHF와 VHF 간의 인터페이스와 같이 서로 다른 이종 장치 간 음성통신을 위해서는 두 장치간의 자동전환장치가 요구되고, 이 장치는 입력 신호로부터 전송해야 할 음성을 검출하는 음성전환장치의 성능에 따라 전송되는 음성신호의 손실여부에 많은 영향을 받는다. 기존방식은 단순 입력신호의 크기 즉, 에너지 레벨을 통해 기준을 정함으로써 잡음에도 반응하는 문제점을 지니고 있다. 본 논문에서는 음성신호처리기법을 이용하여 입력된 신호가 음성임을 판별함으로써, 이종 기기 사이의 음성을 자동으로 전달하는 장치를 구현하였다. 이를 통해 음성 자동전환장치의 성능향상을 확인하였고, 이종 기기 간 음성 손실 없는 전송을 수행할 수 있었다. A radio is a half-duplex voice communication method using the PTT(: Push To Talk), occupy a single line calls during transmission. As an interface between the telephone and the radio, UHF and VHF, for voice communication between the different heterogeneous devices, A device automatically switches between the two devices is required. Therefore, in accordance with the performance of the voice switching apparatus for detecting a voice to be transmitted from an input signal, loss of the audio signal to be transmitted is subjected to Significant influence. Conventional method has the problem responding to noise by setting the level through simple means of amplitude of input signal, in other words, the energy level of the input signal. This paper, by using the audio signal processing techniques, this discriminated what the voice is among the input signal and substantiated a device for the automatic voice transmission between heterogeneous devices. With this proposal, I was confirmed of improvement of performance in the automatic voice switching device, could perform loss-less transmission of voice between heterogeneous devices.

Stopping Criteria for Non-Negative Matrix Factorization Based Supervised and Semi-Supervised Source Separation

Numerous audio signal processing and analysis techniques using non-negative matrix factorization (NMF) have been developed in the past decade, particularly for the task of source separation. NMF-based algorithms iteratively optimize a cost function. However, the correlation between cost functions and application-dependent performance metrics is less known. Furthermore, to the best of our knowledge, no formal heuristic to compute a stopping criterion tailored to a given application exists in the literature. In this paper, we examine this problem for the case of supervised and semi-supervised NMF-based source separation and show that iterating these algorithms to convergence is not optimal for this application. We propose several heuristic stopping criteria that we empirically found to be well correlated with source separation performance. Moreover, our results suggest that simply integrating the learning of an appropriate stopping criterion in a sweep for model size selection could lead to substantial performance improvements with minimal additional effort.

Automatic annotation of tennis games: An integration of audio, vision, and learning

Fully automatic annotation of tennis game using broadcast video is a task with a great potential but with enormous challenges. In this paper we describe our approach to this task, which integrates computer vision, machine listening, and machine learning. At the low level processing, we improve upon our previously proposed state-of-the-art tennis ball tracking algorithm and employ audio signal processing techniques to detect key events and construct features for classifying the events. At high level analysis, we model event classification as a sequence labelling problem, and investigate four machine learning techniques using simulated event sequences. Finally, we evaluate our proposed approach on three real world tennis games, and discuss the interplay between audio, vision and learning. To the best of our knowledge, our system is the only one that can annotate tennis game at such a detailed level.

Signal Processing for Music Analysis

Music signal processing may appear to be the junior relation of the large and mature field of speech signal processing, not least because many techniques and representations originally developed for speech have been applied to music, often with good results. However, music signals possess specific acoustic and structural characteristics that distinguish them from spoken language or other nonmusical signals. This paper provides an overview of some signal analysis techniques that specifically address musical dimensions such as melody, harmony, rhythm, and timbre. We will examine how particular characteristics of music signals impact and determine these techniques, and we highlight a number of novel music analysis and retrieval tasks that such processing makes possible. Our goal is to demonstrate that, to be successful, music audio signal processing techniques must be informed by a deep and thorough insight into the nature of music itself.

Emotional control and visual representation using advanced audiovisual interaction

Modern interactive means combined with new digital media processing and representation technologies can provide a robust framework for enhancing user experience in multimedia entertainment systems and audiovisual artistic installations with non-traditional interaction/feedback paths based on user affective state. In this work, the ‘Elevator’ interactive audiovisual platform prototype is presented, which aims to provide a framework for signalling and expressing human behaviour related to emotions (such as anger) and finally produce a visual outcome of this behaviour, defined here as the emotional ‘thumbnail’ of the user. Optimised, real-time audio signal processing techniques are employed for monitoring the achieved anger-like behaviour, while the emotional elevation is attempted using appropriately selected combined audio/visual content reproduced using state-of-the-art audiovisual playback technologies that allow the creation of a realistic immersive audiovisual environment. The demonstration of the proposed prototype has shown that affective interaction is possible, allowing the further development of relative artistic and technological applications.

Phase-Locked Transparent Tone-in-Band (TTIB): A New Spectrum Configuration Particularly Suited to the Transmission of Data Over SSB Mobile Radio Networks

The paper describes a new pilot tone SSB configuration, transparent tone-in-band (TTIB), which may be used in mobile radio systems from low-band VHF to microwave frequencies. By utilizing audio signal processing techniques in the transmitter and receiver, the pilot reference tone may be positioned centrally within the RF channel bandwidth without losing the property of data transparency and also retains the many system advantages of tone-in-band SSB over the pilot carrier and tone-above-band schemes. Besides speech transmissions, results are presented for noncoherent FSK and DPSK data formats under white noise and Rayleigh fading conditions. Finally, a new technique utilizing TTIB is suggested to facilitate the use of coherent data systems.