Audio Signal Classification Research Articles

HardRain: An R package for quick, automated rainfall detection in ecoacoustic datasets using a threshold-based approach

The increasing demand for cost-efficient biodiversity data at large spatiotemporal scales has led to an increase in the collection of large ecoacoustic datasets. Whilst the ease of collection and storage of audio data has rapidly increased and costs fallen, methods for robust analysis of the data have not developed so quickly. Identification and classification of audio signals to species level is extremely desirable, but reliability can be highly affected by non-target noise, especially rainfall. Despite this demand, there are few easily applicable pre-processing methods available for rainfall detection for conservation practitioners and ecologists. Here, we use threshold values of two simple measures, Power Spectrum Density (amplitude) and Signal-to-Noise Ratio at two frequency bands, to differentiate between the presence and absence of heavy rainfall. We assess the effect of using different threshold values on Accuracy and Specificity. We apply the method to four datasets from both tropical and temperate regions, and find that it has up to 99% accuracy on tropical datasets (e.g. from the Brazilian Amazon), but performs less well in temperate environments. This is likely due to the intensity of rainfall in tropical forests and its falling on dense, broadleaf vegetation amplifying the sound. We show that by choosing between different threshold values, informed trade-offs can be made between Accuracy and Specificity, thus allowing the exclusion of large amounts of audio data containing rainfall in all locations without the loss of data not containing rain. We assess the impact of using different sample sizes of audio data to set threshold values, and find that 200 15 s audio files represents an optimal trade-off between effort, accuracy and specificity in most scenarios. This methodology and accompanying R package ‘hardRain’ is the first automated rainfall detection tool for pre-processing large acoustic datasets without the need for any additional rain gauge data.

Feature selection based on MBFOA for audio signal classification under consideration of Gaussian white noise

Audio classification is a difficult task because of the issue of extracting and choosing the optimum audio features. To reduce the computational complication from existing methods, this study proposes a feature-selection method based on modified bacterial foraging optimisation algorithm (MBFOA) for classification of audio signals. Enhanced mel-frequency cepstral coefficient and enhanced power normalised cepstral coefficients with peak and pitch are estimated the signal feature and optimised using MBFOA with the fitness function. Using the probabilistic neural network, the audio signal is classified into music and speech signal. Then, if the signal is music, the signal is classified as cello, clarinet, flute etc. If the signal is detected as a speech, then it is again classified as male or female voice. This approach shows that it is possible to boost the classification accuracy by using different features and optimisation technique.

Dictionary learning based on M‐PCA‐N for audio signal sparse representation

The current popular dictionary learning algorithms for sparse representation of signals are K-means Singular Value Decomposition (K-SVD) and K-SVD-extended. Only rank-1 approximation is used to update one atom at a time and it is unable to cope with large dictionary efficiently. In order to tackle these two problems, this study proposes M-Principal Component Analysis-N (M-PCA-N), which is an algorithm for dictionary learning and sparse representation. First, M-Principal Component Analysis (M-PCA) utilised information from the top M ranks of SVD decomposition to update M atoms at a time. Then, in order to further utilise the information from remaining ranks, M-PCA-N is proposed on the basis of M-PCA, by transforming information from the following N non-principal ranks onto the top M principal ranks. The mathematic formula indicates that M-PCA may be seen as a generalisation of K-SVD. Experimental results on the BBC Sound Effects Library show that M-PCA-N not only lowers the MSE between original signal and approximation signal in audio signal sparse representation, but also obtains higher audio signal classification precision than K-SVD.

Modified DCTNet for audio signals classification

In this paper, we investigate DCTNet for audio signal classification. Its output feature is related to Cohen's class of time-frequency distributions. We introduce the use of adaptive DCTNet (A-DCTNet) for audio signals feature extraction. The A-DCTNet applies the idea of constant-Q transform, with its center frequencies of filterbanks geometrically spaced. The A-DCTNet is adaptive to different acoustic scales, and it can better capture low frequency acoustic information that is sensitive to human audio perception than features such as Mel-frequency spectral coefficients (MFSC). We use features extracted by the A-DCTNet as input for classifiers. Experimental results show that the A-DCTNet and Recurrent Neural Networks (RNN) achieve state-of-the-art performance in bird song classification rate, and improve artist identification accuracy in music data. They demonstrate A-DCTNet's applicability to signal processing problems.

Soundscape Audio Signal Classification and Segmentation Using Listeners Perception of Background and Foreground Sound

Soundscape Audio Signal Classification and Segmentation Using Listeners Perception of Background and Foreground Sound

CALCULATION OF PITCH FOR THE IRANIAN TRADITIONAL MUSIC GENRE CLASSIFICATION STUDIED ON TWO STRINGED INSTRUMENTS THE TAR AND THE SETAR

Audio signal classification system analyzes the input audio signal and creates a label that describes the signal at the output. These are used to characterize both music and speech signals. The categorization can be done on the basis of pitch, music content, music tempo and rhythm. A musical sound is said to have four perceptual attributes: pitch, loudness, duration and timbre. These four attributes make it possible for a listener to distinguish musical sounds from each other. Pitch is a perceptual and subjective attribute of sound and plays an important role in the human understanding of sound. Although the pitch estimation of monophonic sound is well resolved, the polyphonic pitch estimation has been proved to be a very difficult task. Here, the main purpose is to calculate pitch for classification of The Radif of Mirzâ Abdollâh which has been played by two famous stringed instruments the Tar and the Setar

An Efficient Approach for Segmentation, Feature Extraction and Classification of Audio Signals

Due to the presence of non-stationarities and discontinuities in the audio signal, segmentation and classification of audio signal is a really challenging task. Automatic music classification and annotation is still considered as a challenging task due to the difficulty of extracting and selecting the optimal audio features. Hence, this paper proposes an efficient approach for segmentation, feature extraction and classification of audio signals. Enhanced Mel Frequency Cepstral Coefficient (EMFCC)-Enhanced Power Normalized Cepstral Coefficients (EPNCC) based feature extraction is applied for the extraction of features from the audio signal. Then, multi-level classification is done to classify the audio signal as a musical or non-musical signal. The proposed approach achieves better performance in terms of precision, Normalized Mutual Information (NMI), F-score and entropy. The PNN classifier shows high False Rejection Rate (FRR), False Acceptance Rate (FAR), Genuine Acceptance rate (GAR), sensitivity, specificity and accuracy with respect to the number of classes.

PyAudioAnalysis: An Open-Source Python Library for Audio Signal Analysis.

Audio information plays a rather important role in the increasing digital content that is available today, resulting in a need for methodologies that automatically analyze such content: audio event recognition for home automations and surveillance systems, speech recognition, music information retrieval, multimodal analysis (e.g. audio-visual analysis of online videos for content-based recommendation), etc. This paper presents pyAudioAnalysis, an open-source Python library that provides a wide range of audio analysis procedures including: feature extraction, classification of audio signals, supervised and unsupervised segmentation and content visualization. pyAudioAnalysis is licensed under the Apache License and is available at GitHub (https://github.com/tyiannak/pyAudioAnalysis/). Here we present the theoretical background behind the wide range of the implemented methodologies, along with evaluation metrics for some of the methods. pyAudioAnalysis has been already used in several audio analysis research applications: smart-home functionalities through audio event detection, speech emotion recognition, depression classification based on audio-visual features, music segmentation, multimodal content-based movie recommendation and health applications (e.g. monitoring eating habits). The feedback provided from all these particular audio applications has led to practical enhancement of the library.

Study of Algorithms for Separation of SingingVoice from Music

Audio signal is an acoustic signal which has frequency range roughly in 20 to 20,000 Hz. Human auditory system has a wonderful ability of effectively focusing on sound in the surrounding. Most audio signals are from the mixing of several sound sources. Separation of singing voice from music has wide range of application such as lyrics recognition, alignment, singer identification, and music information retrieval. Music accompaniment that is often non-stationary & harmonic. Basically, audio signal is time frequency segments of singing voice. An audio signal classification system should be able to categorize different audio format like speech, background noise, and musical genres, singer identification, karaoke etc. In this paper, discuss about separation technique and classifier which are used for singing voice separation from music. Non-negative matrix factorization (NMF) is used for separation from music, Gaussian mixture model (GMM) & Support vector machine (SVM) classifier for the classification.

Comparative Study of Filter Performance for Separation of Singing Voice from Music Accompaniment

An audio signal is a representation of sound. Audio signals have frequency range 20 to 20 kHz. Audio signals may be synthesized directly. A mixture refers to the physical combination of two or more substances on which the identities and are mixed in the form to separate out. An audio signal classification system should be able to categorize different audio input formats (speech, background noise, and music). Audio signal classification system analyzes the input audio signal and describes the signal at the output. These are used to characterize both music and speech signals. The categorization can be done on the basis of pitch, music content, music tempo and rhythm. From the comparative results it is observed that the wiener filter is better for noise reduction than others. We refer SEGSNR parameter for study because of its improved filter performance. Separating singing voice from music is very useful in many applications.

Soft Margin Based Low-Rank Audio Signal Classification

We propose an algorithm to do audio signal classification based on low-rank matrix representative audio data. Conventionally, the low-rank matrix data can be represented by a vector in high dimensional space. Some learning algorithms are then applied in such a vector space for matrix data classification. Particularly, maximum margin classifiers, such as support vector machine (SVM) etc. have received much attention due to their effectiveness. In this paper, we classify the data directly in the matrix space. Our methodology is built on recent studies about matrix classification with the trace norm constrained weight matrix and SVM's large-margin linear discrimination principle. The resulting low-rank SVM is then designed to maximize the margin between classes whilst minimizing the complexity of the classifier in both original and low-rank space. We compared our proposed algorithm with SVM and other state-of-the-art matrix signal classification methods. Experimental studies on real life audio signal classification show the effectiveness of our algorithm.

Classification of reverberant audio signals using clustered ad hoc distributed microphones

In a real world scenario, the automatic classification of audio signals constitutes a difficult problem. Often, reverberation and interfering sounds reduce the quality of a target source signal. This results in a mismatch between test and training data when a classifier is trained on clean and anechoic data. To classify disturbed signals more accurately we make use of the spatial distribution of microphones from ad hoc microphone arrays. In the proposed algorithm clusters of microphones that either are dominated by one of the sources in an acoustic scenario or contain mainly signal mixtures and reverberation are estimated in the audio feature domain. Information is shared within and in between these clusters to create one feature vector for each cluster to classify the source dominating this cluster. We evaluate the algorithm using simultaneously active sound sources and different ad hoc microphone arrays in simulated reverberant scenarios and multichannel recordings of an ad hoc microphone setup in a real environment. The cluster based classification accuracy is higher than the accuracy based on single microphone signals and allows for a robust classification of simultaneously active sources in reverberant environments.

Classification of audio events using permutation transformation

Automatic detection and classification of short and nonstationary events in noisy signals is widely considered to be a difficult task for traditional frequency domain and even time–frequency domain approaches. A novel method for audio signal classification is introduced. It is based on statistical properties of the temporal fine structure of audio events. Artificially generated random signals and unvoiced stop consonants of speech are used to evaluate the method. The results show improved recognition accuracy in comparison to traditional approaches.

Automatic Music Genre Classification of Audio Signals with Machine Learning Approaches

AbstractMusical genre classification is put into context by explaining about the structures in music and how it is analyzed and perceived by humans. The increase of the music databases on the personal collection and the Internet has brought a great demand for music information retrieval, and especially automatic musical genre classification. In this research we focused on combining information from the audio signal than different sources. This paper presents a comprehensive machine learning approach to the problem of automatic musical genre classification using the audio signal. The proposed approach uses two feature vectors, Support vector machine classifier with polynomial kernel function and machine learning algorithms. More specifically, two feature sets for representing frequency domain, temporal domain, cepstral domain and modulation frequency domain audio features are proposed. Using our proposed features SVM act as strong base learner in AdaBoost, so its performance of the SVM classifier cannot improve using boosting method. The final genre classification is obtained from the set of individual results according to a weighting combination late fusion method and it outperformed the trained fusion method. Music genre classification accuracy of 78% and 81% is reported on the GTZAN dataset over the ten musical genres and the ISMIR2004 genre dataset over the six musical genres, respectively. We observed higher classification accuracies with the ensembles, than with the individual classifiers and improvements of the performances on the GTZAN and ISMIR2004 genre datasets are three percent on average. This ensemble approach show that it is possible to improve the classification accuracy by using different types of domain based audio features.

Automatic Music Genre Classification of Audio Signals with Machine Learning Approaches

Automatic Music Genre Classification of Audio Signals with Machine Learning Approaches

An analysis of content-based classification of audio signals using a fuzzy c-means algorithm

Content-based audio signal classification into broad categories such as speech, music, or speech with noise is the first step before any further processing such as speech recognition, content-based indexing, or surveillance systems. In this paper, we propose an efficient content-based audio classification approach to classify audio signals into broad genres using a fuzzy c-means (FCM) algorithm. We analyze different characteristic features of audio signals in time, frequency, and coefficient domains and select the optimal feature vector by employing a noble analytical scoring method to each feature. We utilize an FCM-based classification scheme and apply it on the extracted normalized optimal feature vector to achieve an efficient classification result. Experimental results demonstrate that the proposed approach outperforms the existing state-of-the-art audio classification systems by more than 11% in classification performance.

Time–Frequency Matrix Feature Extraction and Classification of Environmental Audio Signals

Audio feature extraction and classification are important tools for audio signal analysis in many applications, such as multimedia indexing and retrieval, and auditory scene analysis. However, due to the nonstationarities and discontinuities exist in these signals, their quantification and classification remains a formidable challenge. In this paper, we develop a new approach for audio feature extraction to effectively quantify these nonstationarities in an attempt to achieve high classification accuracy for environmental audio signals. Our approach consists of three stages: first we propose to construct the time-frequency matrix (TFM) of audio signals using matching-pursuit time-frequency distribution (MP-TFD) technique, and then apply the non-negative matrix decomposition (NMF) technique to decompose the TFM into its significant components. Finally, we propose seven novel features from the spectral and temporal structures of the decomposed vectors in a way that they successfully represent joint TF structure of the audio signal, and combine them with the Mel-frequency cepstral coefficients (MFCCs) features. These features are examined using a database of 192 environmental audio signals which includes 20 aircraft, 17 helicopter, 20 drum, 15 flute, 20 piano, 20 animal, 20 bird, and 20 insect sounds, and the speech of 20 males and 20 females. The results of the numerical simulation support the effectiveness of the proposed approach for environmental audio classification with over 10% accuracy-rate improvement compared to the MFCC features.

Generalizability and Simplicity as Criteria in Feature Selection: Application to Mood Classification in Music

Classification of musical audio signals according to expressed mood or emotion has evident applications to content-based music retrieval in large databases. Wrapper selection is a dimension reduction method that has been proposed for improving classification performance. However, the technique is prone to lead to overfitting of the training data, which decreases the generalizability of the obtained results. We claim that previous attempts to apply wrapper selection in the field of music information retrieval (MIR) have led to disputable conclusions about the used methods due to inadequate analysis frameworks, indicative of overfitting, and biased results. This paper presents a framework based on cross-indexing for obtaining realistic performance estimate of wrapper selection by taking into account the simplicity and generalizability of the classification models. The framework is applied on sets of film soundtrack excerpts that are consensually associated with particular basic emotions, comparing Naive Bayes, k-NN, and SVM classifiers using both forward selection (FS) and backward elimination (BE). K-NN with BE yields the most promising results—56.5% accuracy with only four features. The most useful feature subset for k-NN contains mode majorness and key clarity, combined with dynamical, rhythmical, and structural features.

Spectral and Temporal Periodicity Representations of Rhythm for the Automatic Classification of Music Audio Signal

In this paper, we study the spectral and temporal periodicity representations that can be used to describe the characteristics of the rhythm of a music audio signal. A continuous-valued energy-function representing the onset positions over time is first extracted from the audio signal. From this function we compute at each time a vector which represents the characteristics of the local rhythm. Four feature sets are studied for this vector. They are derived from the amplitude of the discrete Fourier transform (DFT), the auto-correlation function (ACF), the product of the DFT and the ACF interpolated on a hybrid lag/frequency axis and the concatenated DFT and ACF coefficients. Then the vectors are sampled at some specific frequencies, which represent various ratios of the local tempo. The ability of these periodicity representations to describe the rhythm characteristics of an audio item is evaluated through a classification task. In this, we test the use of the periodicity representations alone, combined with tempo information and combined with a proposed set of rhythm features. The evaluation is performed using annotated and estimated tempo. We show that using such simple periodicity representations allows achieving high recognition rates at least comparable to previously published results.

Classification of audio signals using AANN and GMM

Today, digital audio applications are part of our everyday lives. Audio classification can provide powerful tools for content management. If an audio clip automatically can be classified it can be stored in an organised database, which can improve the management of audio dramatically. In this paper, we propose effective algorithms to automatically classify audio clips into one of six classes: music, news, sports, advertisement, cartoon and movie. For these categories a number of acoustic features that include linear predictive coefficients, linear predictive cepstral coefficients and mel-frequency cepstral coefficients are extracted to characterize the audio content. The autoassociative neural network model (AANN) is used to capture the distribution of the acoustic feature vectors. The AANN model captures the distribution of the acoustic features of a class, and the backpropagation learning algorithm is used to adjust the weights of the network to minimize the mean square error for each feature vector. The proposed method also compares the performance of AANN with a Gaussian mixture model (GMM) wherein the feature vectors from each class were used to train the GMM models for those classes. During testing, the likelihood of a test sample belonging to each model is computed and the sample is assigned to the class whose model produces the highest likelihood.