Language and genre detection in audio content analysis

Feature selection using singular value decomposition and QR factorization with column pivoting for text-independent speaker identification

Detection of replay spoof speech using teager energy feature cues

This paper reports some of the observations carried out on SUSE database for emotion classification. A comparative study is made to evaluate the performance of Linear Prediction Cepstral Coefficients (LPCCs) and Mel Frequency Cepstral Coefficients (MFCCs) for designing the emotion classification system for word level utterances. The significance of the orders of the coefficients has been carried out during this study. The results obtained using 12th order LPCC and 13th order MFCC are compared with respect to their reduced dimensions of lower orders. A new classification system based on the feature extraction technique using the 2nd, 3rd and 4th order coefficients of both MFCCs and LPCCs is also proposed. This paper compares the accuracy level of both MFCC and LPCC, enabling us to decide which orders of the parameters (both MFCC and LPCC) are more efficient in conveying the emotion for word level utterances. The initial experiments performed at word level utterances reveal that LPCC is more efficient in detecting emotion as compared to MFCC. Further, we noticed that the emotions conveyed in word level utterances are detected more accurately than that in sentence level utterances. The result suggests that word level approach provides better performance for emotion classification as compared to sentence level approach if the system is designed using vocal tract information only.

Drone classification using RF signal based spectral features

Speech is one of the most sophisticated human motor skills. Speaker identification is the ability of a software component or hardware to acquire a speech signal, recognize the speakers included in the signal, and identify the speaker after the audio signals have been received. This study proposes a fluctuating equation inversion method using feature extraction for broadcast hosting. Feature extraction aims to provide useful signal features from natural audio that can be applied to various downstream processes, including recitation, evaluation, and categorization. Initially, data were collected from the CASIA dataset. This study evaluated the experimental outcomes of the proposed approach using mel-frequency cepstral coefficients, gammatone frequency cepstral coefficients, and linear frequency cepstral coefficients. The proposed technique was tested on a publicly accessible dataset, and the findings showed that it performed better in terms of recognition accuracy (98%), precision (97%), recall (96.05%), sensitivity (92.56%), and F1-score (95.09%) than the conventional feature extraction methods. The proposed approach can be utilized to improve audio signal quality and user experience across broadcast-hosting applications.

The three packages libACA, pyACA, and ACA-Code provide reference implementations for basic approaches and algorithms for the analysis of musical audio signals in three different languages: C++, Python, and Matlab. All three packages cover the same algorithms, such as extraction of low level audio features, fundamental frequency estimation, as well as simple approaches to chord recognition, musical key detection, and onset detection. In addition, implementations of more generic algorithms useful in audio content analysis such as dynamic time warping and the Viterbi algorithm are provided. The three packages thus provide a practical cross-language and cross-platform reference to students and engineers implementing audio analysis algorithms and enable implementation-focused learning of algorithms for audio content analysis and music information retrieval.

Singer identification is one of the important aspects of music information retrieval (MIR). In this work, traditional feature-based and trending convolutional neural network (CNN) based approaches are considered and compared for identifying singers. Two different datasets, namely artist20 and the Indian popular singers’ database with 20 singers are used in this work to evaluate proposed approaches. Cepstral features such as Mel-frequency cepstral coefficients (MFCCs) and linear prediction cepstral coefficients (LPCCs) are considered to represent timbre information. Shifted delta cepstral (SDC) features are also computed beside the cepstral coefficients to capture temporal information. In addition, chroma features are computed from 12 semitones of a musical octave, overall forming a 46-dimensional feature vector. Experiments are conducted with different feature combinations, and suitable features are selected using the genetic algorithm-based feature selection (GAFS) approach. Two different classification techniques, namely artificial neural networks (ANNs) and random forest (RF), are considered on the features mentioned above. Further, spectrograms and chromagrams of audio clips are directly fed to CNN for classification. The singer identification results obtained using CNNs seem to be better than the traditional isolated and ensemble classifiers. Average accuracy of around 75% is observed with CNN in the case of Indian popular singers database. Whereas, on artist20 dataset, the proposed configuration of feature-based approach and CNN could not give better than 60% accuracy.

Automatic voice pathology detection enables objective assessment of pathologies that affect the voice production mechanism. Detection systems have been developed using the traditional pipeline approach (consisting of the feature extraction part and the detection part) and using the modern deep learning -based end-to-end approach. Due to the lack of vast amounts of training data in the study area of pathological voice, the former approach is still a valid choice. In the existing detection systems based on the traditional pipeline approach, the mel-frequency cepstral coefficient (MFCC) features can be regarded as the defacto standard feature set. In this study, automatic voice pathology detection is investigated by comparing the performance of various MFCC variants derived by considering two factors: the input and the filterbank in the cepstrum computation. For the first factor, three inputs (the voice signal, the glottal source and the vocal tract) are compared. The glottal source and the vocal tract are estimated using the quasi-closed phase glottal inverse filtering method. For the second factor, the mel-frequency and linear-frequency filterbanks are compared. Experiments were conducted separately using six databases consisting of voices produced by speakers suffering from one of four disorders (dysphonia, Parkinson’s disease, laryngitis, or heart failure) and by healthy speakers. Support vector machine (SVM) was used as the classifier. The results show that by combining mel- and linear-frequency cepstral coefficients derived from the glottal source and vocal tract, better overall detection accuracy was obtained compared to the defacto MFCC features derived from the voice signal. Furthermore, this combination provided comparable or better performance than four existing cepstral feature extraction techniques in clean and high signal-to-noise ratio (SNR) conditions.

The aim of the study was to inspect the acoustic properties and sleep characteristics of a preapneic snoring sound. The feasibility of forecasting upcoming respiratory events by snoring sound was also investigated. Participants with habitual snoring or a heavy breathing sound during sleep were recruited consecutively. Polysomnography was conducted, and snoring-related breathing sound was recorded simultaneously. Acoustic features and sleep features were extracted from 30-second samples, and a machine learning algorithm was used to establish 2 prediction models. A total of 74 eligible participants were included. Model 1, tested by 5-fold cross-validation, achieved an accuracy of 0.92 and an area under the curve of 0.94 for respiratory event prediction. Model 2, with acoustic features and sleep information tested by Leave-One-Out cross-validation, had an accuracy of 0.78 and an area under the curve of 0.80. Sleep position was found to be the most important among all sleep features contributing to the performance of the 2 models. Preapneic sound presented unique acoustic characteristics, and snoring-related breathing sound could be deployed as a real-time apneic event predictor. The models, combined with sleep information, serve as a promising tool for an early warning system to forecast apneic events. Wang B, Yi X, Gao J, etal. Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal. J Clin Sleep Med. 2021;17(9):1777-1784.

Chapter 3 - Acoustic identification of insects based on cepstral data fusion and hidden Markov models

Feature extraction techniques for input representation to diagnose infant diseases have received significant attention recently. Mel Frequency Cepstral Coefficients (MFCC) is one of the most popular feature extraction techniques due to its representation method being very similar to the human auditory system. The MFCC method for feature extraction depends on several important parameter settings, namely the number of filter banks, and the number of coefficients used in the final representation. These settings affects the way the features are represented, and in turn, affects the performance of the classifier for diagnosis of the disease. In this paper, the Particle Swarm Optimization (PSO) algorithm was used to optimise the parameters of the MFCC feature extraction method for classifying infants with asphyxia. The extracted MFCC features were then used to train several MLP classifiers over different initialization values. The accuracy of these classifiers was then used to guide the PSO optimization. Our results show that the optimization of MFCC computation using PSO yielded 93.9% accuracy, an improvement of 1.45% over typical MFCC parameter settings using the same classifier.

The short-term Fourier transform magnitude spectra (STFT-MS) computed from the dysarthric speech deviates nonlinearly from the normal speech in different frequency bands depending on underlying sound units. This discriminating information can be captured by segmenting the STFT-MS into different frequency bands following the power spectra of board categories of sound units. Motivated by this observation in this study, we have computed the cepstral coefficients by analyzing the STFT-MS in 0–500 Hz, 500–2000 Hz, 2000–4000 Hz, and 4000 – 8000Hz, respectively for 16 kHz sampled speech data. Each of the selected frequency bands is analyzed by using a 30 channel Mel filterbank. The log filterbank energies computed for each sub-band are then polled together and discrete cosine transform (DCT) is applied to compute the cepstral coefficients, here termed as sub-band enhanced Mel frequency cepstral coefficients (SE-MFCC). The i-vector based dysarthric intelligibility assessment system reported in this study shows that the SEMFCC outperforms the conventional Mel frequency cepstral coefficients (MFCC), and the cepstral coefficients computed using inverse-Mel filterbank (IMFCC), and linear filterbank (LFCC). The score level combination of SE-MFCC with the MFCC further improves the overall performance.

Sleep stage scoring is a critical task where conventionally large volume of data has to be analyzed visually which is troublesome, time-consuming and error prone. Eventually, machine learning technique is required for automatic sleep stage scoring. Therefore, a new feature extraction method for EEG analysis and classification is discussed based on the statistical properties of cepstral coefficients. The sleep EEG signal is segmented into 30 s epoch and each epoch is decomposed into different frequency bands: Gamma (γ), Beta (β), Alpha (α), Theta (θ) and Delta (δ) by employing the Discrete Wavelet Transform (DWT). The statistical properties of Mel Frequency Cepstral Coefficients (MFCCs), which represent the short term spectral characteristics of the wavelet coefficients, are extracted. The MFCC feature vectors are incorporated into the Gaussian Mixture Model with Expectation Maximization (GMM-EM) to classify various sleep stages: Wake, Rapid Eye Movement (REM) and Non-Rapid Eye Movement (N-REM) stage1 (S1), N-REM stage2 (S2), N-REM stage3 (S3), N-REM stage4 (S4). The proposed feature extraction for sleep stage scoring achieves 88.71% of average classification accuracy.

Acoustic vocalizations are common in marine mammals which can be used for classification purposes. Pinnipeds are a group of carnivore mammals composed by seals, sea lions, and walruses. But although, there is a great interest in research literature about acoustic monitoring of marine mammals, the identification of pinnipeds trough experts systems has been poorly studied. This paper brings a novel method for the automatic taxonomic classification of pinnipeds using a fusion of Mel and Linear Frequency Cepstral Coefficients (MFCCs and LFCCs), representing the acoustic signal in both low and high frequencies. In our experiment, we have used kNN for classification, achieving an average identification of 96.48% ± 9.17 over 18 pinniped species.

Kärntner Montanindustrie appoints Albion as UK agent for micaceous iron oxide, wollastonite & mica