Birds produce complex vocalizations through coordinated motor systems, with the syrinx producing sound and the trachea, beak, and other structures modifying it. The bird’s vocal tract includes resonating cavities such as the oropharyngeal esophageal cavity (OEC), which shapes the sound produced by the syrinx. We developed computational models of a bird’s upper vocal tract based on micro-CT scans, including three models. The first is the Primary Model, while the others are Refined Models with two different OEC geometries: a cylinder (RMC) and a truncated cone (RMT). Using COMSOL Multiphysics, we analyzed both the impact of the OEC on resonance and the influence of different OEC shapes on sound production. Validation with bird’s vocalizations showed that the truncated conical OEC most accurately matched the observed resonant frequencies.

Mimicry is the art of imitating public figures, animals, and instruments. It’s a popular profession in entertainment, where skilled individuals synchronize voice and gestures, but it is also used deceptively in voice-based crimes. We conducted a paraconsistent feature analysis (PFE) on acoustic features to gain a better understanding of their role in detecting highly competent voice impersonators. To validate our observations from the feature analysis, we performed an experiment on a mimicry dataset using four classifiers. Our proposed system evaluates the competence of artists in voice mimicking and ranks them based on scores obtained from a classifier. A ’hit’ is recorded when the system identifies the artist with the highest mean opinion score as rank-1. Performance is evaluated using the top X-hit criteria on the mimicry dataset. Through our experiments, we demonstrate the potential of PFE in selecting optimal features for assessing the best voice-mimicking candidate.

Poor coordination of the speech production subsystems due to any neurological injury or a neuro-degenerative disease leads to dysarthria, a neuro-motor speech disorder. Dysarthric speech impairments can be mapped to the deficits caused in phonation, articulation, prosody, and glottal functioning. With the aim of reducing the subjectivity in clinical evaluations, many automated systems are proposed in the literature to assess the dysarthria severity level using these features. This work aims to analyse the suitability of these features in determining the severity level. A detailed investigation is done to rank these features for their efficacy in modelling the pathological aspects of dysarthric speech, using the technique of paraconsistent feature engineering. The study used two dysarthric speech databases, UA-Speech and TORGO. It puts light into the fact that both the prosody and articulation features are best useful for dysarthria severity estimation, which was supported by the classification accuracies obtained on using different machine learning classifiers.

Automatic music genre classification based on distance metric learning (DML) is proposed in this paper. Three types of timbral descriptors, namely, mel-frequency cepstral coefficient (MFCC) features, modified group delay features (MODGDF) and low-level timbral feature sets are combined at the feature level. We experimented with k nearest neighbor (kNN) and support vector machine (SVM)-based classifiers for standard and DML kernels (DMLK) using GTZAN and Folk music dataset. Standard kernel-based kNN and SVM-based classifiers report classification accuracy (in%) of 79.03 and 90.16, respectively, on GTZAN dataset and 86.60 and 92.26, respectively, for Folk music dataset, with the best performing RBF kernel. A further improvement was observed when DML kernels were used in place of standard kernels in the kernel kNN and SVM-based classifiers with an accuracy of 84.46%, 92.74% (GTZAN), 90.00 and 96.23 (Folk music dataset) for DMLK-kNN and DMLK-SVM, respectively. The results demonstrate the potential of DML kernels in music genre classification task.

In this paper, we propose a modified group delay based method for melodic pitch extraction from heterophonic music. The power spectrum of the music signal is first flattened in order that the system characteristics are annihilated, while the characteristics of the source are emphasized. The modified group delay function of this signal produces peaks at multiples of the pitch period. The first 3 peaks are used to determine the actual pitch period. The performance of the proposed system was evaluated on two datasets ADC-2004, and LabROSA. The performance is comparable to that of other magnitude spectrum based approaches. The algorithms are also applied to heterophonic music, namely Carnatic Music. As ground truth is not available for Carnatic Music, the pitch contours were used to synthesize the music, which was evaluated for correctness by a professional musician.