Search

Background There has been growing interest towards naturalistic neuroimaging experiments, which deepen our understanding of how human brain processes and integrates incoming streams of multifaceted sensory information, as commonly occurs in real world. Music is a good example of such complex continuous phenomenon. In a few recent fMRI studies examining neural correlates of music in continuous listening settings, multiple perceptual attributes of music stimulus were represented by a set of high-level features, produced as the linear combination of the acoustic descriptors computationally extracted from the stimulus audio. New method fMRI data from naturalistic music listening experiment were employed here. Kernel principal component analysis (KPCA) was applied to acoustic descriptors extracted from the stimulus audio to generate a set of nonlinear stimulus features. Subsequently, perceptual and neural correlates of the generated high-level features were examined. Results The generated features captured musical percepts that were hidden from the linear PCA features, namely Rhythmic Complexity and Event Synchronicity. Neural correlates of the new features revealed activations associated to processing of complex rhythms, including auditory, motor, and frontal areas. Comparison with existing method Results were compared with the findings in the previously published study, which analyzed the same fMRI data but applied linear PCA for generating stimulus features. To enable comparison of the results, methodology for finding stimulus-driven functional maps was adopted from the previous study. Conclusions Exploiting nonlinear relationships among acoustic descriptors can lead to the novel high-level stimulus features, which can in turn reveal new brain structures involved in music processing. [ABSTRACT FROM AUTHOR]

Brain responses to discrete short sounds have been studied intensively using the event-related potential (ERP) method, in which the electroencephalogram (EEG) signal is divided into epochs time-locked to stimuli of interest. Here we introduce and apply a novel technique which enables one to isolate ERPs in human elicited by continuous music. The ERPs were recorded during listening to a Tango Nuevo piece, a deep techno track and an acoustic lullaby. Acoustic features related to timbre, harmony, and dynamics of the audio signal were computationally extracted from the musical pieces. Negative deflation occurring around 100 milliseconds after the stimulus onset (N100) and positive deflation occurring around 200 milliseconds after the stimulus onset (P200) ERP responses to peak changes in the acoustic features were distinguishable and were often largest for Tango Nuevo. In addition to large changes in these musical features, long phases of low values that precede a rapid increase – and that we will call Preceding Low-Feature Phases – followed by a rapid increase enhanced the amplitudes of N100 and P200 responses. These ERP responses resembled those to simpler sounds, making it possible to utilize the tradition of ERP research with naturalistic paradigms. [ABSTRACT FROM AUTHOR]

Music information retrieval (MIR) has witnessed rapid advances in various tasks like musical similarity, music genre classification (MGC), etc. MGC and audio tagging are approached using various features through traditional machine learning and deep learning (DL) based techniques by many researchers. DL-based models require a large amount of data to generalize well on new data samples. Unfortunately, the lack of sizeable open music datasets makes the analyses of the robustness of musical features on DL models even more necessary. So, this paper assesses and compares the robustness of some commonly used musical and non-musical features on DL models for the MGC task by evaluating the performance of selected models on multiple employed features extracted from various datasets accounting for billions of segmented data samples. In our evaluation, Mel-Scale based features and Swaragram showed high robustness across the datasets over various DL models for the MGC task. • Robustness of musical features analyzed for music classification using DL models. • Mel-based features and Swaragram generally perform well across various music styles. • Large frame and small sliding window length envelopes are suitable for DL models. • Small DL models suffer from underfitting, whereas large overfit on musical features. [ABSTRACT FROM AUTHOR]