Topic
Spectrogram
About: Spectrogram is a research topic. Over the lifetime, 5813 publications have been published within this topic receiving 81547 citations.
Papers published on a yearly basis
Papers
More filters
06 Mar 2017
TL;DR: In this article, sample-level deep convolutional neural networks have been proposed to learn representations from very small grains of waveforms beyond typical frame-level input representations for music auto-tagging.
Abstract: Recently, the end-to-end approach that learns hierarchical representations from raw data using deep convolutional neural networks has been successfully explored in the image, text and speech domains. This approach was applied to musical signals as well but has been not fully explored yet. To this end, we propose sample-level deep convolutional neural networks which learn representations from very small grains of waveforms (e.g. 2 or 3 samples) beyond typical frame-level input representations. Our experiments show how deep architectures with sample-level filters improve the accuracy in music auto-tagging and they provide results comparable to previous state-of-the-art performances for the Magnatagatune dataset and Million Song Dataset. In addition, we visualize filters learned in a sample-level DCNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency along layer, such as mel-frequency spectrogram that is widely used in music classification systems.
32 citations
TL;DR: Experimental results show that the tagging performance can be boosted by the proposed method compared with the state-of-the-art models, and the architecture results in faster training speed and less memory usage.
32 citations
19 Apr 1994
TL;DR: A new formulation of this method which allows a generalization of its use for any bilinear time-frequency or time-scale representation and the resulting reassigned distributions are easily computable versatile tools which highlight the signal features and preserve many theoretical properties.
Abstract: Reassigning each value of a time-frequency representation to a different location in the plane can produce a better localization of the signal components. This idea, pioneered by Kodera et al. (1976, 1978), was only applied to the sole spectrogram. We present a new formulation of this method which allows a generalization of its use for any bilinear time-frequency or time-scale representation. The resulting reassigned distributions are easily computable versatile tools which highlight the signal features and preserve many theoretical properties. >
32 citations
TL;DR: A novel, robust algorithm tailored specifically for wheeze detection from the CS-recovered short-term Fourier spectra (STFT) that features execution speed comparable to referent algorithms, and offers good prospects for parallelism.
Abstract: Quantification of wheezing by a sensor system consisting of a wearable wireless acoustic sensor and smartphone performing respiratory sound classification may contribute to the diagnosis, long-term control, and lowering treatment costs of asthma. In such battery-powered sensor system, compressive sensing (CS) was verified as a method for simultaneously cutting down power cost of signal acquisition, compression, and communication on the wearable sensor. Matching real-time CS reconstruction algorithms, such as orthogonal matching pursuit (OMP), have been demonstrated on the smartphone. However, their lossy performance limits the accuracy of wheeze detection from CS-recovered short-term Fourier spectra (STFT), when using existing respiratory sound classification algorithms. Thus, here we present a novel, robust algorithm tailored specifically for wheeze detection from the CS-recovered STFT. The proposed algorithm identifies occurrence and tracks multiple individual wheeze frequency lines using hidden Markov model. The algorithm yields 89.34% of sensitivity, 96.28% of specificity, and 94.91% of accuracy on Nyquist-rate sampled respiratory sounds STFT. It enables for less than 2% loss of classification accuracy when operating over STFT reconstructed by OMP, at the signal compression ratio of up to 4 $\times$ (classification from only 25% signal samples). It features execution speed comparable to referent algorithms, and offers good prospects for parallelism.
32 citations
TL;DR: A new method is designed that uses spectrogram images to feed them without any feature selection/extraction procedure directly into a deep convolutional neural network architecture and train it for the classification of motor impairment neural disorder in a person.
Abstract: The analysis of biomedical signals, such as the EEGs for measuring brain activity, provides means for the diagnosis of various cognitive tasks and neural disorders. These signals are frequently transformed into visual representations such as spectrograms, which can reveal characteristic patterns and serve as a basis for classification, when extracting specific features from them. We designed a new method that uses spectrogram images to feed them without any feature selection/extraction procedure directly into a deep convolutional neural network architecture and train it for the classification of motor impairment neural disorder in a person. The proposed method was tested on a set of (un)impaired subjects, where it outperformed the traditional machine learning methods. The results, obtained without any human intervention and by using all the default parameter values, turned out not to lag much behind an established state-of-the-art method, that takes advantage of using domain knowledge for the analysis of EEG recordings. Based on the experimental results we believe that the proposed method can be considered as a sound basis for further optimization towards a competitive, fully automated method for classification of EEG signals.DOI: http://dx.doi.org/10.5755/j01.eie.24.4.21469
32 citations