A new musical instrument classification method using convolutional neural networks (CNNs) is presented in this paper. Unlike the traditional methods, we investigated a scheme for classifying musical instruments using the learned features from CNNs. To create the learned features from CNNs, we not only used a conventional spectrogram image, but also proposed multiresolution recurrence plots (MRP...

Time-frequency representations such as the spectrogram are commonly used to analyze signals having a time-varying distribution of spectral energy, but the spectrogram is constrained by an unfortunate tradeoff between resolution in time and frequency. A method of achieving high-resolution spectral representations has been independently introduced by several parties. The technique has been variou...

Spectro-temporal modulations (STMs) of the sound convey timbre and rhythm information so that they are intuitively useful for automatic music genre classification. The STMs are usually extracted from a time-frequency representation of the acoustic signal. In this paper, we investigate the efficacy of two kinds of STM features, the Gabor features and the rate-scale (RS) features, selectively ext...

The goal of this paper is to present a very simple approach to text dependent speaker identification using a combination of spectrograms and well known Discrete Cosine Transform (DCT). This approach is based on use of DCT to find similarities between spectrograms obtained from speech samples. The set of spectrograms forms the database for our experiments rather than raw speech samples. Performa...

Accurate recognition of sound patterns in spectrograms is important step for further recognition applications. However, background noise forms fundamental problem regardless the species under study. In this paper, crest factor feature was extracted from the limited dynamic range spectrogram. The developed crest factor image behaved as smoothed version of the spectrogram, at which edges of the i...

A frequency bin-wise nonlinear masking algorithm is proposed in the spectrogram domain for speech segregation in convolutive mixtures. The contributive weight from each speech source to a time-frequency unit of the mixture spectrogram is estimated by a nonlinear function based on location cues. For each sound source, a non-binary mask is formed from the estimated weights and is multiplied to th...

speech emotion recognition (ser) is a new and challenging research area with a wide range of applications in man-machine interactions. the aim of a ser system is to recognize human emotion by analyzing the acoustics of speech sound. in this study, we propose spectral pattern features (sps) and harmonic energy features (hes) for emotion recognition. these features extracted from the spectrogram ...

Speech Emotion Recognition (SER) is a new and challenging research area with a wide range of applications in man-machine interactions. The aim of a SER system is to recognize human emotion by analyzing the acoustics of speech sound. In this study, we propose Spectral Pattern features (SPs) and Harmonic Energy features (HEs) for emotion recognition. These features extracted from the spectrogram ...