To choose the best features in data mining issues, the Relief Feature Selection Algorithm is proposed to implement the feature selection in this paper. Firstly, the data of Ionosphere from the UCI (University of California Irvine) database is used to do a simulation experiment; secondly, the proposed method is employed to do feature selection for voice signal. In this case study, the study star...

In this paper we propose a filter bank structure derived by using admissible wavelet packet transform. These filters have Mel scale spacing and have an advantage of easy implementation with higher resolution in time-frequency domain because of wavelet transform. The features are obtained by first calculating the energy in each filter band and then applying the Discrete Cosine Transform (DCT) to...

This paper describes a robust feature extraction technique for continuous speech recognition. Central to the technique is the Minimum Variance Distortionless Response (MVDR) method of spectrum estimation. We incorporate perceptual information directly in to the spectrum estimation. This provides improved robustness and computational efficiency when compared with the previously proposed MVDR-MFC...

This paper proposes features based on parametric representation of Fourier phase of speech for speaker verification. Direct computation of Fourier phase suffers from phase wrapping and hence we attempt parametric modelling of phase spectrum using an allpass (AP) filter. The coefficients of the AP filter are estimated by minimizing an entropy based objective function motivated from speech produc...

This paper emphasizes text dependent speaker identification system on Principal Component Analysis based Genetic Algorithm which deals with detecting a particular speaker from a known population under noisy environment. At first, the system prompts the user to get speech utterance. Noises are eliminated from the speech utterances by using wiener filtering technique. To extract the features from...

Neha Chauhan Birla Institute of Technology, Mesra, Ranchi Abstract— Speaker Recognition is the computing task of validating a user’s claimed identity using speech characteristics. Main objective of speech recognition system is to communication with a device through our voice. Mel frequency Cepstral Coefficient (MFCC) features are combined with pitch and root mean square values and tested for im...

Feature extraction is a crucial part of many MIR tasks. Many manual-selected features such as MFCC have been applied to music processing but they are not effective for music genre classification. In this work, we present an algorithm based on spectrogram and convolutional neural network (CNN). Compared with MFCC, the spectrogram contains more details of music components such as pitch, flux, etc...

An experimental study of the application of scale-transform to improve the performance of speaker independent continuous speech recognition, is presented in this paper. Three major results are described. First, a comparison was made between the scale-transform based magnitude cepstrum coeÆcients (STCC) and mel-scale lter bank cepstrum coeÆcients (MFCC) on a telephone based connected digit recog...

The objective of this work is to study the speaker-specific nature of analytic phase of speech signals. Since computation of analytic phase suffers from phase wrapping problem, we have used its derivativethe instantaneous frequency for feature extraction. The cepstral coefficients extracted from smoothed subband instantaneous frequencies (IFCC) are used as features for speaker verification. The...

Speech Emotion Recognition (SER) is a hot research topic in the field of Human Computer Interaction (HCI). In this paper, we recognize three emotional states: happy, sad and neutral. The explored features include: energy, pitch, linear predictive spectrum coding (LPCC), Mel-frequency spectrum coefficients (MFCC), and Mel-energy spectrum dynamic coefficients (MEDC). A German Corpus (Berlin Datab...