In this paper, we first present a new variant of Gaussian restricted Boltzmann machine (GRBM) called multivariate Gaussian restricted Boltzmann machine (MGRBM), with its definition and learning algorithm. Then we propose using a learned GRBM or MGRBM to extract better features for robust speech recognition. Our experiments on Aurora2 show that both GRBM-extracted and MGRBM-extracted feature per...

The Mel frequency cepstral coefficient (MFCC) model, which is widely used in speech detection and recognition, is introduced to extract features from hyperspectral image data. The similarities and differences between speech signals and spectral image data are compared and analyzed. The standard MFCC model is then improved to suit the characteristics of spectral image data by reintroducing the d...

Penelitian ini bertujuan untuk membandingkan akurasi pengenalan emosi melalui suara dengan menggunakan beberapa jenis classifier. Emosi dasar yang akan dikenali ada 4, yaitu senang, sedih, neutral dan marah. Metodologi penelitian dimulai memperoleh dataset dari database RAVDESS, terdiri 24 aktor jumlah sebanyak 60 per aktor. Namun, hanya 28 dipilih setiap aktor, sehingga total 672 digunakan dal...

UNLABELLED BACKGROUND Special consideration has recently been given to cepstral analysis with mel-frequency cepstral coefficients (MFCCs). The aim of this study was to assess the applicability of MFCCs in acoustic analysis for diagnosing occupational dysphonia in comparison to subjective and objective parameters of voice evaluation. MATERIALS AND METHODS The study comprised 2 groups, one of 5...

In this paper we present results that indicate that the formant frequencies between di erent speakers scale di erently at di erent frequencies. Based on our experiments on speech data, we then numerically compute a universal frequencywarping function, to make the scale-factor independent of frequency in the warped domain. The proposed warping function is found to be similar to the mel-scale, wh...

In this paper we study low-variance multi-taper spectrum estimation methods to compute the mel-frequency cepstral coefficient (MFCC) features for robust speech recognition. In speech recognition, MFCC features are usually computed from a Hamming-windowed DFT spectrum. Although windowing helps in reducing the bias of the spectrum, but variance remains high. Multitaper spectrum estimation methods...

In this paper, an algorithm for detecting and attenuating puff noises frequently generated under the mobile environment is proposed. As a baseline system, puff detection system is designed based on Gaussian Mixture Model (GMM), and 39th Mel Frequency Cepstral Coefficient (MFCC) is extracted as feature parameters. To improve the detection performance, effective acoustic features for puff detecti...

The aim of this study was to assess the applicability of Mel Frequency Cepstral Coefficients (MFCC) of voice samples in diagnosing vocal nodules and polyps. Patients’ voice samples were analysed acoustically with the measurement of MFCC and values of the first three formants. Classification of mel coefficients was performed by applying the Sammon Mapping and Support Vector Machines. For the tes...

in this paper, first, an initial feature vector for vocal fold pathology diagnosis is proposed. then, for optimizing the initial feature vector, a genetic algorithm is proposed. some experiments are carried out for evaluating and comparing the classification accuracies which are obtained by the use of the different classifiers (ensemble of decision tree, discriminant analysis and k-nearest neig...

The gammachirp filter bank was used to model human cochlea filtering. Recently, we have proposed an auditory feature based on gammachirp wavelet transform. We have found that the features extractor gives a more significant improvement in robust speaker recognition than conventional acoustic features. The Gammachirp Wavelet Transform Frequency Cepestral Coefficients GWTFCC proposed the use of th...