Este artículo describe el conjunto de experimentos realizados para obtener el reconocimiento de 60 notas musicales de un piano digital por medio de técnicas de procesamiento digital de señales y clasificadores. Para la etapa de técnicas de procesamiento digital de señales se utilizaron: Frecuencia fundamental, coeficientes Cepstrales en la Frecuencia de Mel y Cepstrales de Mecánica Coclear. Par...

In this paper, we present a novel method to extract noise-robust speech feature representation in speech recognition. This method employs the algorithm of linear predictive coding (LPC) on the feature time series of mel-frequency cepstral coefficients (MFCC). The resulting linear predictive version of the feature time 國立暨南國際大學電機工程學系 Department of Electrical Engineering, National Chi Nan Univers...

Speaker Recognition is the task of identifying an individual from their voice. Typically this task is performed in two consecutive stages: feature extraction and classification. Using a Gaussian Mixture Model (GMM) classifier different filter-bank configurations were compared as feature extraction techniques for speaker recognition. The filter-banks were also compared to the popular Mel-Frequen...

This work proposes a novel method of predicting formant frequencies from a stream of mel-frequency cepstral coefficients (MFCC) feature vectors. Prediction is based on modelling the joint density of MFCC vectors and formant vectors using a Gaussian mixture model (GMM). Using this GMM and an input MFCC vector, two maximum a posteriori (MAP) prediction methods are developed. The first method pred...

Making no claim of being exhaustive, a review of the most popular MFCC (Mel Frequency Cepstral Coefficients) implementations is made. These differ mainly in the particular approximation of the nonlinear pitch perception of human, the filter bank design, and the compression of the filter bank output. Then, a comparative evaluation of the presented implementations is performed on the task of text...

Three different methodologies for automatic speaker identification have been evaluated in the paper, namely the well known Dynamic Time Warping (DTW), the Auto-Regressive Vector Models (ARVM) and an Algebraic Approach (AA). The aim of our study is to examine the effectiveness of these approaches in the fixed-text speaker identification task with short phrases in Bulgarian language collected ove...

An algorithm involving Mel-Frequency Cepstral Coefficients (MFCCs) is provided to perform signal feature extraction for the task of speaker accent recognition. Then different classifiers are compared based on the MFCC feature. For each signal, the mean vector of MFCC matrix is used as an input vector for pattern recognition. A sample of 330 signals, containing 165 US voice and 165 non-US voice,...

This paper proposes a simple and e cient time domain technique to estimate an all-poll model on a mel-frequency axis (Mel-LPC). This method requires only two-fold computational cost as compared to conventional linear prediction analysis. The recognition performance of mel-cepstral parameters obtained by the Mel LPC analysis is compared with those of conventional LP mel-cepstra and the melfreque...

This paper introduces a novel feature based on the raw output of the gammatone filterbank. Channel selection is used to enhance robustness over a range of signal-to-noise ratios (SNR) of additive noise. The recognition accuracy of the proposed feature is tested on a sound event database using a Hidden Markov Model (HMM) recogniser. A comparison with a series of similar features and the conventi...

Conventional speech recognition engines extract Mel Frequency Cepstral Coefficients (MFCC) features from incoming speech. This paper presents a novel approach for feature extraction in which speech is processed according to the Auditory Image Model, a model of human psychoacoustics. We fist describe the proposed frontend, then we present recognition results obtained with the TIMIT database. Com...