Several features have been proposed for automatic speaker recognition. Despite their noise sensitivity, lowlevel spectral features are the most popular ones because of their easy computation. Although in principle different spectral representations carry similar information (spectral shape), in practice the different features differ in their performance. For instance, LPC-cepstrum picks more “d...

This paper presents a study on the importance of shortterm spectral and excitation parameterizations for emotional hidden Markov model (HMM)-based speech synthesis. The analysis is performed through an emotion classification task by using two methods: K-means emotion clustering and Gaussian Mixture Models (GMMs)based emotion identification. Two known forms of parameterization for the short-term...

Selecting good feature is especially important to achieve high speech recognition accuracy. Although the mel-cepstrum is a popular and effective feature for speech recognition, it is still unclear that the filter-bank in the mel-cepstrum is always optimal regardless of speech recognition environments or the characteristics of specific speech data. In this paper, we focus on the data-driven filt...

In this paper, the correlation between cepstrum coefficients and fundamental frequencies (F0) is quantitatively analyzed. One of our previous studies pointed out that cepstrum coefficients of vowel sounds are varied because of F0 changes and that the variation can be modeled by the multivariate regression analysis. After this previous study, the current work is focused upon the analysis of the ...

A method for updating modal models from response measurements is extended from the case of a single impulsive excitation to a more general broadband excitation in the presence of secondary excitations. The original technique was based on analysis of the cepstrum of the response, as forcing function and transfer function effects are additive in the response cepstrum, and also separated if the fo...

The paper begins by discussing the difficulties in obtaining repeatable results in speech recognition. Theoretical arguments are presented for and against copying human auditory properties in automatic speech recognition. The “standard” acoustic analysis for automatic speech recognition, consisting of melscale cepstrum coefficients and their temporal derivatives, is described. Some variations a...

Line spectral frequencies (LSF) are widely used in the field of speech coding. Due to its properties, the LSF are qualified for the quantisation and the efficient compression of speech signals. In this paper we introduce the line cepstral quefrencies (LCQ). They are derived from the cepstrum in the same manner as the LSF are derived from linear predictive coding (LPC) features. We show that the...

A new cepstrum-based technique is developed in order to provide an alternative means of estimating the harmonics-tonoise ratio in voice signals. The geometric mean harmonics-tonoise ratio (GHNR) is defined as the mean of the individual spectral (i.e. at specific frequency locations) harmonics-tonoise ratios in dB. A heuristic development of the method treats the harmonic spectrum (in dB) of voi...

This paper describes recent improvements to SPLICE, Stereo-based Piecewise Linear Compensation for Environments, which produces an estimate of cepstrum of undistorted speech given the observed cepstrum of distorted speech. For distributed speech recognition applications, SPLICE can be placed at the server, thus limiting the processing that would take place at the client. We evaluated this algor...

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...