Due to the increasing use of fusion in speaker recognition systems, one trend of current research activity focuses on new features that capture complementary information to the MFCC (Mel-frequency cepstral coefficients) for improving speaker recognition performance. The goal of this work is to combine (or fuse) amplitude and phase-based features to improve speaker verification performance. Base...

Acknowledgments Chapter 1: Introduction Chapter 2: The SPHINX Speech Recognition System 1 2 3 5 2.1 Signal Processing ............................ 5 2.2 Clustering and Vector Quantization ..................... 6 2.3 Hidden Markov Models .......................... 7 2.4 Speech Unit ............................... 7 Chapter 3: The Motorola Car Database and AN4 Database 8 3.1 The Motorola Car Data...

The paper describes the problem of cepstral speech analysis in the process of automated voice disorder probability estimation. The author proposes to derive two of the most diagnostically significant voice features: quality of harmonic structure and degree of subharmonic from cepstrum of speech signal. Traditionally, these attributes are estimated auricularly or by spectrum (or spectrogram) obs...

In this paper, a feature extraction method that is robust to additive background noise is proposed for automatic speech recognition. Since the background noise corrupts the autocorrelation coefficients of the speech signal mostly at the lowertime lags, while the higher-lag autocorrelation coefficients are least affected, this method discards the lower-lag autocorrelation coefficients and uses o...

A modified parallel model combination (PMC) for noisy speech recognition is proposed such that both speech cepstral mean and variance are adapted without the mapping of variance between cepstral and log-spectral domains. By investigating an adapted scalar random variable of log-energy in the way of PMC, we observe that the adapted variance of log-energy can be roughly predicted by the energy ra...

This paper presents an effective method for improving the performance of a speaker identification system. Based on the multiresolution property of the wavelet transform, the input speech signal is decomposed into various frequency bands in order not to spread noise distortions over the entire feature space. To capture the characteristics of the vocal tract, the linear predictive cepstral coeffi...

In the past few years, a great deal of research has been directed toward finding acoustic features that are effective for automatic speech recognition. Until recently, most of the speech recognizers used about 12 cepstral coefficients derived through the linear prediction analysis as recognition features [ 11. In [2,3], Furui investigated the use of temporal derivatives of cepstral coefficients...