A comparison of speaker identification results using features based on cepstrum and Fourier-Bessel expansion

Gopalan, K.; Anderson, Timothy R.; Cupples, Edward J.

doi:10.1109/89.759036

Cited by 45 publications

(29 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, unlike the sinusoidal basis functions in the Fourier series, the Bessel functions decay over time. This feature of the Bessel functions make the FB series expansion suitable for nonstationary signals [15,[17][18][19][20][21][22][23].…”

Section: Fourier-bessel Series Expansionmentioning

confidence: 99%

Time-frequency analysis using time-order representation and Wigner distribution

Pachori

Sircar

2008

TENCON 2008 - 2008 IEEE Region 10 Conference

View full text Add to dashboard Cite

Abstract-A new method for time-frequency analysis of a signal, which combines the time-order representation and the Wigner-Ville distribution (WVD) has been presented in this paper. The time-order representation based on short-term FourierBessel (FB) expansion, decomposes a multicomponent signal into a number of monocomponent signals, and then the WVD technique is applied on each component of the composite signal to analyze its time-frequency distribution (TFD). Simulation results with real bat signal are included to illustrate the effectiveness of the proposed method.

show abstract

Section: Fourier-bessel Series Expansionmentioning

confidence: 99%

Time-frequency analysis using time-order representation and Wigner distribution

Pachori

Sircar

2008

TENCON 2008 - 2008 IEEE Region 10 Conference

View full text Add to dashboard Cite

show abstract

“…In the literature, some models have been proposed for representing speech features [1,[3][4][5][6][17][18][19]. In this paper, four well-known models, Linear Predict Coding Cepstrum (LPCC) [1], Fourier Transform Cepstral Coefficients Test Utterance (Sec)…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

“…In addition to the above three most commonly used feature extractions, there are other special speech features extracted often for speaker identification. Gopalan et al [5] propose a compact representation for speech using Bessel functions because of the similarity between voiced speech and Bessel functions. It has been shown that the features obtained from the Fourier-Bessel expansion of speech are comparable to the cepstral features in representing the spectral energy.…”

Section: Introductionmentioning

confidence: 99%

Robust Speaker Identification System Based on Wavelet Transform and Gaussian Mixture Model

Chen

Hsieh

Lai

2005

Natural Language Processing – IJCNLP 2004

View full text Add to dashboard Cite

This paper presents an effective and robust method for extracting features for speech processing. Based on the time-frequency multiresolution property of wavelet transform, the input speech signal is decomposed into various frequency channels. For capturing the characteristics of the vocal track and vocal codes, the traditional linear predictive cepstral coefficients (LPCC) of the approximation channel, and the entropy of the detail channel for each decomposition process are calculated. In addition, a hard thresholding technique for each lower resolution is applied to remove interference from noise. Experimental results show that using this mechanism not only effectively reduces the influence of noise, but also improves recognition. Finally, the proposed feature extraction algorithm is evaluated on the MAT telephone speech database for text-independent speaker identification using the Gaussian Mixture Model (GMM) identifier. Some popular existing methods are also evaluated for comparison in this paper. The results show that the proposed method of feature extraction is more effective and robust than other methods. In addition, the performance of our method is very satisfactory even at low SNR.

show abstract

“…Three speech analysis models that are based on short-term spectrum of speech and use concepts of the psychophysics of hearing, such as the critical-band spectral resolution, the equal-loudness curve and the intensity-loudness power law to derive an estimate of the auditory spectrum [19], have been selected to produce three versions of the proposed speech quality measure (See Section 3.1 for details). The first version of the measure (Version I) utilises a 5 th order Perceptual Linear Prediction (PLP) model [24], the second version (Version II) utilises a 17 th order Bark Spectrum (BS) analysis model [7], and the third version (Version III) utilises a 13 th order Mel-Frequency Cepstrum Coefficients (MFCC) [25]. This selection was also based on the abilities of these speech analysis models in suppressing speaker-dependent information, as investigated in Section 3.2.…”

Section: The Proposed Output-based Speech Quality Measurementioning

confidence: 99%

“…The mel-frequency cepstrum analysis model [25] is a perceptual-based speech analysis motivated by the observation that the human auditory system perceives information based on the energy in a band of frequencies rather than that at a single frequency, and by the fact that most signals can be described in terms of source-filter model. The model is widely accepted as a standard in the speech technology field for a number of challenging tasks, including speech recognition and speaker identification.…”

Section: Mel-frequency Cepstrum Analysismentioning

confidence: 99%

New single-ended objective measure for non-intrusive speech quality evaluation

Mahdi

Picovici

2008

SIViP

View full text Add to dashboard Cite

This article proposes a new output-based method for non-intrusive assessment of speech quality of voice communication systems and evaluates its performance. The method requires access to the processed (degraded) speech only, and is based on measuring perception-motivated objective auditory distances between the voiced parts of the output speech to appropriately matching references extracted from a pre-formulated codebook. The codebook is formed by optimally clustering a large number of parametric speech vectors extracted from a database of clean speech records. The auditory distances are then mapped into objective Mean Opinion listening quality scores. An efficient data-mining tool known as the Self-Organizing Map (SOM) achieves the required clustering and mapping/reference matching processes. In order to obtain a perception-based, speaker-independent parametric representation of the speech, three domain transformation techniques have been investigated. The first technique is based on a Perceptual Linear Prediction (PLP) model, the second utilises a Bark Spectrum (BS) analysis and the third utilises Mel-Frequency Cepstrum Coefficients (MFCC). Reported evaluation results show that the proposed method provides high correlation with subjective listening quality scores, yielding accuracy similar to that of the ITU-T P.563 while maintaining a relatively low computational complexity. Results also demonstrate that the method outperforms the PESQ in a number of distortion conditions, such as those of speech degraded by channel impairments.

show abstract

A comparison of speaker identification results using features based on cepstrum and Fourier-Bessel expansion

Cited by 45 publications

References 4 publications

Time-frequency analysis using time-order representation and Wigner distribution

Time-frequency analysis using time-order representation and Wigner distribution

Robust Speaker Identification System Based on Wavelet Transform and Gaussian Mixture Model

New single-ended objective measure for non-intrusive speech quality evaluation

Contact Info

Product

Resources

About