Speaker verification: a tutorial
IEEE Communications MagazinePublished 1 January 1990
Jayant M. Naik
Citations122
SJR quartileQ1
SJR score3.28
SNIP2.80
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The task of speaker verification, a subset of the general problem of speaker recognition, is defined and the feature selection and pattern matching steps of the recognition procedure are examined.
Abstract
The task of speaker verification, a subset of the general problem of speaker recognition is defined. The feature selection and pattern matching steps of the recognition procedure are examined. Speaker verification system design and performance are discussed, and databases for evaluating them are briefly considered. An example of a speaker verification system is described. An overview of industry research in this area is given.>
Keywords
Computer Science
Proceedings of the IEEEA tutorial on hidden Markov models and selected applications in speech recognition
22,785 Citations1989L. R. Rabiner
IEEE Transactions on Acoustics Speech and Signal ProcessingDynamic programming algorithm optimization for spoken word recognition
6,544 Citations1978Hiroaki Sakoe, Seibi Chiba
This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition, in which the warping function slope is restricted so as to improve discrimination between words in different categories.
IEEE Transactions on Acoustics Speech and Signal ProcessingMinimum prediction residual principle applied to speech recognition
1,613 Citations1975Fumitada Itakura
A computer system is described in which isolated words, spoken by a designated talker, are recognized through calculation of a minimum prediction residual through optimally registering the reference LPC onto the input autocorrelation coefficients using the dynamic programming algorithm.
IEEE Transactions on Acoustics Speech and Signal ProcessingCepstral analysis technique for automatic speaker verification
1,170 Citations1981Sadaoki Furui
New techniques for automatic speaker verification using telephone speech based on a set of functions of time obtained from acoustic analysis of a fixed, sentence-long utterance using a new time warping method using a dynamic programming technique.
IEEE Transactions on Acoustics Speech and Signal ProcessingDistance measures for speech processing
638 Citations1976Alfred Gray, J. Markel
The likelihood ratio, cepstral measure, and cosh measure are easily evaluated recursively from linear prediction filter coefficients, and each has a meaningful and interrelated frequency domain interpretation.
Proceedings of the IEEEAutomatic recognition of speakers from their voices
374 Citations1976Bishnu S. Atal
The paper indudes a discussion of the speaker-dependent properties of the speech signal, methods for selecting an efficient set of speech measurements, results of experimental studies illustrating the performance of various methods of speaker recognition, and a comparision of theperformance of automatic methods with that of human listeners.
Proceedings of the IEEESpeaker recognition—Identifying people by their voices
345 Citations1985George R. Doddington
A discussion of inherent performance limitations, along with a review of the performance achieved by listening, visual examination of spectrograms, and automatic computer techniques, attempts to provide a perspective with which to evaluate the potential of speaker recognition and productive directions for research into and application of speaker Recognition technology.
The Journal of the Acoustical Society of AmericaAutomatic Speaker Recognition Based on Pitch Contours
290 Citations1972Bishnu S. Atal
A data‐reduction procedure based on the Karhunen‐Loeve representation was found effective in representing the pitch information in each contour in a 20‐dimensional space and the percentage of correct identifications was found to be 97%.
Proceedings of the IEEEAutomatic speaker verification: A review
219 Citations1976A. E. Rosenberg
The techniques, evaluations, and implementations of various proposed speaker recognition systems are reviewed with special emphasis on issues peculiar to speaker verification, especially the distinction between speaker verification and speaker identification.
IEEE Transactions on Acoustics Speech and Signal ProcessingAn algorithm for automatic formant extraction using linear prediction spectra
215 Citations1974Stephanie McCandless
An algorithm is presented which finds the frequency and amplitude of the first three formants during all vowel-like segments of continuous speech, using as input the peaks of the linear prediction spectra and a segmentation parameter to indicate energy and voicing.
IEEE Transactions on Acoustics Speech and Signal ProcessingSelection of acoustic features for speaker identification
176 Citations1975M. R. Sambur
The aim of this study was to determine a set of acoustic features in the speech signal that are effective for the identification of a speaker and a novel probability of error criterion was used to determine the the relative merits of the features.
International Conference on Acoustics, Speech, and Signal ProcessingSpeaker verification over long distance telephone lines
80 Citations2003Jayant M. Naik, Lorin Netsch +1 more
The authors present the results of speaker-verification technology development for use over long-distance telephone lines, using template-based dynamic time warping and hidden Markov modeling for discriminant analysis techniques which improve the discrimination between true speakers and imposters.
The Journal of the Acoustical Society of AmericaPerceptual Bases of Speaker Identity
79 Citations1964William D. Voiers
IEEE Transactions on Acoustics Speech and Signal ProcessingSpeaker recognition using orthogonal linear prediction
62 Citations1976M. R. Sambur
The speaker discrimination potential of the linear prediction orthogonal parameters was formally tested in both a speaker identification and a speaker verification experiment, and an accuracy of 94 percent was achieved for high-quality speech inputs.
The Journal of the Acoustical Society of AmericaIdentification of speakers by use of nasal coarticulation
51 Citations1974Lo-Soun Su, K.-P. Li +1 more
A new approach, based on the statistical properties of the nasal spectra, has been used to quantitatively study the coarticulation of nasal consonants with the vowels following them in isolated /hə′CVd/ utterances.
IEEE Transactions on Audio and ElectroacousticsSpeaker verification by computer using speech intensity for temporal registration
41 Citations1973Robert C. Lummis
A technique for automatic speaker verification is described in which voice pitch, low-frequency intensity, and the three lowest formant frequencies, all as functions of time, are the features used to represent an individual utterance.
IEEE Transactions on Audio and ElectroacousticsA scheme for speech processing in automatic speaker verification
40 Citations1971Subrata Das, W. S. Mohn
Experiments investigating adaptive pattern recognition in automatic speaker verification are reported, indicating that the utterances used for training purposes should preferably be collected over a relatively long period of time.
A new method of text-independent speaker recognition
27 Citations2005Alan L. Higgins, R. Wohlford
A new method, based on template matching, that utilizes temporal information to advantage in text-dependent recognition as a special case and is compared with that of similar recently-developed methods.
The Journal of the Acoustical Society of AmericaA Method or Speaker Verification
22 Citations1971George R. Doddington
The speaker‐verification problem is defined and contrasted with the speaker‐identification problem, and proper time normalization is shown to be an important factor in improving verification error performance.
Speech recognition in the F-16 cockpit using principal spectral components
19 Citations2005P.K. Rajasekaran, George R. Doddington
A modification of the usual LPC speaker-dependent speech recognition algorithms yielded significantly improved recognition performance in an F-16 fighter cockpit environment with about half the number of substitutions.
A comparison of four techniques for automatic speaker recognition
19 Citations2005R. Wohlford, Edwin H. Wrench +1 more
The results of this study indicate that LPC derived parameters perform better than do those derived from cepstral and spectral data.
Variants of cepstrum based speaker identity verification
17 Citations2003George A. Velius
Analysis parameters and various distance measures are investigated for a template matching scheme for speaker identity verification (SIV) and performance varies significantly across vocabulary, and average performance is approximately 5% EER for the better algorithms on telephone speech.
Evaluation of a high performance speaker verification system for access control
15 Citations2005Jayant M. Naik, George R. Doddington
The results of an extensive evaluation of a speaker verification system for access control using a 200 speaker population and over 40,000 impostor attempts, both performed on line, over a 4-month period are presented.
High performance speaker verification using principal spectral components
13 Citations2005Jayant M. Naik, George R. Doddington
The described system finds key application in physical entry control and control of access to privileged information through verification based on a fast and user-friendly protocol based on the Principal Spectral Components, derived from the spectrum of the speech signal.
Nucl. Mater. Manage. Annu. Meet. Proc.; (United States)A performance evaluation of personnel identity verifiers
6 Citations1987Robert L. Maxwell, Lance Wright
In an attempt to maintain an awareness of the availability and the capabilities of identity verifiers for the DOE security community, Sandia Laboratories continues to comparatively evaluate the capabilities and improvements of developing devices.
A realtime implementation of a text independent speaker recognition system
5 Citations2005Edwin H. Wrench
The results of this investigation clearly show that Markel's technique is superior for applications using very short speech segments for both the speaker models and the recognition trials.
AT&T Technical JournalReport: A Voice Password System for Access Security
4 Citations1986Martha Birnbaum, L. Cohen +1 more
The voice password system (VPS) can provide secure access to telephone networks, computers, rooms, and buildings and has application in office automation systems, electronic funds transfer, and “smart cards” (interactive computers embedded in credit-card-sized packages).
Bell System Technical JournalThe Effects of Several Transmission Systems on an Automatic Speaker Verification System
4 Citations1979C. A. McGonegal, A. E. Rosenberg +1 more
The effects of the transmission system is shown on an existing automatic speaker verification system in which the measured features are pitch and gain as a function of time for a specified utterance, which verifies that pitch and Gain are robust features for use in a speaker verify system.