%0 Book
%A Anderson, T. W.
%D 1984
%T An Introduction to Multivariate Statistical Analysis
%B A Wiley Publication in Mathematical Statistics
%I Wiley
%C New York
%7 2nd
%O 1958

%0 Journal Article
%A Atal, B. S.
%D 1972
%T Automatic Speaker Recognition Based on Pitch Contours
%B Journal of the Acoustical Society of America
%V 52
%N 6
%P 1687 Ð 1697
%O December, 6.2
Ph.D. thesis, Polytech. Inst. of Brooklyn, June 1968

%0 Journal Article
%A Atal, B. S.
%D 1974
%T Effectiveness of Linear Prediction Characteristics of the Speech Wave for Automatic Speaker Identification and Verification
%B Journal of the Acoustical Society of America
%V 55
%N 6
%P 1304 Ð 1312
%F A.2 COMPREHENSIVE STUDIES
%X Compares several LPC derived feature sets and concludes that LPC Cepstrum, when used with a non-Euclidean distance metric, works best.
Found cepstrum most useful by a little. Text-dependent. Used a ÒclippingÓ procedure, ln(1+d(j,k)), on the Mahalanobis distance terms, d(j,k), where j refers to the speaker and k the frame. These clipped terms were then averaged over frames to form the robust distance measure Dj. (The Òtext-independentÓ result is not fair, since he just reorders the same text. He gets the SAME performance removing mean cepstrum?)


%0 Journal Article
%A Atal, B. S.
%D 1976
%T Automatic Recognition of Speakers from Their Voices
%B Proceedings of the IEEE
%V 64
%P 460 Ð 475


%0 Conference Proceedings
%A Atal, B.
%D 1989
%T A Model of LPC Excitation in terms of the Eigenvectors of the Autocorrelation Matrix of the Impulse Response of the LPC Filter
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Glasgow
%P 45 Ð 48
%F svd


%0 Edited Book
%A Atal, B. S.
%A Miller, J. L.
%A Kent, R. D.
%D 1991
%T Papers in Speech Communication: Speech Processing
%B Papers in Speech Communication
%E J. L. Miller
%I Acoustical Society of America
%C Woodbury
%V 3
%6 3
%O collection of TASSP, ASA, etc. papers

%0 Thesis
%A Attili, J. B.
%D 1987
%T On the Development of a Real-Time Text-Independent Speaker Verification System
%I Rensselaer Polytechnic Institute
%9 Ph.D. Dissertation


%0 Conference Proceedings
%A Attili, J.
%A Savic, M.
%A Campbell, J.
%D 1988
%T A TMS32020-Based Real Time, Text-Independent, Automatic Speaker Verification System
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C New York
%P 599 Ð 602


%0 Journal Article
%A Barbosa, Lineu C.
%D 1986
%T A Maximum-Energy-Concentration Spectral Window
%B IBM Journal of Research and Development
%V 30
%N 3
%P 321 Ð 325
%X An elegant method for designing a time-discrete solution for
realization of a spectral window which is ideal from an energy
concentration viewpoint.  This window is one that concentrates the
maximum amount of energy in a specified bandwidth and hence provides
optimal spectral resolution.  Unlike Kaiser windows, this window is
a discrete-time realization having the same objectives as the
continuous-time prolate spheroidal function; at the expense of not
having a closed form solution.


%0 Journal Article
%A Barnes, E. R.
%D 1982
%T An Algorithm for Separating Patterns by Ellipsoids
%B IBM Journal of Research and Development
%V 26
%N 6
%P 759 Ð 764
%O November

%0 Book
%A Blahut, R. E.
%D 1987
%T Principles and Practice of Information Theory
%B Electrical and Computer Engineering
%I Addison-Wesley
%C Reading
%O Discrimination (nonsymmetric divergence), Entropy Function, and Mutual Information

%0 Journal Article
%A Bogner, R. E.
%D 1981
%T On Talker Verification Via Orthogonal Parameters
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V ASSP-29
%N 1
%P 1 Ð 12
%O corrupted channels

%0 Journal Article
%A Bolt, R. H.
%A Cooper, F. S.
%A David, E. E., Jr.
%A Denes, P. B.
%A Pickett, J. M.
%A Stevens, K. N.
%D 1970
%T Speaker Identification by Speech Spectrograms: A Scientist's View of its Reliability for Legal Purposes
%B Journal of the Acoustical Society of America
%V 47
%N 2
%P 597 Ð 612
%F A.1 TUTORIAL PAPERS
%X General background on voice identification. Concentration on human identification methods and only touches on automatic methods?


%0 Book
%A Bolt, Richard H.
%A Cooper, Franklin S.
%A Green, David M.
%A Hamlet, Sandra L.
%A McKnight, John G.
%A Pickett, James M.
%A Tosi, Oscar I.
%A Underwood, Barbara D.
%A Hogan, Douglas L.
%A Banks, Waldena
%D 1979
%T On the Theory and Practice of Voice Identification
%I National Academy of Sciences
%C Washington
%O By the Committee on Evaluation of Sound Spectrograms.  Forensic aspects and Legal issues

%0 Book
%A Borden, G.
%A Harris, K.
%D 1984
%T Speech Science Primer
%I Williams & Wilkins
%C Baltimore
%P 302
%7 2nd


%0 Journal Article
%A Campbell, J. P., Jr.
%A Tremain, T. E.
%A Welch, V. C.
%D 1991
%T The Federal Standard 1016 4800 bps CELP Voice Coder
%B Digital Signal Processing
%V 1
%N 3
%P 145 Ð 155
%O Academic Press
Campbell, Joseph P., Jr.
Thomas E. Tremain
Vanoy C. Welch

%0 Thesis
%A Campbell, Joseph P., Jr.
%D 1991
%T False Acceptance Errors in Speaker Authentication Systems
%I Oklahoma State University
%9 Ph.D. Qualifying Examination Report
%O 6/19/91

%0 Book
%A Chen, C. H.
%D 1973
%T Statistical Pattern Recognition
%I Hayden
%C Rochelle Park
%O Kullback-Leibler numbers, divergence, Bhattacharyya distance, Matusita distance, Kolmogorov variational distance, Mahalanobis D^2 statistic. Chi-hau Chen

%0 Edited Book
%A Chen, C. H.
%D 1982
%T Digital Waveform Processing and Recognition
%I CRC Press
%C Boca Raton
%O Divergence, Bhattacharyya dist, mutual info. Chapters on Stat PR, Speech Proc, Spectral Analysis. Fortran programs included

%0 Book
%A Cover, Thomas M.
%A Thomas, Joy A.
%D 1991
%T Elements of Information Theory
%B Telecommunications
%E Donald L. Schilling
%I Wiley
%C New York
%O divergence, gambling

%0 Book
%A Crochiere, R. E.
%A Rabiner, L. R.
%D 1983
%T Multirate Digital Signal Processing
%I Prentice-Hall
%X This book is the only real reference for filter banks and multirate
systems, as opposed to being a tutorial.
%O ISBN 0136051626

%0 Report
%A Crystal, Thomas H.
%D 1990
%T Speaker Authentication Monitoring: Doomed to Failure?
%I IDA/CRD
%8 May 18


%0 Conference Proceedings
%A De Iacovo, R. Drogo
%A Montagna, R.
%A Sereno, D.
%D 1990
%T Vector Quantization and Perceptual Criteria in SVD based CELP Coders
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Albuquerque
%V 1
%6 5
%P 33 Ð 36
%F svd


%0 Journal Article
%A Demmel, James
%A Kahan, W.
%D 1990
%T Accurate Singular Values of Bidiagonal Matrices
%B SIAM Journal on Scientific and Statistical Computing
%V 11
%N 5
%P 873 Ð 912
%O September

%0 Book
%A Denes, P.
%A Pinson, E.
%D 1973
%T The Speech Chain
%I Doubleday
%C New York
%O Bell Telephone Laboratories, 1963

%0 Edited Book
%A Deprettere, E. F.
%D 1988
%T SVD and Signal Processing: Algorithms, Applications and Architectures
%I North-Holland
%C Amsterdam
%F svd


%0 Journal Article
%A Devijver, P. A.
%D 1974
%T On a New Class of Bounds on Bayes Risk in Multihypothesis Pattern Recognition
%B IEEE Transactions on Computers
%V C-23
%N 1
%P 70 Ð 80
%O Bayesian distance, equivocation, divergence, Bhattacharyya dist

%0 Edited Book
%A Dixon, N. R.
%A Martin, T. B.
%D 1979
%T Automatic Speech & Speaker Recognition
%I IEEE Press
%C New York
%O Collection of essential early works

%0 Journal Article
%A Doddington, G. R.
%D 1985
%T Speaker RecognitionÑIdentifying People by their Voices
%B Proceedings of the IEEE
%V 73
%N 11
%P 1651 Ð 1664
%F A.1 TUTORIAL PAPERS
%X Survey paper, oriented to illustrate the issues rather than exhaustively cataloging all the recent work. Treats acoustical bases of speaker recognition and factors limiting the recognizability of speakers. Reviews listening and spectrographic means of identification, also computer methods (more extensively), and then describes TIÕs operational verification system. Good overall introduction to speaker recognition methods and systems.
%O November 1985.

%0 Book
%A Duda, R.
%A Hart, P.
%D 1973
%T Pattern Classification and Scene Analysis
%I Wiley
%C New York


%0 Thesis
%A Endsley, J.
%D 1991
%T Joint Source-Channel Coding with Real Number BCH and Reed-Solomon Codes: Their Properties and Performance in the Presence of Additive Noise
%I Oklahoma State University
%9 Ph.D. Dissertation
%F svd


%0 Edited Book
%A Fallside, F.
%A Woods, W.
%D 1985
%T Computer Speech Processing
%I Prentice/Hall International
%C London
%O From U. Cambridge advanced course in 1983

%0 Book
%A Fant, Gunnar
%D 1970
%T Acoustic Theory of Speech Production: With Calculations based on X-Ray Studies of Russian Articulations
%B Description and Analysis of Contemporary Standard Russian
%I Mouton
%C The Hague


%0 Book
%A Flanagan, J.
%D 1972
%T Speech Analysis Synthesis and Perception
%I Springer-Verlag
%C Berlin
%7 2nd


%0 Journal Article
%A Foley, D.
%A Sammon, J.
%D 1975
%T An Optimal Set of Discriminant Vectors
%B IEEE Transactions on Computers
%V c-24
%N 3
%P 281 Ð 289
%O March

%0 Book
%A Fukunaga, K.
%D 1990
%T Introduction to Statistical Pattern Recognition
%B Computer Science and Scientific Computing
%E W. Rheinboldt and D. Siewiorek
%I Academic Press
%C San Diego
%7 2nd


%0 Journal Article
%A Furui, S.
%D 1981
%T Cepstral Analysis Technique for Automatic Speaker Verification
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V ASSP-29
%N 2
%P 254 Ð 272
%F A.3 TEXT DEPENDENT TECHNIQUES
%X Speaker verification using LPC-cepstral coefficients and 2nd order orthogonal polynomial coefficients, representing the short-time functions describing those coefficients. Normalization by subtracting the average cepstrum is used. Speech data recorded over the telephone, a high quality microphone, through an LPC vocoder, and through an ADPCM coder is used. Verification errors under 1% are achieved for most conditions. Fixed and per-speaker verification thresholds are investigated. Speaker model updating is investigated. DTW time registration is guided by the shorter of the reference or input utterance. FFT-cepstrum coefficients perform about as well as LPC-cepstrum ones, but require twice as much computation. LPC cepstrum coefficients yield a lower error rate than LARs.


%0 Journal Article
%A Furui, S.
%D 1991
%T Speaker-Dependent-Feature Extraction, Recognition and Processing Techniques
%B Speech Communication
%V 10
%P 505 Ð 520
%O Tutorial Review

%0 Audiovisual Material
%A Fussell, J.
%D 1986
%T Speech Processing (52.747) Class Notes
%I The Johns Hopkins University
%C Baltimore
%O Spring

%0 Report
%A Gish, H.
%A Karnofsky, K.
%A Krasner, M.
%A Roucos, S.
%A Russell, W.
%A Schwartz, R.
%A Wolf, J.
%D 1986
%T ISIS Literature Survey
%I BBN
%8 April
%9 Task Report
%@ 6142
%O Performed 1/14/82 to 2/15/86

%0 Journal Article
%A Gnanadesikan, R.
%A Kettenring, J. R.
%D 1989
%T Discriminant Analysis and Clustering
%B Statistical Science
%V 4
%N 1
%P 34 Ð 69
%O (Panel on Discriminant Analysis, Classification, and Clustering)

%0 Book Section
%A Golub, G.
%A Van Loan, C.
%D 1983
%T Matrix Computations
%I Johns Hopkins University Press
%C Baltimore
%P ¤8.3 and Chapter 12
%F svd


%0 Journal Article
%A Harris, F. J.
%D 1978
%T On the Use of Windows for Harmonic Analysis with the DFT
%B Proceedings of the IEEE
%V 66
%P 51 Ð 83
%X f. j. harris' classic overview paper for discrete-time 1D windows.  It discusses
some 15 different classes of windows including their spectral responses and
the reasons for their development.
%O January.  See also Nezih C. Geckinli & Davras Yavuz, "Some Novel Windows and a Concise Tutorial Comparison of Window Families", IEEE Transactions on Acoustics, Speech,
and Signal Processing, Vol. ASSP-26, No. 6, December 1978.

%0 Book
%A Haykin, S.
%D 1991
%T Adaptive Filter Theory
%I Prentice-Hall
%C Englewood Cliffs
%7 2nd


%0 Book
%A Hedges, L.
%A Olkin, I.
%D 1985
%T Statistical Methods for Meta-Analysis
%I Academic Press
%C San Diego


%0 Journal Article
%A Hermansky, H.
%D 1990
%T Perceptual Linear Predictive (PLP) Analysis of Speech
%B Journal of the Acoustical Society of America
%V 87
%N 4
%P 1738 Ð 1752
%O April

%0 Journal Article
%A Hermes, D. J.
%D 1988
%T Measurement of Pitch by Subharmonic Summation
%B Journal of the Acoustical Society of America
%V 83
%N 1
%P 257 Ð 264
%X Extension of Noll's pitch tracker with much less computation (shorter FFTs)


%0 Report
%A Hermes, D. J.
%D 1992
%T Pitch Analysis (for Proceedings of ESCA Workshop on Comparing Speech Signal Representations, Sheffield, England, April 7 Ð 9, 1992)
%I Institute for Perception Research
%8 March 3
%9 Manuscript
%@ 848


%0 Book Section
%A Hershey, J.
%A Yarlagadda, R.
%D 1986
%T Data Transportation and Protection
%I Plenum Press
%C New York
%P 193 Ð 194
%Y R. Lucky
%S R. Lucky
%F svd


%0 Book
%A Hess, W.
%D 1983
%T Pitch Determination of Speech Signals: Algorithms and Devices
%B Information Sciences
%E M. Schroeder
%I Springer-Verlag
%C Berlin


%0 Conference Proceedings
%A Higgins, A. L.
%A Wohlford, R. E.
%D 1986
%T A New Method of Text-Independent Speaker Recognition
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Tokyo
%V 2
%P 869 Ð 872
%F A.4 TEXT INDEPENDENT TECHNIQUES
%O April 1986.

%0 Personal Communication
%A Higgins, A.
%D 1988
%T Tutorial Papers


%0 Report
%A Higgins, A.
%A Porter, J.
%D 1989
%T YOHO Speaker Authentication Final Report
%I ITT Defense Communications Division
%8 September


%0 Audiovisual Material
%A Higgins, A.
%D 1990
%T YOHO Speaker Verification
%C Baltimore
%9 Speech Research Symposium-X
%O 16 Ð 17 October

%0 Journal Article
%A Higgins, A.
%A Bahler, L.
%A Porter, J.
%D 1991
%T Speaker Verification Using Randomized Phrase Prompting
%B Digital Signal Processing
%V 1
%N 2
%P 89 Ð 106
%O YOHO DTW System (NN System not included)

%0 Edited Book
%A Holmes, Mark H.
%A Rubenfeld, Lester A.
%D 1980
%T Mathematical Modeling of the Hearing Process
%B Lecture Notes in Biomathematics
%E S. Levin
%I Springer-Verlag
%C Berlin
%O NSF-CBMS Conference Proceedings, Troy, NY

%0 Report
%A House, Arthur S.
%D 1989
%T The Recognition of Speech by MachineÑA Bibliography
%I IDA/CRD
%8 December
%9 CRD Technical Report
%@ 28
%O This is a book now.

%0 Journal Article
%A Itakura, Fumitada
%D 1975
%T Line Spectrum Representation of Linear Predictive Coefficients
%B Transactions of the Committee on Speech Research, Acoustical Society of Japan
%V S75
%P 34
%O In Japanese

%0 Edited Book
%A Jesorsky, P.
%D 1978
%T Principles of Automatic Speaker-Recognition
%B Speech Communication with Computers
%E L. Bolc
%I Macmillan
%C New York
%F A.1 TUTORIAL PAPERS
%X Survey paper, just the basics, not very deep. Two interesting points, though. (1) figure 5.5 shows speaker recognition results as a function of speech sounds. The best are the 3 nasals, followed (generally) by the vowels, and then the fricatives; the stops were not shown. (2) In a brief description of the AUROS system, in deriving spectral features as, for each spectral channel or bin, the quotient of the mean and standard deviation, on the grounds that any spectral distortion from a channel would appear equally in numerator and denominator and therefore be canceled out.


%0 Audiovisual Material
%A Juang, B.-H.
%D 1988
%T Hidden Markov Model and its Application to Speech Processing (MA-513) Class Notes
%I AT&T Bell Labs
%C Linthicum
%O 5/9 - 5/13/88

%0 Journal Article
%A Kailath, T.
%D 1967
%T The Divergence and Bhattacharyya Distance Measures in Signal Selection
%B IEEE Transactions on Communication Technology
%V COM-15
%N 1
%P 52 Ð 60


%0 Report
%A Kang, G.
%A Fransen, L.
%D 1985
%T Low Bit Rate Speech Encoder Based on Line-Spectrum-Frequency
%I NRL
%8 January 24
%@ NRL Report 8857


%0 Report
%A Krasner, M.
%A Gish, H.
%A Makhoul, J.
%A Roucos, S.
%A Schwartz, R.
%D 1986
%T YOHO Speaker Authentication, Part II: Technical Proposal
%I BBN Laboratories
%8 February
%9 Proposal
%@ P86-CISD-010
%O Excellent introduction

%0 Journal Article
%A Kullback, S.
%A Leibler, R.
%D 1951
%T On Information and Sufficiency
%B Annals of Mathematical Statistics
%V 22
%P 79 Ð 86


%0 Book
%A Kullback, S.
%D 1968
%T Information Theory and Statistics
%I Dover
%C New York
%O Wiley, New York, 1959

%0 Book
%A Kullback, S.
%A Keegel, J. C.
%A Kullback, J. H.
%D 1987
%T Topics in Statistical Information Theory
%B Lecture Notes in Statistics
%E D. Brillinger, S. Fienberg, J. Gani, J. Hartigan and K. Krickeberg
%I Springer-Verlag
%C New York
%V 42


%0 Book
%A Ladefoged, Peter
%D 1962
%T Elements of Acoustic Phonetics
%I The University of Chicago Press
%C Chicago


%0 Edited Book
%A Lass, N.
%A McReynolds, L.
%A Northern, J.
%A Yoder, D.
%D 1982
%T Speech, Language, and Hearing
%I W. B. Sanders
%C Philadelphia
%V 1, Normal Processes
%6 3


%0 Journal Article
%A Lee, Yi-Teh
%D 1991
%T Information-Theoretic Distortion Measures for Speech Recognition
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V 39
%N 2
%P 330 Ð 335


%0 Book
%A Lewis, Frank L.
%D 1986
%T Optimal Estimation: With an Introduction to Stochastic Control Theory
%B A Wiley-Interscience publication
%I Wiley
%C New York
%O Reduced-order filters, p. 233

%0 Conference Proceedings
%A Li, K. P.
%A Wrench, E. H., Jr.
%D 1983
%T Text-Independent Speaker Recognition with Short Utterances
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Boston
%P 555 Ð 558
%F A.4 TEXT INDEPENDENT TECHNIQUES
%O See also JASA, 1982, Vol 72, p. S29-30

%0 Journal Article
%A Makhoul, J.
%D 1975
%T Linear Prediction: A Tutorial Review
%B Proceedings of the IEEE
%V 63
%P 561 Ð 580


%0 Book
%A Markel, J.
%A Gray, A.
%D 1976
%T Linear Prediction of Speech
%B Communication and Cybernetics
%I Springer-Verlag
%C Berlin


%0 Journal Article
%A Markel, J. D.
%A Oshika, B. T.
%A Gray, A. H., Jr.
%D 1977
%T Long-Term Feature Averaging for Speaker Recognition
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V ASSP-25
%P 330 Ð 337
%J Automatic Speech & Speaker Recognition, IEEE Press
%F text independent
%O covariance structure, scatter plots

%0 Journal Article
%A Markel, J. D.
%A Davis, S. B.
%D 1979
%T Text-Independent Speaker Recognition from a Large Linguistically Unconstrained Time-Spaced Data Base
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V ASSP-27
%N 1
%P 74 Ð 82
%X Uses spectra, pitch, and gain. Concludes that 30s or more yields stable linguistically-free data that result in recognition comparable to text dependent experiments.
%O Extension of Markel77?

%0 Book
%A Martin, F. N.
%D 1991
%T Introduction to Audiology
%I Prentice-Hall
%C Englewood Cliffs
%7 4th


%0 Book Section
%A Moler, Cleve
%A Little, John
%A Bangert, Steve
%D 1989
%T MatLabª for Macintosh Computers
%I The MathWorks, Inc.
%C South Natick
%P 2-54 Ð 2-55
%F svd


%0 Book
%A Myers, David
%A Schlosser, Woodrow D.
%A Wolfson, Robert J.
%A Winchester, Richard A.
%A Carmel, Norman
%D 1970
%T Otologic Diagnosis and the Treatment of Deafness
%I CIBA Pharmaceutical Company
%C Summit
%O Illustrations by Netter

%0 Magazine Article
%A Naik, J.
%D 1990
%T Speaker Verification: A Tutorial
%B IEEE Communications Magazine
%V 28
%N 1
%P 42 Ð 48
%8 January


%0 Conference Proceedings
%A Neuburg, E.
%D 1981
%T A Note on the Frequency Scale
%B Symposium on Acoustic Phonetics and Speech Modeling
%E A. House
%I IDA/CRD
%C Williamstown, Massachusetts
%V 3
%6 3
%P paper F22
%O SCAMP, 22 June to 31 July

%0 Book
%A OÕShaughnessy, D.
%D 1987
%T Speech Communication, Human and Machine
%B Digital Signal Processing
%I Addison-Wesley
%C Reading
%X Signal Processing, Physiology, Perception, Recognition by Humans


%0 Conference Proceedings
%A Offer, E.
%A Malah, D.
%A Dembo, A.
%D 1989
%T A Unified Framework for LPC Excitation Representation in Residual Speech Coders
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Glasgow
%P 41 Ð 44
%F svd


%0 Book
%A Oppenheim, A.
%A Schafer, R.
%D 1975
%T Digital Signal Processing
%I Prentice-Hall
%C Englewood Cliffs


%0 Book
%A Oppenheim, A. V.
%A Schafer, R. W.
%D 1989
%T Discrete-Time Signal Processing
%I Prentice-Hall
%C Englewood Cliffs
%X This is an updated version of the original, with some old material deleted
and lots of new material added.
%O ISBN 0-13-216292-X

%0 Journal Article
%A Paige, C. C.
%D 1986
%T Computing the Generalized Singular Value Decomposition
%B SIAM Journal on Scientific and Statistical Computing
%V 7
%N 4
%P 1126 Ð 1146
%O Improvement over van Loan, 1984?

%0 Book
%A Papoulis, Athanasios
%D 1962
%T The Fourier Integral and its Applications
%I McGraw-Hill
%C New York


%0 Book
%A Papoulis, Athanasios
%D 1984
%T Probability, Random Variables, and Stochastic Processes
%I McGraw-Hill
%C New York
%7 2nd


%0 Book
%A Parsons, T.
%D 1987
%T Voice and Speech Processing
%B Communications and Signal Processing
%E S. Director
%I McGraw-Hill
%C New York
%X Addresses the cocktail party effect, as well as other material.
%O ISBN 0-07-048541-0.

%0 Audiovisual Material
%A Pentz, A.
%D 1990
%T Speech Science (SPATH 4313) Class Notes
%I Oklahoma State University
%C Stillwater


%0 Book Section
%A Press, W.
%A Flannery, B.
%A Teukolsky, S.
%A Vetterling, W.
%D 1990
%T Numerical Recipes, The Art of Scientific Computing (FORTRAN version)
%I Cambridge University Press
%C Cambridge
%P 52 Ð 64
%F svd


%0 Report
%A Press, W.
%D 1991
%T Wavelet Transforms (to appear in Numerical Recipes: The Art of Scientific Computing, 2nd ed.)
%I Harvard-Smithsonian Center for Astrophysics
%8 July 21
%9 Preprint
%@ 3184
%X Pedagogical review
%O From: Bill Press, Harvard University.
Date: Tue, 21 Jul 92 11:40:31 -0400
Subject: Numerical Recipes software

This fall, the second edition of the Numerical Recipes book will come
out. It will include a chapter on wavelets and software both in Fortran
and C.

A preliminary version of the paper and the software can be downloaded
from anonymous ftp to 128.103.40.79, in /pub/wavelet.tex and
/pub/wavelet.f.
The figures are, unfortunately, NOT available on-line, and there are
no more preprints.

%0 Book
%A Rabiner, L.
%A Schafer, R.
%D 1978
%T Digital Processing of Speech Signals
%B Signal Processing
%E A. Oppenheim
%I Prentice-Hall
%C Englewood Cliffs
%O ISBN 0-13-213603-1

%0 Magazine Article
%A Rabiner, L.
%A Juang, B.-H.
%D 1986
%T An Introduction to Hidden Markov Models
%B IEEE ASSP Magazine
%V 3
%N 1
%P 4 Ð 16
%8 January


%0 Journal Article
%A Rabiner, L. R.
%D 1989
%T A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition
%B Proceedings of the IEEE
%V 77
%N 2
%P 257 Ð 286
%X Excellent review of HMMs in speech: MMI & MDI criteria, higher order HMMs, "classic problems"


%0 Journal Article
%A Rosenberg, A.
%D 1976
%T Automatic Speaker Verification: A Review
%B Proceedings of the IEEE
%V 64
%N 4
%P 475 Ð 487
%F A.1 TUTORIAL PAPERS
%X An introduction to speaker verification with many references. References include papers discussing intersession variability of speakers and channels, as well as experiments using telephone channels.
%O April 1976.

%0 Journal Article
%A Rosenberg, A. E.
%A Soong, F. K.
%D 1987
%T Evaluation of a Vector Quantization Talker Recognition System in Text Independent and Text Dependent Modes
%B Computer Speech and Language
%V 22
%P 143 Ð 157


%0 Book Section
%A Rosenberg, A. E.
%A Soong, F. K.
%D 1992
%T Recent Research in Automatic Speaker Recognition
%B Advances in Speech Signal Processing
%E S. Furui and M. M. Sondhi
%I Marcel Dekker
%C New York
%P 701 Ð 738


%0 Book
%A Saito, Shuzo
%A Nakata, Kazuo
%D 1985
%T Fundamentals of Speech Signal Processing
%I Academic Press
%C Tokyo
%O English translation from 1981

%0 Journal Article
%A Sakoe, H.
%A Chiba, S.
%D 1978
%T Dynamic Programming Algorithm Optimization for Spoken Word Recognition
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V ASSP-26
%N 1
%P 43 Ð 49


%0 Conference Proceedings
%A Sanchez-Calle, V.
%A Lopez-Soler, J.
%A Segura-Luna, J.
%A Peinado-Herreros, A.
%A Rubio-Ayuso, A.
%D 1990
%T Increasing the Difference between the Significant and the Non-Significant Singular Values in a Model of LPC Excitation Based on the SVD
%B Fifth European Signal Processing Conference
%I Elsevier
%C Barcelona
%V 2
%P 1287 Ð 1290
%7 V
%F svd


%0 Book
%A Sanders, D. A.
%D 1977
%T Auditory Perception of Speech
%I Prentice-Hall
%C Englewood Cliffs
%O Ch 5

%0 Book
%A Saunders, William H.
%D 1964
%T The Larynx
%I CIBA Pharmaceutical Company
%C Summit
%O Illustrations by Netter

%0 Book
%A Scharf, L.
%D 1991
%T Statistical Signal Processing: Detection, Estimation, and Time Series Analysis
%B Digital Signal Processing
%E R. Roberts
%I Addison-Wesley
%C Reading
%O Strong linear algebra & statistics

%0 Book Section
%A Schroeder, M.
%A Atal, B.
%A Hall, J.
%D 1979
%T Objective Measure of Certain Speech Signal Degradations Based on Masking Properties of Human Auditory Perception
%B Frontiers of Speech Communication Research
%E Lindblom and Ohman
%I Academic Press
%C London


%0 Edited Book
%A Schwab, E. C.
%A Nusbaum, H. C.
%D 1986
%T Pattern Recognition by Humans and Machines
%B Cognition and Perception
%I Academic Press
%C San Diego
%V 1
%6 2
%O Emphasis on speech recog rather than speaker recog.

%0 Conference Proceedings
%A Schwartz, R.
%A Roucos, S.
%A Berouti, M.
%D 1982
%T The Application of Probability Density Estimation to Text Independent Speaker Identification
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Paris
%P 1649 Ð 1652
%F A.4 TEXT INDEPENDENT TECHNIQUES
%X Compares 4 classifiers: (1) Mahalanobis distance, (2) Gaussian pdf, (3) robust Gaussian pdf, and (4) k-NN nonparametric pdf. Laboratory speech, single session, 21 male talkers. The pdf classifiers perform better than the Mahalanobis distance one, and the nonparametric method is the best of these.


%0 Journal Article
%A Sekey, A.
%A Hanson, B.
%D 1984
%T Improved One-Bark Bandwidth Auditory Filter
%B Journal of the Acoustical Society of America
%V 75
%N 6
%P 1902 Ð 1904
%O June

%0 Report
%A Slaney, M.
%D 1988
%T LyonÕs Cochlear Model
%I Apple Computer, Inc.
%8 November
%9 Apple Technical Report
%@ 13


%0 Conference Proceedings
%A Slaney, M.
%A Lyon, R.
%D 1990
%T A Perceptual Pitch Detector
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Albuquerque
%P 357 Ð 360


%0 Journal Article
%A Soong, F. K.
%A Rosenberg, A. E.
%A Rabiner, L. R.
%A Juang, B.-H.
%D 1987
%T A Vector Quantization Approach to Speaker Recognition
%B AT&T Technical Journal
%V 66
%N 2
%P 14 Ð 26
%O March/April

%0 Journal Article
%A Soong, F. K.
%A Rosenberg, A. E.
%D 1988
%T On the Use of Instantaneous and Transitional Spectral Information in Speaker Recognition
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V 36
%N 6
%P 871 Ð 879
%O delta cepstrum

%0 Journal Article
%A Spicer, C. C.
%D 1972
%T Calculation of Power Sums of Deviations about the Mean
%B Applied Statistics
%V 21
%N 2
%P 226 Ð 227
%O Minimize rounding error (used in SYSTAT)

%0 Book
%A Stevens, Stanley Smith
%A Davis, Hallowell
%D 1966
%T Hearing: Its Psychology and Physiology
%I Wiley
%C New York


%0 Book
%A Strang, G.
%D 1988
%T Linear Algebra and its Applications
%I Harcourt Brace Jovanovich
%C San Diego
%P 505
%7 3rd
%F svd


%0 Book Section
%A Sutherland, A.
%A Jack, M.
%D 1988
%T Speaker Verification
%B Aspects of Speech Technology
%E M. Jack and J. Laver
%I Edinburgh University Press
%C Edinburgh
%P 185 Ð 215
%O review/survey chapter

%0 Journal Article
%A Timcke, Rolf H.
%A von Leden, Hans
%A Moore, Paul
%D 1958
%T Laryngeal Vibrations: Measurements of the Glottic Wave
%B Archives of Otolaryngology
%V 68
%P 1 Ð 19
%O Phonation

%0 Journal Article
%A Tishby, N. Z.
%D 1991
%T On the Application of Mixture AR Hidden Markov Models to Text Independent Speaker Recognition
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V 39
%N 3
%P 563 Ð 570
%O Marginal improvement over VQ method

%0 Book
%A Tobias, J. V.
%D 1970
%T Foundations of Modern Auditory Theory
%I Academic Press
%C New York
%F svd


%0 Book Section
%A Tou, J.
%A Heydorn, P.
%D 1967
%T Some Approaches to Optimum Feature Extraction
%B Computer and Information Sciences-II
%E J. Tou
%I Academic Press
%C New York
%V COINS II
%P 57 Ð 89


%0 Book
%A Tou, J.
%A Gonzalez, R.
%D 1974
%T Pattern Recognition Principles
%B Applied Mathematics and Computation
%E R. Kalaba
%I Addison-Wesley
%C Reading


%0 Journal Article
%A Trancoso, I.
%A Atal, B.
%D 1990
%T Efficient Search Procedures for Selecting the Optimum Innovation in Stochastic Coders
%B IEEE Transactions on Acoustics, Speech, and Signal Processing
%V 38
%N 3
%P 385 Ð 396
%F svd


%0 Book
%A Turabian, Kate L.
%D 1987
%T A Manual for Writers of Term Papers, Theses, and Dissertations
%I The University of Chicago Press
%C Chicago
%7 5th
%O Based upon The Chicago Manual of Style, 13th ed, 1982.

%0 Edited Book
%A Vaccaro, R. J.
%D 1991
%T SVD and Signal Processing, II: Algorithms, Analysis and Applications
%I Elsevier
%C Amsterdam


%0 Journal Article
%A Vaidyanathan, P. P.
%D 1990
%T Multirate Digital Filters, Filter Banks, Polyphase Networks, and Applications: A Tutorial
%B Proceedings of the IEEE
%V 78
%N 1
%P 56 Ð 93


%0 Journal Article
%A Van Immerseel, Luc M.
%A Martens, Jean-Pierre
%D 1992
%T Pitch and Voiced/Unvoiced Determination with an Auditory Model
%B Journal of the Acoustical Society of America
%V 91
%N 6
%P 3511 Ð 3526
%X AMPEX (new method) shown to outperform SIFT (Markel) and SHS (Hermes) in noise and bandpass speech


%0 Journal Article
%A Van Loan, C.
%D 1985
%T Computing the CS and Generalized Singular Value Decomposition
%B Numerische Mathematik
%V 46
%P 479 Ð 492
%F svd
%O GSVD algorithm.  See also Technical Report CS-604 (same title), Dept of Computer Science, Cornell Univ (out of print)

%0 Book Section
%A Vetterling, W.
%A Teukolsky, S.
%A Press, W.
%A Flannery, B.
%D 1989
%T Numerical Recipes, Example Book (FORTRAN version)
%I Cambridge University Press
%C Cambridge
%P Chapters 2 and 14
%F svd


%0 Book
%A von BŽkŽsy, Georg
%D 1960
%T Experiments in Hearing
%E E. G. Wever
%I McGraw-Hill
%C New York
%? E. G. Wever


%0 Book
%A Wald, A.
%D 1947
%T Sequential Analysis
%I Wiley
%C New York


%0 Conference Proceedings
%A Wang, S.
%A Sekey, A.
%A Gersho, A.
%D 1991
%T Auditory Distortion Measure for Speech Coding
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Toronto
%V 1
%P 493 Ð 496
%O see also Shihua's Ph.D. dissertation: Low Bit-Rate Vector Excitation Coding of Phonetically Classified Speech, UCSB, 1991

%0 Thesis
%A Wang, Shihua
%D 1991
%T Low Bit-Rate Vector Excitation Coding of Phonetically Classified Speech
%I University of California at Santa Barbara
%9 Ph.D. Dissertation


%0 Book
%A Whalen, A.
%D 1971
%T Detection of Signals in Noise
%B Electrical Science
%E H. Booker and N. DeClaris
%I Academic Press
%C New York


%0 Book
%A Widrow, B.
%A Stearns, S. D.
%D 1985
%T Adaptive Signal Processing
%I Prentice-Hall
%C Englewood Cliffs


%0 Conference Proceedings
%A Wohlford, R. E.
%A Wrench, E. H., Jr.
%A Landell, B. P.
%D 1980
%T A Comparison of Four Techniques for Automatic Speaker Recognition
%B International Conference on Acoustics, Speech, and Signal Processing
%I IEEE
%C Denver
%V 3
%P 908 Ð 911
%F A.2 COMPREHENSIVE STUDIES
%X Comparison of four methods using LPC, cepstra, and spectral bands. Models use a lot of data, at least 10 minutes per reference speaker. Classification by minimum distance. LPC features performed better, may be due to overall gain not normalized for spectral bands or cepstrum. Notes change in speakers over time.


%0 Book Section
%A Wolfram, S.
%D 1988
%T Mathematicaª, A System for Doing Mathematics by Computer
%I Addison-Wesley
%C Redwood City
%P 454 Ð 455
%F svd


%0 Audiovisual Material
%A Yarlagadda, R.
%D 1991
%T Data Transportation and Protection (ECEN 5543) Class Notes
%I Oklahoma State University
%C Stillwater
%9 Viewgraphs
%F svd
%O 18 February, p. 25 Ð 27

%0 Personal Communication
%A Yarlagadda, R.
%D 1991
%T Personal Communication