@article{saeidi_mohammadi_ganchev_rodman_2009, title={Particle Swarm Optimization for Sorted Adapted Gaussian Mixture Models}, volume={17}, ISSN={["1558-7924"]}, DOI={10.1109/TASL.2008.2010278}, abstractNote={Recently, we introduced the sorted Gaussian mixture models (SGMMs) algorithm providing the means to tradeoff performance for operational speed and thus permitting the speed-up of GMM-based classification schemes. The performance of the SGMM algorithm depends on the proper choice of the sorting function, and the proper adjustment of its parameters. In the present work, we employ particle swarm optimization (PSO) and an appropriate fitness function to find the most advantageous parameters of the sorting function. We evaluate the practical significance of our approach on the text-independent speaker verification task utilizing the NIST 2002 speaker recognition evaluation (SRE) database while following the NIST SRE experimental protocol. The experimental results demonstrate a superior performance of the SGMM algorithm using PSO when compared to the original SGMM. For comprehensiveness we also compared these results with those from a baseline Gaussian mixture model-universal background model (GMM-UBM) system. The experimental results suggest that the performance loss due to speed-up is partially mitigated using PSO-derived weights in a sorted GMM-based scheme.}, number={2}, journal={IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING}, author={Saeidi, Rahim and Mohammadi, Hamid Reza Sadegh and Ganchev, Todor and Rodman, Robert David}, year={2009}, month={Feb}, pages={344–353} }
 @article{rodman_mcallister_bitzer_cepeda_abbitt_2002, title={Forensic speaker identification based on spectral moments}, volume={9}, ISSN={["1350-1771"]}, DOI={10.1558/sll.2002.9.1.22}, abstractNote={A new method for doing text-independent speaker identification geared to forensic situations is presented. By analysing ‘isolexemic’ sequences, the method addresses the issues of very short criminal exemplars and the need for open-set identification. An algorithm is given that computes an average spectral shape of the speech to be analysed for each glottal pulse period. Each such spectrum is converted to a probability density function and the first moment (i.e. the mean) and the second moment about the mean (i.e. the variance) are computed. Sequences of moment values are used as the basis for extracting variables that discriminate among speakers. Ten variables are presented all of which have sufficiently high inter- to intraspeaker variation to be effective discriminators. A case study comprising a ten-speaker database, and ten unknown speakers, is presented. A discriminant analysis is performed and the statistical measurements that result suggest that the method is potentially effective. The report represents work in progress.}, number={1}, journal={FORENSIC LINGUISTICS-THE INTERNATIONAL JOURNAL OF SPEECH LANGUAGE AND THE LAW}, author={Rodman, R and McAllister, D and Bitzer, D and Cepeda, L and Abbitt, P}, year={2002}, pages={22–43} }
 @article{rodman_2002, title={Linguistics and the law: how knowledge of, or ignorance of, elementary linguistics may affect the dispensing of justice}, volume={9}, ISSN={["1350-1771"]}, DOI={10.1558/sll.2002.9.1.94}, abstractNote={Ignorance of elementary linguistic concepts may have a bearing on justice. This thesis is drawn from the conviction appeal of a Haitian-born American sentenced to prison for 12 years for dealing cocaine. The verdict was based in part on a surreptitious recording of the drug deal. Although the drug dealer on the tape spoke a dialect of American Black English, and the defendant speaks English with a Creole accent, the State persuaded the jury that the Haitian disguised his voice by purposefully dropping his accent. His ability to perform this feat was attributed in testimony to the fact that he had been an interpreter for the United States Army in Haiti, and was therefore a linguist, and therefore understood ‘sound change’, and therefore could disguise his voice by dropping his foreign accent. This absurd chain of non sequiturs, and the resulting miscarriage of justice, is the result of linguistic naivety and would not have occurred if the court knew that an interpreter is not necessarily a linguist, and that sound change refers to the historical development of languages.}, number={1}, journal={FORENSIC LINGUISTICS-THE INTERNATIONAL JOURNAL OF SPEECH LANGUAGE AND THE LAW}, author={Rodman, R}, year={2002}, pages={94–103} }
 @book{rodman_1999, title={Computer speech technology}, ISBN={0890062978}, publisher={Boston: Artech House}, author={Rodman, R. D.}, year={1999} }
 @book{rodman_fromkin_1998, title={An introduction to language (6th ed.)}, ISBN={003018682X}, publisher={Fort Worth: Harcourt Brace Jovanovich College Publishers}, author={Rodman, R. D. and Fromkin, V.}, year={1998} }
 @inproceedings{rodman_mcallister_bitzer_freeman_1998, title={Automated lip-sync animation as a telecommunications aid for the hearing impaired}, booktitle={Proceedings, 1998 IEEE 4th Workshop Interactive Voice Technology for Telecommunications Applications: IVTTA '98, September 29th-30th, 1998, Turino, Italy}, publisher={New York: Institute of Electrical and Electronics Engineers, Inc.; Piscataway, NJ: IEEE Service Center}, author={Rodman, R. D. and McAllister, D. F. and Bitzer, D. L. and Freeman, A. S.}, year={1998}, pages={202–208} }
 @article{mcallister_rodman_bitzer_freeman_1998, title={Speaker independence in automated lip-sync for audio-video communication}, volume={30}, ISSN={["0169-7552"]}, DOI={10.1016/S0169-7552(98)00216-5}, abstractNote={By analyzing the absolute value of the Fourier transform of a speaker's voice signal we can predict the position of the mouth for English vowel sounds. This is without the use of text, speech recognition or mechanical or other sensing devices attached to the speaker's mouth. This capability can reduce the time required for mouth animation considerably. We expect it to be competitive eventually with the speech/text driven solutions which are becoming popular. Our technique would require much less interaction from the user and no knowledge of phonetic spelling. We discuss the problems of producing an algorithm that is speaker independent. The goal is to avoid having to measure mouth movements off video for each speaker's training sounds. We have discovered that eliminating variation due to pitch yields moments which are mouth shape dependent but not speaker dependent. This implies that careful construction of predictor surfaces can produce speaker independent prediction of mouth motion for English vowels.}, number={20-21}, journal={COMPUTER NETWORKS AND ISDN SYSTEMS}, author={McAllister, DF and Rodman, RD and Bitzer, DL and Freeman, AS}, year={1998}, month={Nov}, pages={1975–1980} }
 @inproceedings{rodman_1998, title={Speaker recognition of disguised voices}, number={1998}, booktitle={Proceedings of the COST250 Conference on speaker recognition by man and machine: directions for forensic applications. Ankara, Turkey. April, 1998}, author={Rodman, R. D.}, year={1998}, pages={9–22} }
 @inproceedings{rodman_bitzer_mcallister_1997, title={Lip synchronization as an aid to the hearing disabled}, number={1997}, booktitle={AVIOS 97: Proceedings of the American Voice Input/Output Society (AVIOS), September 1997}, publisher={San Jose, Calif.: American Voice Input/Output Society Society}, author={Rodman, R. D. and Bitzer, D. L. and McAllister, D. F.}, year={1997}, pages={233–248} }
 @inproceedings{rodman_mcallister_bitzer_1997, title={Lip synchronization for animation}, booktitle={Computer graphics: Proceedings, annual conference series, 1997: SIGGRAPH 97 Conference proceedings, August 3-8, 1997}, publisher={New York, N.Y.: Association for Computing Machinery}, author={Rodman, R. D. and McAllister, D. F. and Bitzer, D. L.}, year={1997}, pages={225–226} }
 @inproceedings{mcallister_bitzer_rodman_1997, title={Lip synchronization of speech}, booktitle={Proceedings of the Audio Visual Speech Processing Conference '97, October 1997}, author={McAllister, D. F. and Bitzer, D. L. and Rodman, R. D.}, year={1997}, pages={133–136} }
 @inbook{rodman_1997, title={On left dislocation}, booktitle={Materials on left dislocation}, publisher={Philadelphia: Benjamins Pub. Co.}, author={Rodman, R. D.}, editor={E. Anagnostopoulou, H. van Riemsdijk and Zwarts, F.Editors}, year={1997}, pages={31–54} }
 @inproceedings{rodman_mcallister_bitzer_1997, title={Toward speaker independence in automated lip-sync}, number={1997}, booktitle={Compugraphics '97: Proceedings of the International Conference on Computational Graphics and Visualization Techniques, December 1997}, publisher={Portugal}, author={Rodman, R. D. and McAllister, D. F. and Bitzer, D. L.}, year={1997}, pages={1–5} }
 @book{rodman_klevans_1997, title={Voice recognition}, ISBN={0890069271}, publisher={Boston, MA: Artech House}, author={Rodman, R. D. and Klevans, R.}, year={1997} }