{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T05:53:06Z","timestamp":1771480386124,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":45,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540715030","type":"print"},{"value":"9783540715054","type":"electronic"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-71505-4_7","type":"book-chapter","created":{"date-parts":[[2007,5,23]],"date-time":"2007-05-23T21:29:56Z","timestamp":1179955796000},"page":"101-117","source":"Crossref","is-referenced-by-count":41,"title":["Voice Disguise and Automatic Detection: Review and Perspectives"],"prefix":"10.1007","author":[{"given":"Patrick","family":"Perrot","sequence":"first","affiliation":[]},{"given":"Guido","family":"Aversano","sequence":"additional","affiliation":[]},{"given":"G\u00e9rard","family":"Chollet","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"7_CR1","unstructured":"Abe, M., Nakamura, S., Shikano, K., Kuwabara, H.: Voice conversion through vector quantization. In: Proc. ICASSP 88, New-York (1988)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Amir, N.: Classifying emotions in speech: a comparison of methods. In: Proceedings EUROSPEECH 2001, Scandinavia (2001)","DOI":"10.21437\/Eurospeech.2001-44"},{"key":"7_CR3","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/3-540-46154-X_37","volume-title":"Text, Speech and Dialogue","author":"G. Baudoin","year":"2002","unstructured":"Baudoin, G., Capman, F., \u010cernock\u00fd, J., El Chami, F., Charbit, M., Chollet, G., Petrovska-Delacr\u00e9taz, D.: Advances in Very Low Bit Rate Speech Coding Using Recognition and Synthesis Techniques. In: Sojka, P., Kope\u010dek, I., Pala, K. (eds.) TSD 2002. LNCS (LNAI), vol.\u00a02448, pp. 269\u2013276. Springer, Heidelberg (2002)"},{"key":"7_CR4","unstructured":"Beaugendre, F.: \u201cMod\u00e8le de l\u2019intonation pour la synth\u00e8se\u201d.1995 de la parole\u201d. In: Fondements et perspectives en traitement automatique de la parole, Aupelf-Uref, edn. (1995)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Bimbot, F., Chollet, G., Deleglise, P., Montaci\u00e9, C.: Temporal Decomposition and Acoustic-phonetic Decoding of Speech. In: Proc. ICASSP 88, New-York, pp. 445\u2013448 (1988)","DOI":"10.1109\/ICASSP.1988.196614"},{"key":"7_CR6","unstructured":"Blomberg, M., Elenius, D., Zetterholm, E.: Speaker verification scores and acoustics analysis of a professional impersonator. In: Proc. FONETIK (2004)"},{"key":"7_CR7","unstructured":"Blouet, R., Mokbel, C., Chollet, G.: BECARS: a free software for speaker recognition. In: ODYSSEY 2004, Toledo (2004)"},{"key":"7_CR8","unstructured":"Boersma, P., Weenink, D.: PRAAT: doing phonetics by computer, http:\/\/www.praat.org"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Cappe, O., Stylianou, Y., Moulines, E.: Statistical methods for voice quality transformation. In: Proc. of EUROSPEECH 95, Madrid (1995)","DOI":"10.21437\/Eurospeech.1995-121"},{"key":"7_CR10","unstructured":"Chollet, G., Cernocky, J., Constantinescu, A., Deligne, S., Bimbot, F.: Toward ALISP: a proposal for Automatic Language Independent Speech Processing. In: Computational Models of Speech Processing. NATO ASI Series (1997)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Delvaux, V., Metens, T., Soquet, A.: French nasal vowels: articulary and acoustic properties. In: Proc. Of the 7th ICSLP, vol. 1, Denver, pp. 53\u201356 (2002)","DOI":"10.21437\/ICSLP.2002-51"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Dutoit, T.: High quality text to speech synthesis: a comparison of four candidates algorithms. In: Proc. ICASSP 1994, vol. 1, Adela\u00efde, Australie, pp. 565\u2013568 (1994)","DOI":"10.1109\/ICASSP.1994.389231"},{"issue":"1","key":"7_CR13","first-page":"168","volume":"3","author":"R.M. Figueiredo de","year":"1996","unstructured":"de Figueiredo, R.M., de Souza Britto, H.: A report on the acoustic effects of one type of disguise. Forensic Linguistics\u00a03(1), 168\u2013175 (1996)","journal-title":"Forensic Linguistics"},{"key":"7_CR14","volume-title":"Advances in Phonetics","author":"D. Genoud","year":"1999","unstructured":"Genoud, D., Chollet, G.: Voice transformations: some tools for the imposture of speaker verification systems. In: Braun, A. (ed.) Advances in Phonetics, Franz Steiner Verlag, Stuttgart (1999)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Gibbon, D., Gut, U.: Measuring speech rhythm. In: Proc. Eurospeech 2001, Scandinavia (2001)","DOI":"10.21437\/Eurospeech.2001-36"},{"key":"7_CR16","doi-asserted-by":"publisher","first-page":"1842","DOI":"10.1121\/1.1912589","volume":"49","author":"W. Endres","year":"1971","unstructured":"Endres, W., Balbach, W., Fl\u00f6sser, G.: Voice spectrograms as a function of age, voice disguise and voice imitation. Journal of the Acosutical Society of America\u00a049, 1842\u20131848 (1971)","journal-title":"Journal of the Acosutical Society of America"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Gu, L., Harris, J.G., Shrivastav, R., Sapienza, C.: Disordered speech evaluation using objective quality measures. In: Proc. ICASSP 2005, Philadelphia (2005)","DOI":"10.1155\/ASP.2005.1400"},{"key":"7_CR18","unstructured":"Hall, M.: Spectrographic analysis of interspeaker and intraspeaker variability of professional mimicry. MA dissertation, Michigan State University (1975)"},{"key":"7_CR19","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1558\/sll.2000.7.2.149","volume":"7","author":"H.J. K\u00fcnzel","year":"2000","unstructured":"K\u00fcnzel, H.J.: Effects of voice disguise on fundamental frequency. Forensic linguistics\u00a07, 149\u2013179 (2000)","journal-title":"Forensic linguistics"},{"key":"7_CR20","unstructured":"K\u00fcnzel, H., Gonzalez-Rodriguez, J., Ortega-Garcia, J.: Effect of voice disguise on the performance of a forensic automatic speaker recognition system. In: Proc. Odyssey (2004)"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/0141-5425(93)90115-F","volume":"15","author":"A. Hirson","year":"1993","unstructured":"Hirson, A., Duckworth, M.: Glottal fry and voice disguise: a case study in forensic phonetics. Journal of Biomedical Enginering\u00a015, 193\u2013200 (1993)","journal-title":"Journal of Biomedical Enginering"},{"key":"7_CR22","unstructured":"Jiang, D., Zhang, W., Shen, L., Cai, L.: Prosody analysis and modelling for emotional speech synthesis. In: Proc. ICASSP 2005, Philadelphia (2005)"},{"key":"7_CR23","unstructured":"Kain, A., Macon, M.W.: Spectral voice conversion for text to speech synthesis. In: Proc. ICASSP 98, New York (1998)"},{"key":"7_CR24","unstructured":"Kain, A., Macon, M.W.: Design and evaluation of a voice conversion algorithm based on spectral envelope mapping and residual prediction. In: Proc. ICASSP 01, Salt Lake City (2001)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Lummis, R.C., Rosenberg, A.E.: Test of an automatic speaker verification method with intensively trained professional mimics. Journal of Acoustical Society of America\u00a09(1) (1972)","DOI":"10.1121\/1.1981415"},{"issue":"1","key":"7_CR26","first-page":"160","volume":"3","author":"H. Masthoff","year":"1996","unstructured":"Masthoff, H.: A report on voice disguise experiment. Forensic Linguistics\u00a03(1), 160\u2013167 (1996)","journal-title":"Forensic Linguistics"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Martin, A., Doddington, G., Kamm, T., Ordowski, M., Przybocki, M.: The DET curve in assessment of detection task performance. In: Proc. EUROSPEECH 97, Rhodes, Greece, pp. 1895\u20131898 (1997)","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"7_CR28","unstructured":"Melvaldova, J.: Caract\u00e9ristiques temporelle de la parole imit\u00e9e. In: Proceedings JEP, Journ\u00e9es d\u2019Etudes sur la Parole (2004)"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Moosm\u00fcller, S.: The influence of creaky voice on formant frequency changes. The International Journal of Speech, Language and the Law\u00a08(1) (2001)","DOI":"10.1558\/ijsll.v8i1.100"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Moulines, E., Charpentier, F.: Pitch synchronous waveform processing techniques for text to speech synthesis using diphone. Speech comm.\u00a09, 453\u2013497","DOI":"10.1016\/0167-6393(90)90021-Z"},{"issue":"3","key":"7_CR31","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1002\/acp.2350090306","volume":"9","author":"T. Ochard","year":"1995","unstructured":"Ochard, T., Yarmey, A.: The effects of whispers, voice sample duration and voice distinctiveness on criminal Speaker Identification. Appl. Cogn. Psychol.\u00a09(3), 249\u2013260 (1995)","journal-title":"Appl. Cogn. Psychol."},{"key":"7_CR32","unstructured":"Perrot, P., Aversano, G., Blouet, R., Charbit, M., Chollet, G.: Voice forgery using ALISP. In: Proc. ICASSP 2005, Philadelphie (2005)"},{"key":"7_CR33","unstructured":"Rodman, R.: Speaker Recognition of disguised voices: a program for research. In: Consortium on Speech Technology Conference on Speaker by man and machine: direction for forensic applications, COST 250, Ankara, Turkey (1998)"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Valbret, H., Moulines, E., Tubach, J.P.: Voice trans-formation using PSOLA technique. In: Proc. ICASSP 92, San Francisco (1992)","DOI":"10.1109\/ICASSP.1992.225951"},{"key":"7_CR35","unstructured":"Shafran, I., Mohri, M.: A comparison of classifiers for detecting emotion from speech. In: Proc. ICASSP 2005, Philadelphia (2005)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Stylianou, Y., Cappe, O.: A system for voice conversion based on probabilistic classification and a harmonic plus noise model. In: Proc ICASSP 98, Seattle, WA, pp. 281\u2013284 (1998)","DOI":"10.1109\/ICASSP.1998.674422"},{"issue":"2","key":"7_CR37","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/89.661472","volume":"6","author":"Y. Stylianou","year":"1998","unstructured":"Stylianou, Y., Cappe, O., Moulines, E.: Continuous probalistic transform for voice conversion. IEEE Trans. Speech and Audio Processing\u00a06(2), 131\u2013142 (1998)","journal-title":"IEEE Trans. Speech and Audio Processing"},{"key":"7_CR38","unstructured":"Zetterholm, E.: Voice Imitation. A phonetic study of perceptual illusions and acoustic success. Dissertation, Department of Linguistics and Phonetics, Lund University (2003)"},{"key":"7_CR39","first-page":"118","volume":"50","author":"D. Rostolland","year":"1982","unstructured":"Rostolland, D.: Acoustic features of shouted voice. Acustica\u00a050, 118\u2013125 (1982a)","journal-title":"Acustica"},{"key":"7_CR40","first-page":"80","volume":"51","author":"D. Rostolland","year":"1982","unstructured":"Rostolland, D.: Phonetic structure of shouted voice. Acustica\u00a051, 80\u201389 (1982b)","journal-title":"Acustica"},{"key":"7_CR41","first-page":"103","volume":"57","author":"D. Rostolland","year":"1985","unstructured":"Rostolland, D.: Intelligibility of shouted voice. Acoustica\u00a057, 103\u2013121 (1985)","journal-title":"Acoustica"},{"key":"7_CR42","unstructured":"Abboud, B., Bredin, H., Aversano, G., Chollet, G.: Audio visual forgery in identity verification. In: Workshop on Nonlinear Speech Processing, Heraklion, Crete, 20-23 Sep (2005)"},{"key":"7_CR43","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1121\/1.1913303","volume":"52","author":"B.S. Atal","year":"1972","unstructured":"Atal, B.S.: Automatic speaker recognition based on pitch contours. Journal of Acoustical Society of America\u00a052, 1687\u20131697 (1972)","journal-title":"Journal of Acoustical Society of America"},{"key":"7_CR44","first-page":"20","volume":"34","author":"J. Zalewski","year":"1975","unstructured":"Zalewski, J., Maljewski, W., Hollien, H.: Cross correlation between Long-term speech Spectra as a criterion for speaker identification. Acoustica\u00a034, 20\u201324 (1975)","journal-title":"Acoustica"},{"key":"7_CR45","unstructured":"http:\/\/www.zdnet.fr\/telecharger\/windows\/fiche\/0,39021313,11009007s,00.htm"}],"container-title":["Lecture Notes in Computer Science","Progress in Nonlinear Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-71505-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T15:42:59Z","timestamp":1737042179000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-71505-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540715030","9783540715054"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-71505-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007]]}}}