{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T07:15:23Z","timestamp":1794381323542,"version":"4.9.0"},"publisher-location":"Berlin, Heidelberg","reference-count":96,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540274414","type":"print"},{"value":"9783540318866","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11520153_12","type":"book-chapter","created":{"date-parts":[[2010,9,24]],"date-time":"2010-09-24T15:43:03Z","timestamp":1285342983000},"page":"261-290","source":"Crossref","is-referenced-by-count":15,"title":["Text Independent Methods for Speech Segmentation"],"prefix":"10.1007","author":[{"given":"Anna","family":"Esposito","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guido","family":"Aversano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Altosaar, T., Karjalainen, M.: Event-Based Multiple Resolution Analysis of Speech Signals. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, New-York, pp. 327\u2013330 (1988)","DOI":"10.1109\/ICASSP.1988.196582"},{"key":"12_CR2","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/29.1486","volume":"36","author":"R. Andre-Obrecht","year":"1988","unstructured":"Andre-Obrecht, R.: A New Statistical Approach for the Automatic Segmentation of Continuous Speech Signals. IEEE Transactions on Acoustics, Speech Signal Processing\u00a036, 29\u201340 (1988)","journal-title":"IEEE Transactions on Acoustics, Speech Signal Processing"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Atal, B.S.: Efficient Coding of LPC Parameters by Temporal Decomposition. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, pp. 81\u201384 (1983)","DOI":"10.1109\/ICASSP.1983.1172248"},{"key":"12_CR4","unstructured":"Aversano, G.: Phone Level Automatic Speech Segmentation. A Text-Independent Segmentation Algorithm and a Software Tool for Speech Annotation and Analysis. Ph.D. Thesis, Universit\u00e0 di Salerno. Italy (2004)"},{"key":"12_CR5","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/3-540-46154-X_40","volume-title":"Text Speech and Dialogue, 5th International Conference","author":"G. Aversano","year":"2002","unstructured":"Aversano, G., Esposito, A.: Automatic Parameter Estimation for a Context-Independent Speech Segmentation Algorithm. In: Sojka, P., Kopecek, I., Pala, K. (eds.) Text Speech and Dialogue, 5th International Conference. LNCS (LNAI), pp. 293\u2013300. Springer, Heidelberg (2002)"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Aversano, G., Esposito, A., Esposito, A., Marinaro, M.: A New Text-Independent Method for Phoneme Segmentation. In: Ewing, R.L., et al. (eds.) Proceedings of the IEEE International Workshop on Circuits and Systems, vol.\u00a02, pp. 516\u2013519 (2001)","DOI":"10.1109\/MWSCAS.2001.986241"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Backfried, G., Rainoldi, R., Riedler, J.: Automatic Language Identification in Broadcast News. In: Proceedings of International Joint Conference on Neural Networks, vol.\u00a02, pp. 1406\u20131410 (2002)","DOI":"10.1109\/IJCNN.2002.1007722"},{"key":"12_CR8","volume-title":"Detection of Abrupt Changes: Theory and Applications","author":"M. Basseville","year":"1993","unstructured":"Basseville, M., Nikiforov, I.V.: Detection of Abrupt Changes: Theory and Applications. Prentice-Hall, Englewood Cliffs (1993)"},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/0165-1684(89)90079-0","volume":"18","author":"M. Basseville","year":"1989","unstructured":"Basseville, M.: Distance Measures for Signal Processing and Pattern Recognition. Signal Processing\u00a018, 349\u2013369 (1989)","journal-title":"Signal Processing"},{"key":"12_CR10","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/3-540-46154-X_37","volume-title":"Text Speech and Dialogue, 5th International Conference","author":"G. Baudoin","year":"2002","unstructured":"Baudoin, G., Capman, F., Cernocky, J., El Chami, F., Charbit, M., Chollet, G., Petrovska- Delacretaz, D.: Advances in Very Low Bit-rate Speech Coding using Recognition and Synthesis. In: Sojka, P., Kopecek, I., Pala, K. (eds.) Text Speech and Dialogue, 5th International Conference. LNCS (LNAI), pp. 269\u2013276. Springer, Heidelberg (2002)"},{"key":"12_CR11","unstructured":"Beringer, N., Neff, M.: Regional Pronunciation Variants for Automatic Segmentation. In: Proceedings of the 2nd International Conference on Language Resources and Evaluation, Athens, Greece (2000)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Beringer, N., Schiel, F.: The Quality of Multilingual Automatic Segmentation Using German MAUS. In: Proceedings of the 6th Int. Conference on Spoken Language Processing, Beijing, China, pp. 728\u2013731 (2000)","DOI":"10.21437\/ICSLP.2000-915"},{"key":"12_CR13","unstructured":"Beringer, N., Schiel, F.: Independent Automatic Segmentation of Speech by Pronunciation Modeling. In: Proceedings of the 14th Int. Congress of Phonetic Sciences, San Francisco, pp. 1653\u20131656 (1999)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Beulen, K., Ney, H.: Automatic Question Generation for Decision Tree Based State Tying. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 805\u2013808 (1998)","DOI":"10.1109\/ICASSP.1998.675387"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Beulen, K., Bransch, E., Ney, H.: State Tying for Context Dependent Phoneme Models. In: Proceedings of European Conference on Speech Communication and Technology, pp. 1179\u20131182 (1997)","DOI":"10.21437\/Eurospeech.1997-18"},{"key":"12_CR16","unstructured":"Binnenpoorte, D., Goddijn, S., Cucchiarini, C.: How to Improve Human and Machine Transcriptions of Spontaneous Speech. In: ISCA\/IEEE Workshop on Spontaneous Speech Processing and Recognition, Tokyo, pp. 147\u2013150 (2003)"},{"key":"12_CR17","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural Networks for Pattern Recognition","author":"C.M. Bishop","year":"1995","unstructured":"Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)"},{"key":"12_CR18","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/0167-6393(93)90083-W","volume":"12","author":"F. Brugnara","year":"1993","unstructured":"Brugnara, F., Falavigna, D., Omologo, M.: Automatic Segmentation and Labeling of Speech Based on Hidden Markov Models. Speech Communication\u00a012, 357\u2013370 (1993)","journal-title":"Speech Communication"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Brugnara, F., De Mori, A., Giuliani, D., Omologo, M.: Improved Connected Digit Recognition Using Spectral Variation Functions. In: Proceedings of International Conference on Spoken Language Processing, pp. 627\u2013630 (1992)","DOI":"10.21437\/ICSLP.1992-209"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Chang, S., Shastri, L., Greenberg, S.: Automatic Phonetic Transcription of Spontaneous Speech (American English). In: Proceedings of the 6th International Conference on Spoken Language Processing, Beijing, China, pp. 330\u2013333 (2000)","DOI":"10.21437\/ICSLP.2000-817"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Church, K.W.: Speech and Language Processing: Where Have We Been and Where Are We Going? In: Proceedings of the 8th European Conference on Speech Communication and Technology - Eurospeech 2003, Geneva, Switzerland, pp. 1\u20134 (2003)","DOI":"10.21437\/Eurospeech.2003-1"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Daoudi, K., Fohr, D., Antoine, C.: Continuous Multi-Band Speech Recognition using Bayesian Networks. In: Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop, Trento, Italy (2001)","DOI":"10.1109\/ASRU.2001.1034584"},{"key":"12_CR23","volume-title":"Detection of Abrupt Changes in Signals and Dynamical Systems","author":"J. Deshayes","year":"1986","unstructured":"Deshayes, J., Picard, D.: Off-line Statistical Analysis in Change-point Models Using Nonparametric and Likelihood Methods. In: Basseville, M., Beneviste, A. (eds.) Detection of Abrupt Changes in Signals and Dynamical Systems, Springer, New-York (1986)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"du Jeu, C., Charbit, M., Chollet, G.: Very-low-rate Speech Compression by Indexation of Polyphones. In: Proceedings of the 8th European Conference on Speech Communication and Technology - Eurospeech 2003, Geneva, Switzerland, pp. 1085\u20131088 (2003)","DOI":"10.21437\/Eurospeech.2003-358"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Eisen, B., Tillman, H.G.: Consistency of Judgments in Manual Labeling of Phonetic Segments: The Distinction between Clear and Nnclear Cases. In: Proceedings of ICSLP, Banf., Canada, pp. 871\u2013874 (1992)","DOI":"10.21437\/ICSLP.1992-261"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Eisen, B.: Reliability of Speech Segmentation and Labeling at Different Levels of Transcription. In: Proceedings of the 3rd European Conference on Speech Communication and Technology, Eurospeech 1993, Berlin, Germany, pp. 673\u2013676 (1991)","DOI":"10.21437\/Eurospeech.1993-163"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Esposito, A.: The Importance of Data for Training Intelligent Devices. In: Apolloni, B., Kurfess, F. (eds.) From Synapses to Rules: Discovering Symbolic Rules from Neural Processed Data, pp. 229\u2013250. Kluwer Academic\/Plenum Publishers (2002)","DOI":"10.1007\/978-1-4615-0705-5_12"},{"key":"12_CR28","unstructured":"Esposito, A., Pannacci, L., Perfetti, R., Russo, R.C.: Speech Segmentation by Parametric Filtering: Two New Distortion Measures and Experimental Evaluation, Technical Report n. IIASS-1 2000, International Institute for Advanced Scientific Studies, Vietri sul Mare (SA), Italy (2000)"},{"key":"12_CR29","first-page":"7","volume":"AU-2","author":"G. Fairbanks","year":"1954","unstructured":"Fairbanks, G., Everitt, W., Jaeger, R.: Method for Time or Frequency Compression Expansion of Speech. IEEE Transactions on Audio and Electro-acoustics\u00a0AU-2, 7\u201312 (1954)","journal-title":"IEEE Transactions on Audio and Electro-acoustics"},{"key":"12_CR30","unstructured":"Faundez-Zanuy, M., Vallverd\u00f9-Bayes, F.: Speech Segmentation Using Multilevel Hybrid Filters. In: Proceedings of European Signal Processing Conference (EUSIPCO), pp. 1003\u20131006 (1996)"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Finster, H.: Automatic speech segmentation using neural network and phonetic transcription. In: Proceedings of International Conference on Neural Networks, vol.\u00a04, pp. 734\u2013736 (1992)","DOI":"10.1109\/IJCNN.1992.227231"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Flammia, G., Dalsgaard, P., Andersen, O., Lindberg, B.: Segment Based Variable Frame Rate Speech Analysis and Recognition Using Spectral Variation Function. In: Proceedings of International Conference on Spoken Language Processing, pp. 983\u2013986 (1992)","DOI":"10.21437\/ICSLP.1992-306"},{"issue":"10","key":"12_CR33","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1002\/1520-684X(200009)31:10<89::AID-SCJ9>3.0.CO;2-7","volume":"31","author":"C. Furuichi","year":"2000","unstructured":"Furuichi, C., Aizawa, K., Inoue, K.: Speech Recognition Using Stochastic Phonemic Segment Model Based on Phoneme Segmentation. Systems and Computers in Japan\u00a031(10), 1111\u20131119 (2000)","journal-title":"Systems and Computers in Japan"},{"key":"#cr-split#-12_CR34.1","doi-asserted-by":"crossref","unstructured":"Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., Pallett, D. S., Dahlgren, N. L.: The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus. CDROM (1992);","DOI":"10.6028\/NIST.IR.4930"},{"key":"#cr-split#-12_CR34.2","unstructured":"NTIS order number PB91-100354"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Gemello, R., Albesano, D., Mana, F.: CSELT Hybrid HMM\/Neural Networks Technology for Continuous Speech Recognition. In: Proceedings of IEEE-INNS-ENNS International Joint Conference on Neural Networks, vol.\u00a05, pp. 103\u2013108 (2000)","DOI":"10.1109\/IJCNN.2000.861442"},{"key":"12_CR36","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/S0885-2308(03)00006-8","volume":"17","author":"J.R. Glass","year":"2003","unstructured":"Glass, J.R.: A Probabilistic Framework for Segment -Based Speech Recognition. Computer Speech and Language\u00a017, 137\u2013152 (2003)","journal-title":"Computer Speech and Language"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Glass, J.R., Zue, V.W.: Multilevel Acoustic Segmentation of Continuous Speech. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, pp. 429\u2013432 (1988)","DOI":"10.1109\/ICASSP.1988.196610"},{"key":"12_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1007\/3-540-70659-3_70","volume-title":"Structural, Syntactic, and Statistical Pattern Recognition","author":"J.A. G\u00f3mez","year":"2002","unstructured":"G\u00f3mez, J.A., Castro, M.J.: Automatic Segmentation of Speech at the Phonetic Level. In: Caelli, T.M., Amin, A., Duin, R.P.W., Kamel, M.S., de Ridder, D. (eds.) SPR 2002 and SSPR 2002. LNCS, vol.\u00a02396, pp. 672\u2013680. Springer, Heidelberg (2002)"},{"key":"12_CR39","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/TASSP.1980.1163421","volume":"28","author":"R.M. Gray","year":"1980","unstructured":"Gray, R.M., Buzo, A., Gray, A., Matsuyama, Y.: Distortion Measures for Speech Processing. IEEE Transactions on Acoustics, Speech Signal Processing\u00a028, 367\u2013376 (1980)","journal-title":"IEEE Transactions on Acoustics, Speech Signal Processing"},{"key":"12_CR40","volume-title":"Signal Detection Theory and Psychophysics","author":"D. Green","year":"1996","unstructured":"Green, D., Swets, J.: Signal Detection Theory and Psychophysics. John Wiley and Sons, Chichester (1996)"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Greenberg, S.: Strategies for Automatic Multi-Tier Annotation of Spoken Language Corpora. In: Proceedings of the 8th European Conference on Speech Communication and Technology - Eurospeech 2003, Geneva, Switzerland, pp. 45\u201348 (2003)","DOI":"10.21437\/Eurospeech.2003-12"},{"key":"12_CR42","unstructured":"Greenberg, S.: The Switchboard Transcription Project. Technical Report # 24, Center for Language and Speech Processing, Johns Hopkins University, Baltimore USA (1997)"},{"key":"12_CR43","first-page":"115","volume-title":"Speech Processing, Recognition and Artificial Neural Networks, 3rd International School on Neural Nets \u201dEduardo R. Caianiello\u201d","author":"H. Hermansky","year":"1999","unstructured":"Hermansky, H.: Analysis in Automatic Recognition of Speech. In: Chollet, G., Di Benedetto, M., Esposito, A., Marinaro, M. (eds.) Speech Processing, Recognition and Artificial Neural Networks, 3rd International School on Neural Nets \u201dEduardo R. Caianiello\u201d, pp. 115\u2013137. Springer, Heidelberg (1999)"},{"key":"12_CR44","unstructured":"Hermansky, H.: Auditory Modeling in Automatic Recognition of Speech. In: Proceedings of the ESCA Workshop on the Auditory Basis of Speech Perception, Keele, Sweden (1996)"},{"issue":"4","key":"12_CR45","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H. Hermansky","year":"1994","unstructured":"Hermansky, H., Morgan, N.: RASTA Processing of Speech. IEEE Transactions. Speech and Audio Processing\u00a02(4), 578\u2013589 (1994)","journal-title":"IEEE Transactions. Speech and Audio Processing"},{"issue":"4","key":"12_CR46","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H.: Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of Acoustical Society of America\u00a087(4), 1738\u20131752 (1990)","journal-title":"Journal of Acoustical Society of America"},{"key":"12_CR47","first-page":"331","volume-title":"Improvements in Speech Synthesis","author":"P. Horak","year":"2001","unstructured":"Horak, P.: Automatic Speech Segmentation Based on DTW with the Application of the Czech TTS System. In: Keller, E., Bailly, G., Monaghan, A., Terken, J., Huckwale, M. (eds.) Improvements in Speech Synthesis, pp. 331\u2013340. John Wiley and Sons Ltd., Chichester (2001)"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Jankowski, C., Kalyanswamy, A., Basson, S., Spitz, J.: NTIMIT: A Phonetically Balanced, Continuous Speech, Telephone Bandwidth Speech Database. In: Proceedings of ICASSP, pp. 109\u2013112 (1990)","DOI":"10.1109\/ICASSP.1990.115550"},{"key":"12_CR49","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S0167-6393(96)00064-7","volume":"20","author":"C.G. Jeong","year":"1997","unstructured":"Jeong, C.G., Jeong, H.: Automatic Phone Segmentation and Labeling of Continuous Speech. Speech Communication\u00a020, 291\u2013311 (1997)","journal-title":"Speech Communication"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Kanthak, S., Ney, H.: Multilingual Acoustic Modeling Using Graphemes. In: Proceedings of European Conference on Speech Communication and Technology, vol.\u00a02, pp. 1145\u20131148 (2003)","DOI":"10.21437\/Eurospeech.2003-373"},{"issue":"6","key":"12_CR51","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1023\/A:1024145801240","volume":"64","author":"A.S. Kolokolov","year":"2003","unstructured":"Kolokolov, A.S.: Preprocessing and Segmentation of the Speech Signal in the Frequency Domain for Speech Recognition. Automation and Remote Control\u00a064(6), 985\u2013994 (2003)","journal-title":"Automation and Remote Control"},{"key":"12_CR52","volume-title":"Applications of Digital Signal Processing to Audio and Acoustics","author":"J. Laroche","year":"1998","unstructured":"Laroche, J.: Time and Pitch Scale Modification of Audio Signals. In: Kahrs, M., Brandenburg, K. (eds.) Applications of Digital Signal Processing to Audio and Acoustics, Kluwer Academic Publishers, Dordrecht (1998)"},{"key":"12_CR53","unstructured":"Laureys, T., Demuynck, K., Duchateau, J., Wambacq, P.: An Improved Algorithm for the Automatic Segmentation of Speech Corpora. In: Gonz\u00e1lez Rodriguez, M., Paz Su\u00e1rez Araujo, C. (eds.) Proceedings of Third International Conference on Language Resources and Evaluation, pp. 1564\u20131567 (2002)"},{"key":"12_CR54","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1109\/78.193214","volume":"41","author":"M. Lavielle","year":"1993","unstructured":"Lavielle, M.: Detection of Changes in the Spectrum of Multidimensional Process. IEEE Transactions on Signal Processing\u00a041, 742\u2013749 (1993)","journal-title":"IEEE Transactions on Signal Processing"},{"key":"12_CR55","doi-asserted-by":"crossref","unstructured":"Le Cerf, P., Demuynck, K., Duchateau, J., Van Compernolle, D.: Pseudo-Segment Based Speech Recognition Using Neural Recurrent Whole-Word Recognizers. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, vol.\u00a01, pp. 609\u2013612 (1994)","DOI":"10.1109\/ICASSP.1994.389220"},{"key":"12_CR56","unstructured":"Li, B.N.L., Liu, J.N.K.: A Comparative Study of Speech Segmentation for Automatic Multi-Lingual Recognition. In: Proceedings of Second ACM Hong Kong Postgraduate Research Conference (1999), http:\/\/www.cse.cuhk.edu.hk\/~acm-hk\/activity\/pg\/polyu-nlli.pdf"},{"issue":"3","key":"12_CR57","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/89.496216","volume":"4","author":"T.H. Li","year":"1996","unstructured":"Li, T.H., Gibson, J.D.: Speech Analysis and Segmentation by Parametric Filtering. IEEE Transactions on Speech and Audio Processing, Vol\u00a04(3), 203\u2013213 (1996)","journal-title":"IEEE Transactions on Speech and Audio Processing, Vol"},{"key":"12_CR58","unstructured":"Li, T.H., Gibson, J.D.: Time-Correlation Analysis of Non-stationary Signals with Application to Speech Processing. In: Proceedings of International Symposium on Time- Frequency &Time-Scale Analysis, Paris, France, pp. 449\u2013452 (1996)"},{"key":"12_CR59","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1006\/csla.1999.0121","volume":"23","author":"M.-T. Lin","year":"1999","unstructured":"Lin, M.-T., Lee, C.-K., Lin, C.-Y.: Consonant\/Vowel Segmentation for Mandarin Syllable Recognition. Computer Speech and Language\u00a023, 207\u2013222 (1999)","journal-title":"Computer Speech and Language"},{"issue":"4","key":"12_CR60","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/S0167-6393(02)00131-0","volume":"40","author":"F. Malfr\u00e8re","year":"2003","unstructured":"Malfr\u00e8re, F., Deroo, O., Dutoit, T., Ris, C.: Phonetic Alignment: Speech Synthesis-Based vs. Viterbi-Based. Speech Communication\u00a040(4), 503\u2013515 (2003)","journal-title":"Viterbi-Based. Speech Communication"},{"issue":"5","key":"12_CR61","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/TASSP.1975.1162685","volume":"23","author":"J. Makhoul","year":"1975","unstructured":"Makhoul, J.: Spectral Linear Prediction: Properties and Applications. IEEE Transactions ASSP\u00a023(5), 283\u2013296 (1975)","journal-title":"IEEE Transactions ASSP"},{"key":"12_CR62","unstructured":"Mirghafori, N.: A Multi-Band Approach to Automatic Speech Recognition. Ph.D. thesis, University of California, Berkeley (December 1988), ch. 4. Reprinted as ICSI Technical Report, TR-99-04, Berkeley, CA (1999)"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Mitchell, C.D., Harper, M.P., Jamieson, L.H.: Using Explicit Segmentation to Improve HMM Phone Recognition. In: Proceedings of International Conference on Acoustic, Speech and Signal Processing, pp. 229\u2013232 (I995)","DOI":"10.1109\/ICASSP.1995.479406"},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"Park, E.-Y., Kim, S.-H., Chung, J.-H.: Automatic Speech Synthesis Unit Generation with MLP Based Postprocessor against Auto-segmented Phoneme Errors. In: Proceedings of International Joint Conference on Neural Networks, vol.\u00a05, pp. 2985\u20132990 (1999)","DOI":"10.1109\/IJCNN.1999.835996"},{"key":"12_CR65","volume-title":"Voice and Speech Processing","author":"T. Parson","year":"1986","unstructured":"Parson, T.: Voice and Speech Processing. McGraw-Hill, New York (1986)"},{"key":"12_CR66","series-title":"The IMA Volumes in Mathematics and its Applications. Series","volume-title":"New Directions in Time Series Analysis, Part I","author":"E. Parzen","year":"1992","unstructured":"Parzen, E.: Time Series, Statistics and Information. In: Brillinger, D., Caines, P., Geweke, J., Parzen, E., Rosenblatt, M., Taqqu, M.S. (eds.) New Directions in Time Series Analysis, Part I. The IMA Volumes in Mathematics and its Applications. Series, vol.\u00a045, Springer, New York (1992)"},{"key":"12_CR67","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/S0167-6393(98)00031-4","volume":"25","author":"B.L. Pellom","year":"1998","unstructured":"Pellom, B.L., Hansen, J.H.L.: Automatic Segmentation of Speech Recorded in UnknownNoisy Channel Characteristics. Speech Communication\u00a025, 97\u2013116 (1998)","journal-title":"Speech Communication"},{"key":"12_CR68","doi-asserted-by":"crossref","unstructured":"Petek, B., Andersen, O., Dalsgaard, P.: On the Robust Automatic Segmentation of Spontaneous Speech. In: Proceedings of International Conference on Spoken Language Processing, pp. 913\u2013916 (1996)","DOI":"10.1109\/ICSLP.1996.607750"},{"issue":"4","key":"12_CR69","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1109\/TIT.1954.1057460","volume":"4","author":"W. Peterson","year":"1954","unstructured":"Peterson, W., Birdsall, T., Fox, W.: The Theory of Signal Detectability. IEEE Transactions on Information Theory\u00a04(4), 171\u2013212 (1954)","journal-title":"IEEE Transactions on Information Theory"},{"key":"12_CR70","doi-asserted-by":"crossref","unstructured":"Picone, J.: Continuous Speech Recognition Using Hidden Markov Models. IEEE ASSP Magazine, 26\u201341 (1990)","DOI":"10.1109\/53.54527"},{"key":"12_CR71","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.specom.2003.12.002","volume":"42","author":"V.K. Prasad","year":"2004","unstructured":"Prasad, V.K., Nagarajan, T., Mutrhy, H.A.: Automatic Segmentation of Continuous Speech Using Phase Group Delay Functions. Speech Communication\u00a042, 429\u2013446 (2004)","journal-title":"Speech Communication"},{"key":"12_CR72","volume-title":"Objective Measures of Speech Quality","author":"S.R. Quackenbush","year":"1988","unstructured":"Quackenbush, S.R., Barnwell, T.P., Clements, M.A.: Objective Measures of Speech Quality. Prentice Hall, Englewood Cliffs (1988)"},{"key":"12_CR73","volume-title":"Fundamentals of Speech Recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice-Hall, Inc., Upper Saddle River (1993)"},{"key":"12_CR74","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R., Juang, B.H.: An Introduction to Hidden Markov Models. IEEE ASSP Magazine, 4\u201316 (1986)","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"12_CR75","doi-asserted-by":"crossref","unstructured":"Raymond, W.D., et al.: An Analysis of Transcription Consistency in Spontaneous Speech from the Buckeye Corpus. In: Proceedings of ICSLP 2002, Denver, USA (2002)","DOI":"10.21437\/ICSLP.2002-371"},{"key":"12_CR76","unstructured":"Schiel, F.: Automatic Phonetic Transcription of Non-Prompted Speech. In: Proceedings of the 14th International Congress on Phonetic Sciences, San Francisco, pp. 607\u2013610 (1999)"},{"key":"12_CR77","doi-asserted-by":"crossref","unstructured":"Schillo, C., Fink, G.A., Kummert, F.: Grapheme Based Recognition for Large Vocabularies. In: Procceedings of International Conference on Spoken Processing, pp. 129\u2013132 (2000)","DOI":"10.21437\/ICSLP.2000-879"},{"key":"12_CR78","doi-asserted-by":"crossref","unstructured":"Sharma, M., Mammone, R.: Automatic Speech Segmentation Using Neural Tree Networks. In: Proceedings of IEEE Workshop on Neural Networks for Signal Processing, pp. 282\u2013290 (1995)","DOI":"10.1109\/NNSP.1995.514902"},{"key":"12_CR79","unstructured":"Segura-Luna, J.C., Soler, J.M., Peinado, A.M., Sanchez, V., Rubio, A.: Signal Segmentation into Spectral Homogeneous Units. In: Proceedings of European Signal Processing Conference, pp. 1251\u20131254 (1990)"},{"key":"12_CR80","doi-asserted-by":"crossref","unstructured":"Silverman, H.F., Morgan, D.P.: The Application of Dynamic Programming to Connected Speech Recognition. IEEE ASSP Magazine, 6\u201325 (1990)","DOI":"10.1109\/53.54526"},{"issue":"3","key":"12_CR81","doi-asserted-by":"publisher","first-page":"329","DOI":"10.2307\/1417526","volume":"53","author":"S.S. Stephens","year":"1940","unstructured":"Stephens, S.S., Volkman, J.: The Relation of Pitch to Frequency. American Journal of Psychology\u00a053(3), 329\u2013353 (1940)","journal-title":"American Journal of Psychology"},{"key":"12_CR82","doi-asserted-by":"crossref","unstructured":"Suontasuta, J., Hakkinen, J.: Decision Tree Based Text-to-Mapping for Speech Recognition. In: Procceedings of International Conference on Spoken Processing, pp. 199\u2013202 (2000)","DOI":"10.21437\/ICSLP.2000-398"},{"key":"12_CR83","doi-asserted-by":"crossref","unstructured":"Svendsen, T., Soong, F.K.: On Automatic Segmentation of Speech Signals. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, Dallas, pp. 77\u201380 (1987)","DOI":"10.1109\/ICASSP.1987.1169628"},{"key":"12_CR84","doi-asserted-by":"crossref","unstructured":"Torkolla, K.: An Efficient Way to Learn English Grapheme-to-Phoneme Rules Automatically. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, vol.\u00a02, pp. 199\u2013202 (1993)","DOI":"10.1109\/ICASSP.1993.319268"},{"issue":"4","key":"12_CR85","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1109\/78.80941","volume":"39","author":"J.P. Hemert van","year":"1991","unstructured":"van Hemert, J.P.: Automatic Segmentation of Speech. IEEE Transactions on Signal Processing\u00a039(4), 1008\u20131012 (1991)","journal-title":"IEEE Transactions on Signal Processing"},{"key":"12_CR86","first-page":"43","volume-title":"Signal Processing V: Theories and Applications","author":"E. Vidal","year":"1990","unstructured":"Vidal, E., Marzal, A.: A Review and New Approaches for Automatic Segmentation of Continuous Speech Signals. In: Torress, L., et al. (eds.) Signal Processing V: Theories and Applications, pp. 43\u201353. Elsevier Publisher, New-York (1990)"},{"issue":"4","key":"12_CR87","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/S0167-6393(96)00037-4","volume":"19","author":"A. Vorstermans","year":"1996","unstructured":"Vorstermans, A., Martens, J.P., Van Coile, B.: Automatic Segmentation and Labeling of Multi-lingual Speech Data. Speech Communication\u00a019(4), 271\u2013293 (1996)","journal-title":"Speech Communication"},{"issue":"4","key":"12_CR88","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/LSP.2003.808550","volume":"10","author":"B. Wei","year":"2003","unstructured":"Wei, B., Gibson, J.D.: A New Discrete Spectral Modeling Method and an Application to CELP Coding. IEEE Signals Processing Letters\u00a010(4), 101\u2013103 (2003)","journal-title":"IEEE Signals Processing Letters"},{"key":"12_CR89","unstructured":"Wei, B., Gibson, J.D.: Comparison of Distance Measure in Discrete Spectral Modeling. In: Proceedings of IEEE Digital Signal Processing Workshop, pp. 1\u20134 (2000)"},{"key":"12_CR90","doi-asserted-by":"crossref","unstructured":"Wendt, C., Petropulu, A.P.: Pitch Determination and Speech Segmentation Using the Discrete Wavelet Transform. In: Proccedings of IEEE International Symposium on Circuits and Systems, vol.\u00a02, pp. 45\u201348 (1996)","DOI":"10.1109\/ISCAS.1996.540348"},{"key":"12_CR91","doi-asserted-by":"crossref","unstructured":"Wesenick, M.B., Kipp, A.: Estimating the Quality of Phonetic Transcriptions and Segmentations of Speech Signals. In: Proceedings of ICSLP 1996, Philadelphia, USA, pp. 129\u2013132 (1996)","DOI":"10.1109\/ICSLP.1996.607054"},{"key":"12_CR92","unstructured":"Wester, M., Kessens, J.M., Cucchiarini, C., Strik, H.: Comparison between Expert Listeners and Continuous Speech Recognizers in Selecting Pronunciation Variants. In: Proceedings of the 14th Int. Congress of Phonetic Sciences, San Francisco, pp. 723\u2013726 (1999)"},{"key":"12_CR93","unstructured":"Wokurek, W.: Corpus Based Evaluation of Entropy Rate Speech Segmentation. In: Proceedings of 14th International Congress of Phonetic Sciences, pp. 1217\u20131220 (1999)"},{"key":"12_CR94","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1006\/csla.1994.1019","volume":"8","author":"S.J. Young","year":"1994","unstructured":"Young, S.J., Woodland, P.C.: State Clustering in Hidden Markov Model-Based Continuous Speech Recognition. Computer Speech and Language\u00a08, 369\u2013383 (1994)","journal-title":"Computer Speech and Language"},{"key":"12_CR95","doi-asserted-by":"crossref","unstructured":"Zue, V.W., Glass, J.R., Philips, M., Seneff, S.: Acoustic Segmentation and Phonetic Classification in the Summit System. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, pp. 389\u2013392 (1989)","DOI":"10.1109\/ICASSP.1989.266447"}],"container-title":["Lecture Notes in Computer Science","Nonlinear Speech Modeling and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11520153_12.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T20:49:27Z","timestamp":1740516567000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11520153_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540274414","9783540318866"],"references-count":96,"URL":"https:\/\/doi.org\/10.1007\/11520153_12","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/b138975","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005]]}}}