{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T06:10:09Z","timestamp":1736662209294,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":35,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540496656"},{"type":"electronic","value":"9783540496663"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11939993_60","type":"book-chapter","created":{"date-parts":[[2006,11,28]],"date-time":"2006-11-28T06:20:13Z","timestamp":1164694813000},"page":"578-589","source":"Crossref","is-referenced-by-count":0,"title":["Contextual Maximum Entropy Model for Edit Disfluency Detection of Spontaneous Speech"],"prefix":"10.1007","author":[{"given":"Jui-Feng","family":"Yeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Yen","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"60_CR1","doi-asserted-by":"crossref","unstructured":"Nakatani, C., Hirschberg, J.: A speech-first model for repair detection and correction. In: Proceedings of the 31 Annual Meeting of the Association for Computational Linguistics, pp. 46\u201353 (1993)","DOI":"10.3115\/981574.981581"},{"key":"60_CR2","unstructured":"Coquoz, S.: Broadcast News segmentation using MDE and STT Information to Improve Speech Recognition. International Computer Science Instute, Tech. Report (2004)"},{"key":"60_CR3","unstructured":"Gregory, M., Johnson, M., Charniak, E.: Sentence-internal prosody does not help parsing the way punctuation does not Help Parsing the Way Punctuation Does. In: Proc. NAACL, pp. 81\u201388 (2004)"},{"key":"60_CR4","doi-asserted-by":"crossref","unstructured":"Kahn, J.G., Ostendorf, M., Chelba, C.: Parsing Conversational Speech Using Enhanced Segmentation. In: Proc. HLT-NAACL, pp. 125\u2013128 (2004)","DOI":"10.3115\/1613984.1614016"},{"issue":"3","key":"60_CR5","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1109\/TSA.2005.845820","volume":"13","author":"C.-H. Wu","year":"2005","unstructured":"Wu, C.-H., Yan, G.-L.: Speech Act Modeling and Verification of Spontaneous Speech With Disfluency in a Spoken Dialogue System. IEEE Transaction on Speech and Acoustic Processing\u00a013(3), 330\u2013344 (2005)","journal-title":"IEEE Transaction on Speech and Acoustic Processing"},{"issue":"5","key":"60_CR6","first-page":"1574","volume":"18","author":"J.-F. Yeh","year":"2006","unstructured":"Yeh, J.-F., Wu, C.-H.: Edit Disfluency Detection and Correction Using a Cleanup Language Model and an Alignment Model. IEEE Transactions on Audio, Speech, and Language Processing\u00a018(5), 1574\u20131583 (2006)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1-2","key":"60_CR7","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/S0167-6393(00)00028-5","volume":"32","author":"E. Shriberg","year":"2000","unstructured":"Shriberg, E., Stolcke, A., Hakkani-Tur, D., Tur, G.: Prosody-based automatic segmentation of speech into sentences and topics. Speech Communication\u00a032(1-2), 127\u2013154 (2000)","journal-title":"Speech Communication"},{"key":"60_CR8","doi-asserted-by":"crossref","unstructured":"Bear, J., Dowding, J., Shriberg, E.: Integrating multiple knowledge sources for detecting and correction of repairs in human computer dialog. In: Proc. of ACL, pp. 56\u201363 (1992)","DOI":"10.3115\/981967.981975"},{"key":"60_CR9","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.specom.2005.02.018","volume":"46","author":"E. Shriberg","year":"2005","unstructured":"Shriberg, E., Ferrer, L., Kajarekar, S., Venkataraman, A., Stolcke, A.: Modeling prosodic feature sequences for speaker recognition. Speech Communication\u00a046, 455\u2013472 (2005)","journal-title":"Speech Communication"},{"key":"60_CR10","unstructured":"Savova, G., Bachenko, J.: Prosodic features of four types of disfluencies. In: Proc. of DiSS 2003, pp. 91\u201394 (2003)"},{"key":"60_CR11","unstructured":"Soltau, H., Kingsbury, B., Mangu, L., Povey, D., Saon, G., Zweig, D.: The IBM 2004 Conversational Telephony System for Rich Transcription. In: Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005 (ICASSP 2005), pp. 205\u2013208 (2005)"},{"key":"60_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Schwarm, S.E., Ostendorf, M.: Detecting structural metadata with decision trees and transformation-based learning. In: Proceedings of HLT\/NAACL 2004, pp. 137\u2013144 (2004)","DOI":"10.21236\/ADA457891"},{"key":"60_CR13","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.specom.2005.02.010","volume":"47","author":"S. Furui","year":"2005","unstructured":"Furui, S., Nakamura, M., Ichiba, T., Iwano, K.: Analysis and recognition of spontaneous speech using Corpus of Spontaneous Japanese. Speech Communication\u00a047, 208\u2013219 (2005)","journal-title":"Speech Communication"},{"key":"60_CR14","doi-asserted-by":"crossref","unstructured":"Charniak, E., Johnson, M.: Edit detection and parsing for transcribed speech. In: Proc. of NAACL 2001, vol.\u00a02001, pp. 118\u2013126 (2001)","DOI":"10.3115\/1073336.1073352"},{"key":"60_CR15","doi-asserted-by":"crossref","unstructured":"Johnson, M., Charniak, E.: A TAG-based noisy channel model of speech repairs. In: Proc. of ACL 2004, pp. 33\u201339 (2004)","DOI":"10.3115\/1218955.1218960"},{"key":"60_CR16","doi-asserted-by":"crossref","unstructured":"Lease, M., Charniak, E., Johnson, M.: Parsing and its applications for conversational speech. In: Proc. of ICASSP 2005 (2005)","DOI":"10.1109\/ICASSP.2005.1416465"},{"key":"60_CR17","doi-asserted-by":"crossref","unstructured":"Honal, M., Schultz, T.: Automatic Disfluency Removal on Recognized Spontaneous Speech - Rapid Adaptation to Speaker Dependent Disfluencies. In: Proceedings of ICASSP 2005, pp. 969\u2013972 (2005)","DOI":"10.1109\/ICASSP.2005.1415277"},{"key":"60_CR18","first-page":"527","volume":"25","author":"P.A. Heeman","year":"1999","unstructured":"Heeman, P.A., Allen, J.: Speech repairs, intonational phrases and discourse markers: Modeling speakers\u2019 utterances in spoken dialogue. Computational Linguistics\u00a025, 527\u2013571 (1999)","journal-title":"Computational Linguistics"},{"key":"60_CR19","doi-asserted-by":"crossref","unstructured":"Heeman, P.A., Loken-Kim, K., Allen, J.: Combining the detection and correction of speech repairs. In: Proceedings of the 4th International Conference on Spoken Language Processing (ICSLP-1996), pp. 358\u2013361 (1996)","DOI":"10.1109\/ICSLP.1996.607129"},{"key":"60_CR20","doi-asserted-by":"crossref","unstructured":"Honal, M., Schultz, T.: Automatic disfluency removal on recognized spontaneous speech - rapid adaptation to speaker dependent dislfuencies. In: Proc. of ICASSP 2005, pp. 969\u2013972 (2005)","DOI":"10.1109\/ICASSP.2005.1415277"},{"key":"60_CR21","unstructured":"Honal, M., Schultz, T.: Corrections of disfluencies in spontaneous speech using a noisy-channel approach. In: Proc. of Eurospeech, 2003, pp. 2781\u20132784 (2003)"},{"key":"60_CR22","doi-asserted-by":"crossref","unstructured":"Snover, M., Dorr, B., Schwartz, R.: A lexically-driven algorithm for disfluency detection. In: Proc. of HLT\/NAACL 2004, pp. 157\u2013160 (2004)","DOI":"10.3115\/1613984.1614024"},{"key":"60_CR23","unstructured":"Hain, T., Woodland, P.C., Evermann, G., Gales, M.J.F., Liu, X., Moore, G.L., Povey, D., Wang, L.: Automatic Transcription of Conversational Telephone Speech. IEEE Transactions on Speech and Audio Processing (accepted for future publication)"},{"key":"60_CR24","unstructured":"Soltau, H., Yu, H., Metze, F., Fugen, C., Qin, J., Jou, S.-C.: The 2003 ISL rich transcription system for conversational telephony speech. In: Proceedings of Acoustics, Speech, and Signal Processing 2004 (ICASSP), pp. 17\u201321 (2004)"},{"key":"60_CR25","unstructured":"Harper, M., Dorr, B.J., Hale, J., Roark, B., Shafran, I., Lease, M., Liu, Y., Snover, M., Yung, L., Krasnyanskaya, A., Stewart, R.: Final Report on Parsing and Spoken Structural Event Detection. In: Johns Hopkins Summer Workshop (2005)"},{"key":"60_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Stolcke, A., Shriberg, E., Harper, M.: Using Conditional Random Fields for Sentence Boundary Detection in Speech. In: Proceedings of the 43nd Annual Meeting of the Association for Computational Linguistics: ACL 2005 (2005)","DOI":"10.3115\/1219840.1219896"},{"key":"60_CR27","doi-asserted-by":"crossref","unstructured":"Huang, J., Zweig, G.: Maximum Entropy Model for Punctuation Annotation from Speech. In: Proceedings of ICSLP 2002, pp. 917\u2013920 (2002)","DOI":"10.21437\/ICSLP.2002-307"},{"key":"60_CR28","unstructured":"Liu, Y., Shriberg, E., Stolcke, A., Harper, M.: Comparing HMM, Maximum Entropy, and Conditional Random Fields for Disfluency Detection. In: Proc. of Eurospeech, 2005, pp. 3313\u20133316 (2005)"},{"key":"60_CR29","first-page":"39","volume":"22","author":"A.L. Berger","year":"1996","unstructured":"Berger, A.L., Pietra, S.A.D., Pietra, V.J.D.: A maximum entropy approach to natural language processing. Computational Linguistics\u00a022, 39\u201372 (1996)","journal-title":"Computational Linguistics"},{"key":"60_CR30","unstructured":"Chinese Knowledge Information Processing Group (CKIP): Technical Report 93-05: Chinese Part-of-speech Analysis. Academia Sinica, Taipei (1993)"},{"key":"60_CR31","unstructured":"Tseng, S.-C., Liu, Y.-F.: Annotation of Mandarin Conversational Dialogue Corpus. CKIP Technical Report no. 02-01.\u201d Academia Sinica (2002)"},{"key":"60_CR32","first-page":"87","volume":"36","author":"C.-H. Wu","year":"2004","unstructured":"Wu, C.-H., Yan, G.-L.: Acoustic Feature Analysis and Discriminative Modeling of Filled Pauses for Spontaneous Speech Recognition. Journal of VLSI Signal Processing- Systems for Signal, Image, and Video Technology\u00a036, 87\u201399 (2004)","journal-title":"Journal of VLSI Signal Processing- Systems for Signal, Image, and Video Technology"},{"key":"60_CR33","volume-title":"The HTK Book","author":"S.J. Young","year":"2003","unstructured":"Young, S.J., Evermann, G., Hain, T., Kershaw, D., Moore, G.L., Odell, J.J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.C.: The HTK Book. Cambridge Univ. Press, Cambridge (2003)"},{"key":"60_CR34","unstructured":"MAT Speech Database \u2013 TCC-300, http:\/\/rocling.iis.sinica.edu.tw\/ROCLING\/MAT\/Tcc_300brief.htm"},{"key":"60_CR35","doi-asserted-by":"crossref","unstructured":"Stolcke, A., Shriberg, E.: Statistical Language Modeling for Speech Disfluencies. In: Proceedings of ICASSP-1996, pp. 405\u2013408 (1996)","DOI":"10.1109\/ICASSP.1996.541118"}],"container-title":["Lecture Notes in Computer Science","Chinese Spoken Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11939993_60.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T05:04:02Z","timestamp":1736658242000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11939993_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540496656","9783540496663"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/11939993_60","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}