{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:05:49Z","timestamp":1725516349764},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540685845"},{"type":"electronic","value":"9783540685852"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-68585-2_43","type":"book-chapter","created":{"date-parts":[[2008,8,12]],"date-time":"2008-08-12T16:07:43Z","timestamp":1218557263000},"page":"464-474","source":"Crossref","is-referenced-by-count":5,"title":["The ISL RT-07 Speech-to-Text System"],"prefix":"10.1007","author":[{"given":"Matthias","family":"W\u00f6lfel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"St\u00fcker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Kraft","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"F\u00fcgen, C., W\u00f6lfel, M., McDonough, J.W., Ikbal, S., Kraft, F., Laskowski, K., Ostendorf, M., St\u00fcker, S., Kumatani, K.: Advances in lecture recognition: The ISL RT-06S evaluation System. In: Proc. of Interspeech (2006)","DOI":"10.21437\/Interspeech.2006-370"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"W\u00f6lfel, M., F\u00fcgen, C., Ikbal, S., McDonough, J.W.: Multi-source far-distance microphone selection and combination for automatic transcription of lectures. In: Proc. of Interspeech (2006)","DOI":"10.21437\/Interspeech.2006-122"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"W\u00f6lfel, M., McDonough, J.: Combining multi-source far distance speech recognition strategies: Beamforming, blind channel and confusion network combination. In: Proc. of Interspeech (2005)","DOI":"10.21437\/Interspeech.2005-270"},{"key":"43_CR4","unstructured":"Metze, F., Jin, Q., F\u00fcgen, C., Laskowski, K., Pan, Y., Schultz, T.: Issues in meeting transcription \u2013 The ISL meeting transcription system. In: Proc. of ICSLP (2004)"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"St\u00fcker, S., F\u00fcgen, C., Kraft, F., W\u00f6lfel, M.: The ISL 2007 english speech transcription system for european parliament speeches. In: Proc. of Interspeech (2007)","DOI":"10.21437\/Interspeech.2007-588"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"W\u00f6lfel, M., McDonough, J.: Minimum variance distortionless response spectral estimation: Review and refinements. IEEE Signal Processing Magazine (September 2005)","DOI":"10.1109\/MSP.2005.1511829"},{"key":"43_CR7","unstructured":"W\u00f6lfel, M.: Warped-twice minimum variance distortionless response spectral estimation. In: Proc. of EUSIPCO (2006)"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"St\u00fcker, S., F\u00fcgen, C., Burger, S., W\u00f6lfel, M.: Cross-system adaptation and combination for continuous speech recognition: The influence of phoneme set and acoustic front-end. In: Proc. of Interspeech (2006)","DOI":"10.21437\/Interspeech.2006-199"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"W\u00f6lfel, M.: Channel selection by class separability measures for automatic transcriptions on distant microphones. In: Proc. of Interspeech (2007)","DOI":"10.21437\/Interspeech.2007-255"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Povey, D., Woodland, P.: Improved discriminative training techniques for large vocabulary continuous speech recognition. In: Proc. of ICASSP, Salt Lake City, UT, USA (May 2001)","DOI":"10.1109\/ICASSP.2001.940763"},{"key":"43_CR11","unstructured":"Zhan, P., Westphal, M.: Speaker normalization based on frequency warping. In: Proc. of ICASSP (1997)"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Boakye, K., Stolcke, A.: Improved speech activity detection using cross-channel features for recognition of multiparty meetings. In: Proc. of Interspeech (2006)","DOI":"10.21437\/Interspeech.2006-538"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Jin, Q., Schultz, T.: Speaker segmentation and clustering in meetings. In: Proc. of ICSLP (2004)","DOI":"10.21437\/Interspeech.2004-249"},{"key":"43_CR14","unstructured":"Soltau, H., Metze, F., F\u00fcgen, C., Waibel, A.: A one pass-decoder based on polymorphic linguistic context assignment. In: Proc. of ASRU (2001)"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Gales, M.J.F.: Semi-tied covariance matrices. In: Proc. of ICASSP (1998)","DOI":"10.1109\/ICASSP.1998.675350"},{"key":"43_CR16","unstructured":"Gales, M.J.F.: Adaptive training schemes for robust asr. In: Proc. of ASRU"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"McDonough, J., Schaaf, T., Waibel, A.: On maximum mutual information speaker-adapted training. In: Proc. of ICASSP (2002)","DOI":"10.1109\/ICASSP.2002.5743789"},{"key":"43_CR18","unstructured":"Scripts for web data collection provided by University of Washington, http:\/\/ssli.ee.washington.edu\/projects\/ears\/WebData\/web_data_collection.html"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM \u2013 an extensible language modeling toolkit. In: Proc. of ICSLP (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"43_CR20","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language Modeling, Computer Science Group, Harvard University, Tech. Rep. TR-10-98, (1998)"},{"key":"43_CR21","unstructured":"Black, A.W., Taylor, P.A.: The festival speech synthesis system: System documentation, Human Communciation Research Centre, University of Edinburgh, Edinburgh, Scotland, United Kongdom, Tech. Rep. HCRC\/TR-83 (1997)"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Fisher, W.M.: A statistical text-to-phone function using n-grams and rules. In: Proc. of ICASSP (1999)","DOI":"10.1109\/ICASSP.1999.759750"},{"key":"43_CR23","unstructured":"Yu, H., Tam, Y.-C., Schaaf, T., St\u00fcker, S., Jin, Q., Noamany, M., Schultz, T.: The ISL RT04 mandarin broadcast news evaluation system. In: Proc. of EARS Rich Transcription Workshop (2004)"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Lamel, L., Gauvain, J.-L.: Alternate phone models for conversational speech. In: Proc. of ICASSP (2005)","DOI":"10.1109\/ICASSP.2005.1415286"},{"key":"43_CR25","unstructured":"St\u00fcker, S., F\u00fcgen, C., Hsiao, R., Ikbal, S., Jin, Q., Kraft, F., Paulik, M., Raab, M.W.M., Tam, Y.-C.: The ISL TC-STAR spring 2006 ASR evaluation systems. In: Proc. of TC-Star Workshop on Speech-to-Speech Translation (2006)"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Mangu, L., Brill, E., Stolcke, A.: Finding consensus among words: Lattice-based word error minimization. In: Proc. of EUROSPEECH (1999)","DOI":"10.21437\/Eurospeech.1999-127"},{"key":"43_CR27","unstructured":"CHIL \u2013 computers in the human interaction loop, http:\/\/chil.server.de"}],"container-title":["Lecture Notes in Computer Science","Multimodal Technologies for Perception of Humans"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-68585-2_43.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T14:42:57Z","timestamp":1684507377000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-68585-2_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540685845","9783540685852"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-68585-2_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}