{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T04:10:26Z","timestamp":1748664626714,"version":"3.41.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319240329"},{"type":"electronic","value":"9783319240336"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-24033-6_54","type":"book-chapter","created":{"date-parts":[[2015,9,18]],"date-time":"2015-09-18T15:11:04Z","timestamp":1442589064000},"page":"480-488","source":"Crossref","is-referenced-by-count":15,"title":["Open Source German Distant Speech Recognition: Corpus and Acoustic Model"],"prefix":"10.1007","author":[{"given":"Stephan","family":"Radeck-Arneth","sequence":"first","affiliation":[]},{"given":"Benjamin","family":"Milde","sequence":"additional","affiliation":[]},{"given":"Arvid","family":"Lange","sequence":"additional","affiliation":[]},{"given":"Evandro","family":"Gouv\u00eaa","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Radomski","sequence":"additional","affiliation":[]},{"given":"Max","family":"M\u00fchlh\u00e4user","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Biemann","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,12,11]]},"reference":[{"unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: Proc. IEEE ASRU, pp. 1\u20134 (2011)","key":"54_CR1"},{"unstructured":"Huggins-Daines, D., Kumar, M., Chan, A., Black, A.W., Ravishankar, M., Rudnicky, A.I.: PocketSphinx: a free, real-time continuous speech recognition system for hand-held devices. In: Proc. ICASSP (2006)","key":"54_CR2"},{"unstructured":"Schiel, F., Steininger, S., T\u00fcrk, U.: The smartkom multimodal corpus at BAS. In: Proc. LREC (2002)","key":"54_CR3"},{"unstructured":"Wahlster, W.: Verbmobil: translation of face-to-face dialogs. In: Proc. 4th Machine Translation Summit, pp. 128\u2013135 (1993)","key":"54_CR4"},{"doi-asserted-by":"crossref","unstructured":"Hess, W.J., Kohler, K.J., Tillmann, H.G.: The Phondat-verbmobil speech corpus. In: Proc. EUROSPEECH (1995)","key":"54_CR5","DOI":"10.21437\/Eurospeech.1995-197"},{"unstructured":"Brinckmann, C., Kleiner, S., Kn\u00f6bl, R., Berend, N.: German today: a really extensive corpus of spoken standard german. In: Proc. LREC (2008)","key":"54_CR6"},{"unstructured":"Spiegl, W., Riedhammer, K., Steidl, S., N\u00f6th, E.: FAU IISAH corpus - a german speech database consisting of human-machine and human-human interaction acquired by close-talking and far-distance microphones. In: Proc. LREC (2010)","key":"54_CR7"},{"doi-asserted-by":"crossref","unstructured":"Schiel, F., Heinrich, C., Barf\u00fc\u00dfer, S.: Alcohol language corpus: the first public corpus of alcoholized German speech. In: Proc. LREC, vol. 46(3), pp. 503\u2013521 (2012)","key":"54_CR8","DOI":"10.1007\/s10579-011-9139-y"},{"unstructured":"Stadtschnitzer, M., Schwenninger, J., Stein, D., K\u00f6hler, J.: Exploiting the large-scale german broadcast corpus to boost the fraunhofer IAIS speech recognition system. In: Proc. LREC, pp. 3887\u20133890 (2014)","key":"54_CR9"},{"doi-asserted-by":"crossref","unstructured":"Woelfel, M., McDonough, J.: Distant Speech Recognition. Wiley (2009)","key":"54_CR10","DOI":"10.1002\/9780470714089"},{"unstructured":"Gaida, C., Lange, P., Proba, P., Malatawy, A., Suendermann-Oeft, D.: Comparing open-source speech recognition toolkits. http:\/\/suendermann.com\/su\/pdf\/oasis2014.pdf","key":"54_CR11"},{"unstructured":"Morbini, F., Audhkhasi, K., Sagae, K., Artstein, R., Can, D., Georgiou, P., Narayanan, S., Leuski, A., Traum, D.: Which ASR should I choose for my dialogue system? In: Proc. SIGDIAL (2013)","key":"54_CR12"},{"doi-asserted-by":"crossref","unstructured":"Akita, Y., Mimura, M., Kawahara, T.: Automatic transcription system for meetings of the japanese. In: Proc. INTERSPEECH, pp. 84\u201387 (2009)","key":"54_CR13","DOI":"10.21437\/Interspeech.2009-19"},{"key":"54_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/11553762_16","volume-title":"Innovative Internet Community Systems","author":"C Biemann","year":"2006","unstructured":"Biemann, C., B\u00f6hm, K., Heyer, G., Melz, R.: Automatically building concept structures and displaying concept trails for the use in brainstorming sessions and content management systems. In: B\u00f6hme, T., Larios Rosillo, V.M., Unger, H., Unger, H. (eds.) IICS 2004. LNCS, vol. 3473, pp. 157\u2013167. Springer, Heidelberg (2006)"},{"unstructured":"Schnelle-Walka, D., Radeck-Arneth, S., Biemann, C., Radomski, S.: An open source corpus and recording software for distant speech recognition with the microsoft kinect. In: Proc. 11. ITG Fachtagung Sprachkommunikation (2014)","key":"54_CR15"},{"unstructured":"Koehn, P.: Europarl: A Parallel Corpus for Statistical Machine Translation. In: Proc. 10th MT Summit, Phuket, Thailand, AAMT, AAMT, pp. 79\u201386 (2005)","key":"54_CR16"},{"doi-asserted-by":"crossref","unstructured":"Remus, S.: Unsupervised relation extraction of in-domain data from focused crawls. In: Proc. Student Research Workshop of EACL, Gothenburg, Sweden, pp. 11\u201320 (2014)","key":"54_CR17","DOI":"10.3115\/v1\/E14-3002"},{"key":"54_CR18","first-page":"365","volume":"6","author":"M Schr\u00f6der","year":"2003","unstructured":"Schr\u00f6der, M., Trouvain, J.: The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching. IJST 6, 365\u2013377 (2003)","journal-title":"IJST"},{"doi-asserted-by":"crossref","unstructured":"Kneser, R., Ney, H.: Improved backing-off for m-gram language modeling. In: Proc. ICASSP, vol. 1, pp. 181\u2013184 (1995)","key":"54_CR19","DOI":"10.1109\/ICASSP.1995.479394"},{"doi-asserted-by":"crossref","unstructured":"Ali, A., Zhang, Y., Cardinal, P., Dahak, N., Vogel, S., Glass, J.: A complete KALDI recipe for building Arabic speech recognition systems. In: Proc. IEEE SLT, pp. 525\u2013529. Institute of Electrical and Electronics Engineers Inc. (2015)","key":"54_CR20","DOI":"10.1109\/SLT.2014.7078629"},{"doi-asserted-by":"crossref","unstructured":"Povey, D., Burget, L., Agarwal, M., Akyazi, P., Feng, K., Ghoshal, A., Glembek, O., Goel, N.K., Karafiat, M., Rastrow, A., Rose, R.C., Schwarz, P., Thomas, S.: Subspace gaussian mixture models for speech recognition. In: Proc. ICASSP, pp. 4330\u20134333 (2010)","key":"54_CR21","DOI":"10.1109\/ICASSP.2010.5495662"},{"key":"54_CR22","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/89.759034","volume":"7","author":"MJ Gales","year":"1999","unstructured":"Gales, M.J.: Semi-Tied Covariance Matrices for Hidden Markov Models. IEEE Trans. Speech and Audio Processing 7, 272\u2013281 (1999)","journal-title":"IEEE Trans. Speech and Audio Processing"},{"issue":"2","key":"54_CR23","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJF Gales","year":"1998","unstructured":"Gales, M.J.F.: Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech & Language 12(2), 75\u201398 (1998)","journal-title":"Computer Speech & Language"},{"doi-asserted-by":"crossref","unstructured":"Gales, M.: Discriminative models for speech recognition. In: 2007 Information Theory and Applications Workshop (2007)","key":"54_CR24","DOI":"10.1109\/ITA.2007.4357576"},{"doi-asserted-by":"crossref","unstructured":"Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., Visweswariah, K.: Boosted MMI for model and feature-space discriminative training. In: Proc. ICASSP, pp. 4057\u20134060 (2008)","key":"54_CR25","DOI":"10.1109\/ICASSP.2008.4518545"},{"doi-asserted-by":"crossref","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio, Speech, Language Process. 20(1), 30\u201342 (2012)","key":"54_CR26","DOI":"10.1109\/TASL.2011.2134090"},{"doi-asserted-by":"crossref","unstructured":"Swietojanski, P., Ghoshal, A., Renals, S.: Hybrid acoustic models for distant and multichannel large vocabulary speech recognition. In: Proc. IEEE ASRU, pp. 285\u2013290 (2013)","key":"54_CR27","DOI":"10.1109\/ASRU.2013.6707744"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-24033-6_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T18:15:01Z","timestamp":1748628901000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-24033-6_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319240329","9783319240336"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-24033-6_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]}}}