{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T06:41:38Z","timestamp":1693032098316},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2017,8,17]],"date-time":"2017-08-17T00:00:00Z","timestamp":1502928000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s10772-017-9449-6","type":"journal-article","created":{"date-parts":[[2017,8,17]],"date-time":"2017-08-17T09:06:28Z","timestamp":1502960788000},"page":"799-811","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Phoneme class based feature adaptation for mismatch acoustic modeling and recognition of distant noisy speech"],"prefix":"10.1007","volume":"20","author":[{"given":"Se\u00e7kin","family":"Uluskan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhijeet","family":"Sangwan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John H. L.","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,17]]},"reference":[{"key":"9449_CR1","unstructured":"Arslan, L. M., & Hansen, J. H. L. (1994). A minimum cost based phoneme class detector for improved iterative speech enhancement. IEEE ICASSP-94 Proceedings, Adelaide, Australia, Vol.\u00a02 pp.\u00a045\u201348."},{"key":"9449_CR2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-04619-7","volume-title":"Microphone arrays: Signal processing techniques and applications","author":"MS Brandstein","year":"2001","unstructured":"Brandstein, M. S., & Ward, D. B. (2001). Microphone arrays: Signal processing techniques and applications. Berlin: Springer."},{"key":"9449_CR3","doi-asserted-by":"crossref","unstructured":"Clarkson, P. R., & Rosenfeld, R. (1997). Statistical language modeling using the CMU-Cambridge Toolkit. ESCA Eurospeech Proceedings, Rhodes, Greece, Vol.\u00a01, pp.\u00a02707\u20132710.","DOI":"10.21437\/Eurospeech.1997-683"},{"key":"9449_CR4","unstructured":"CMU Sphinx - Speech Recognition Toolkit. Open source toolkit for speech recognition project by Carnegie Mellon University. http:\/\/cmusphinx.sourceforge.net\/ ."},{"key":"9449_CR5","doi-asserted-by":"crossref","unstructured":"Demiroglu, C., & Anderson, D. V. (2004). Broad phoneme class recognition in noisy environments using the GEMS. ACSSC Proceedings, Vol.\u00a02, pp.\u00a01805\u20131808.","DOI":"10.1109\/ACSSC.2004.1399474"},{"key":"9449_CR6","doi-asserted-by":"crossref","unstructured":"Dmochowski, J. P., Zicheng, L., & Chou, P. A. (2008). Blind source separation in a distributed microphone meeting environment for improved teleconferencing. ICASSP IEEE international conference on acoustics, speech and signal processing conference proceedings, pp.\u00a089\u201392.","DOI":"10.1109\/ICASSP.2008.4517553"},{"key":"9449_CR7","doi-asserted-by":"crossref","DOI":"10.6028\/NIST.IR.4930","volume-title":"TIMIT acoustic-phonetic continuous speech corpus","author":"JS Garofolo","year":"1993","unstructured":"Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., Pallett, D. S., Dahlgren, N. L., & Zue, V. (1993). TIMIT acoustic-phonetic continuous speech corpus. Philadelphia: Linguistic Data Consortium."},{"key":"9449_CR8","doi-asserted-by":"crossref","unstructured":"Gehrig, T., Nickel, K., Ekenel, H. K., Klee, U., & McDonough, J. (2005). Kalman filters for audio-video source localization. IEEE workshop of applications of signal processing to audio and acoustics proceedings, pp.\u00a0118\u2013121.","DOI":"10.1109\/ASPAA.2005.1540183"},{"issue":"1","key":"9449_CR9","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/89.365376","volume":"3","author":"JHL Hansen","year":"1995","unstructured":"Hansen, J. H. L., & Arslan, L. M. (1995). Markov model-based phoneme class partitioning for improved constrained iterative speech enhancement. IEEE Transactions on Speech and Audio Processing, 3(1), 98\u2013104.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"6","key":"9449_CR10","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A. R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T. N., & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"9449_CR11","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1007\/s10772-016-9377-x","volume":"19","author":"MK Khwaja","year":"2016","unstructured":"Khwaja, M. K., Vikash, P., Arulmozhivarman, P., & Lui, S. (2016). Robust phoneme classification for automatic speech recognition using hybrid features and an amalgamated learning model. International Journal of Speech Technology, 19(4), 895\u2013905.","journal-title":"International Journal of Speech Technology"},{"key":"9449_CR12","doi-asserted-by":"crossref","unstructured":"Lee, C. M., Yildirim, S., Bulut, M., Kazemzadeh, A., Busso, C., Deng, Z., Lee, S., & Narayanan, S. (2004). Emotion recognition based on phoneme classes. ICSLP-04 Proceedings, pp.\u00a0889\u2013892.","DOI":"10.21437\/Interspeech.2004-322"},{"key":"9449_CR13","doi-asserted-by":"crossref","unstructured":"Liao, H. (2013). Speaker adaptation of context dependent deep neural networks. IEEE international conference on acoustics, speech and signal processing proceedings, pp.\u00a07947\u20137951.","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"9449_CR14","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.csl.2016.06.007","volume":"41","author":"AL Maas","year":"2017","unstructured":"Maas, A. L., Qi, P., Xie, Z., Hannun, A. Y., Lengerich, C. T., Jurafsky, D., & Ng, A. Y. (2017). Building DNN acoustic models for large vocabulary speech recognition. Computer Speech and Language, 41, 195\u2013213.","journal-title":"Computer Speech and Language"},{"key":"9449_CR15","doi-asserted-by":"crossref","unstructured":"Mirsamadi, S., & Hansen, J. H. (2015). A study on deep neural network acoustic model adaptation for robust far-field speech recognition. Interspeech Proceedings, Dresden, Germany, pp.\u00a02430\u20132434.","DOI":"10.21437\/Interspeech.2015-525"},{"issue":"10","key":"9449_CR16","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.1109\/TASLP.2016.2580943","volume":"24","author":"S Mirsamadi","year":"2016","unstructured":"Mirsamadi, S., & Hansen, J. H. (2016). A generalized nonnegative tensor factorization approach for distant speech recognition with distributed microphones. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(10), 1721\u20131731.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9449_CR17","unstructured":"Montanari, A. Principal component analysis, University of Bologna. http:\/\/www2.stat.unibo.it\/montanari\/Didattica\/Multivariate\/PCA1.pdf ."},{"key":"9449_CR18","doi-asserted-by":"crossref","unstructured":"Palaz, D., Collobert, R., & Magimai, M. (2013). Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks. Interspeech Proceedings, Lyon, France, pp.\u00a01766\u20131770.","DOI":"10.21437\/Interspeech.2013-438"},{"key":"9449_CR19","unstructured":"Senior Design Day Presentation Videos of University of Texas at Dallas, Erik Jonsson School of Engineering and Computer Science. http:\/\/www.youtube.com\/user\/EE1Events1UTD\/ ."},{"issue":"8","key":"9449_CR20","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1109\/TASLP.2016.2560534","volume":"24","author":"P Swietojanski","year":"2016","unstructured":"Swietojanski, P., Li, J., & Renals, S. (2016). Learning hidden unit contributions for unsupervised acoustic model adaptation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(8), 1450\u20131463.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9449_CR21","unstructured":"The Carnegie Mellon University Pronouncing Dictionary. http:\/\/www.speech.cs.cmu.edu\/cgi-bin\/cmudict ."},{"key":"9449_CR22","unstructured":"US English WSJ5K Language Model. https:\/\/sourceforge.net\/projects \/cmusphinx\/files\/Acoustic%20and%20Language%20Models\/Archive\/US%20English%20WSJ5K%20Language%20Model\/ ."},{"key":"9449_CR23","doi-asserted-by":"crossref","DOI":"10.1002\/9780470714089","volume-title":"Distant speech recognition","author":"M W\u00f6lfel","year":"2009","unstructured":"W\u00f6lfel, M., & McDonough, J. W. (2009). Distant speech recognition. New York: Wiley."},{"key":"9449_CR24","unstructured":"Woodland, P. C. (2001). Speaker adaptation for continuous density HMMs: A review. ISCA Workshop on Adaptation, pp.\u00a011\u201319."},{"key":"9449_CR25","unstructured":"Zhang, C., Wu, X., Zheng, T. F., Wang, L., & Yin, C. (2012). A K-phoneme-class based multi-model method for short utterance speaker recognition. Signal & Information Processing Association Annual Summit and Conference (APSIPA ASC) Proceedings, pp.\u00a01\u20134."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-017-9449-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9449-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9449-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T03:29:07Z","timestamp":1692934147000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-017-9449-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,17]]},"references-count":25,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["9449"],"URL":"https:\/\/doi.org\/10.1007\/s10772-017-9449-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,8,17]]}}}