{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:52:04Z","timestamp":1740099124844,"version":"3.37.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319925363"},{"type":"electronic","value":"9783319925370"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-92537-0_57","type":"book-chapter","created":{"date-parts":[[2018,5,25]],"date-time":"2018-05-25T07:25:50Z","timestamp":1527233150000},"page":"494-502","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Comparative Study of Spatial Speech Separation Techniques to Improve Speech Recognition"],"prefix":"10.1007","author":[{"given":"Xinhui","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiman","family":"Kwan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bulent","family":"Ayhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanwoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K.","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Stern","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,26]]},"reference":[{"key":"57_CR1","doi-asserted-by":"crossref","unstructured":"Kim, C., Menon, A., Bacchiani, M., Stern, R.M.: Sound source separation using phase difference and reliable mask selection. In: IEEE International Conference on Acoustics, Speech and Signal Processing (2018)","DOI":"10.1109\/ICASSP.2018.8462269"},{"key":"57_CR2","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.heares.2017.11.010","volume":"360","author":"M Dietz","year":"2017","unstructured":"Dietz, M., Lestang, J.H., Majdak, P., Stern, R.M., Marquardt, T., Ewert, S.D., Hartmann, W.M., Goodman, D.: A framework for testing and comparing binaural models. J. Hear. Res. 360, 92\u2013106 (2017)","journal-title":"J. Hear. Res."},{"key":"57_CR3","unstructured":"Li, Y., Vicente, L., Ho, K.C., Kwan, C., Lun, D.P.K., Leung, Y.H.: A study of partially adaptive concentric ring array. J. Circuits, Syst. Sig. Process. 27(5), 733\u2013748 (2008)"},{"key":"57_CR4","doi-asserted-by":"crossref","unstructured":"Vicente, L.M., Ho, K.C., Kwan, C.: An improved partial adaptive narrow-band beamformer using concentric ring array. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (2006)","DOI":"10.1109\/ICASSP.2006.1661149"},{"key":"57_CR5","unstructured":"Li, Y., Ho, K.C., Kwan, C., Leung, Y.H.: Generalized partially adaptive concentric ring array. In: IEEE International Symposium Circuits System, pp. 3745\u20133748 (2005)"},{"key":"57_CR6","doi-asserted-by":"crossref","unstructured":"Kwan, C., Mei, G., Zhao, X., Ren, Z., Xu, R., Stanford, V., Rochet, C., Aube, J., Ho, K.C.: Bird classification algorithms: theory and experimental results. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 289\u2013292 (2004)","DOI":"10.1109\/ICASSP.2004.1327104"},{"key":"57_CR7","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387","volume-title":"Computational Auditory Scene Analysis: Principles, Algorithms, and Applications","author":"D Wang","year":"2006","unstructured":"Wang, D., Brown, G.: Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. Wiley\/IEEE Press, Hoboken (2006)"},{"issue":"2","key":"57_CR8","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/TASSP.1985.1164550","volume":"33","author":"Y Ephraim","year":"1985","unstructured":"Ephraim, Y., Malah, D.: Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans. Acoust. Speech Sig. Process. 33(2), 443\u2013445 (1985)","journal-title":"IEEE Trans. Acoust. Speech Sig. Process."},{"key":"57_CR9","doi-asserted-by":"crossref","unstructured":"Kwan, C., Chu, S., Yin, J., Liu, X., Kruger, M., Sityar, I.: Enhanced speech in noisy multiple speaker environment. In: IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) (2008)","DOI":"10.1109\/IJCNN.2008.4634017"},{"key":"57_CR10","doi-asserted-by":"crossref","unstructured":"Deng, Y., Li, X., Kwan, C., Xu, R., Raj, B., Stern, R., Williamson, D.: An integrated approach to improve speech recognition rate for non-native speakers. In: Ninth International Conference on Spoken Language Processing, INTERSPEECH 2006 \u2013 ICSLP (2006)","DOI":"10.21437\/Interspeech.2006-481"},{"key":"57_CR11","unstructured":"Zhou, J., Ayhan, B., Kwan, C., Sands, O.S.: A high performance approach to minimizing interactions between inbound and outbound signals in helmet. In: SPIE Conference on Defense, Security, and Applications (2012)"},{"key":"57_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/11825890_11","volume-title":"Ambient Intelligence in Everyday Life","author":"R Xu","year":"2006","unstructured":"Xu, R., Mei, G., Ren, Z., Kwan, C., Aube, J., Rochet, C., Stanford, V.: Speaker Identification and Speech Recognition Using Phased Arrays. In: Cai, Y., Abascal, J. (eds.) Ambient Intelligence in Everyday Life. LNCS (LNAI), vol. 3864, pp. 227\u2013238. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11825890_11"},{"key":"57_CR13","doi-asserted-by":"crossref","unstructured":"Kwan, C., Yin, J., Ayhan, B., Chu, S., Liu, X., Puckett, K., Zhao, Y., Ho, K.C., Kruger, M., Sityar, I.: An Integrated Approach to Robust Speaker Identification and Speech Recognition. IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) (2008)","DOI":"10.1109\/IJCNN.2008.4634016"},{"key":"57_CR14","unstructured":"Kwan, C., Zhou, J.: Compact Plug-In Noise Cancellation Device. Patent # 9,117,457 (2015)"},{"key":"57_CR15","unstructured":"Deng, Y., Li., X., Kwan, C., Raj, B., Stern, R.: Continuous feature adaptation for non-native speech recognition. Int. J. Comput. Control, Quantum Inf. Eng. 1, 1675\u20131682 (2007)"},{"key":"57_CR16","doi-asserted-by":"crossref","unstructured":"Kwan, C., Yin, J., Ayhan, B., Chu, S., Liu, X., Puckett, K., Zhao, Y., Ho, D., Kruger, M., Sityar, I.: Speech separation algorithms for multiple speaker environments. In: IEEE International Joint Conference on Neural Networks (2008)","DOI":"10.1109\/IJCNN.2008.4634018"},{"key":"57_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387","volume-title":"Computational auditory scene analysis: principles, algorithms and applications","author":"D Wang","year":"2006","unstructured":"Wang, D.: Computational auditory scene analysis: principles, algorithms and applications. Wiley, Hoboken (2006)"},{"key":"57_CR18","doi-asserted-by":"crossref","unstructured":"Stern, R., Gouvea, E., Kim, C., Kumar, K., Park, H.-M.: Binaural and multiple-microphone signal processing motivated by auditory perception. In: Proceedings of HSCMA Joint Workshop on Hands-Free Speech Communication and Microphone Arrays (2008)","DOI":"10.1109\/HSCMA.2008.4538697"},{"key":"57_CR19","unstructured":"Park, H.-M., Stern, R.M.: Spatial separation of speech signals using continuously-variable masks estimated from comparisons of zero crossings. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (2006)"},{"key":"57_CR20","unstructured":"Bernstein, J., Price, P., Fisher, W.M., Pallett, D.S.: Resource Management RM1 2.0, Linguistic Data Consortium, Philadelphia (1993)"},{"key":"57_CR21","doi-asserted-by":"crossref","unstructured":"Clarkson, P.: Statistical language modeling using the cmu-cambridge toolkit. In: Proceedings of Eurospeech, pp. 2707\u20132710 (1997)","DOI":"10.21437\/Eurospeech.1997-683"},{"key":"57_CR22","unstructured":"Ellis, D.P.W.: PLP and RASTA (and MFCC, and inversion) in Matlab (2005). http:\/\/labrosa.ee.columbia.edu\/matlab\/"},{"key":"57_CR23","volume-title":"Speech and Audio Signal Processing: Processing and Perception of Speech and Music","author":"B Gold","year":"2001","unstructured":"Gold, B., Morgan, N.: Speech and Audio Signal Processing: Processing and Perception of Speech and Music. Wiley, New York (2001)"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2018"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92537-0_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T04:37:40Z","timestamp":1661315860000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92537-0_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319925363","9783319925370"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92537-0_57","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}