{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T05:42:18Z","timestamp":1749966138030,"version":"3.38.0"},"publisher-location":"Berlin, Heidelberg","reference-count":40,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642194566"},{"type":"electronic","value":"9783642194573"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-19457-3_14","type":"book-chapter","created":{"date-parts":[[2011,4,21]],"date-time":"2011-04-21T13:44:27Z","timestamp":1303393467000},"page":"227-244","source":"Crossref","is-referenced-by-count":12,"title":["Robot Audition: Missing Feature Theory Approach and Active Audition"],"prefix":"10.1007","author":[{"given":"Hiroshi G.","family":"Okuno","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Nakadai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun-Don","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"4","key":"14_CR1","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/BF00133571","volume":"1","author":"Y. Aloimonos","year":"1999","unstructured":"Aloimonos, Y., Weiss, I., Bandyopadhyay, A.: Active vision. Intern\u2019l J. of Computer Vision\u00a01(4), 333\u2013356 (1999)","journal-title":"Intern\u2019l J. of Computer Vision"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Asano, F., Asoh, H., Matsui, T.: Sound source localization and signal separation for office robot \u201cJijo-2\u201d. In: Proc. of IEEE Intern\u2019l Conf. on Multisensor Fusion and Integration for Intelligent Systems, pp. 243\u2013248 (1999)","DOI":"10.1109\/MFI.1999.815997"},{"key":"14_CR3","unstructured":"Bahoura, M., Pelletier, C.: Respiratory Sound Classification using Cepstral Analysis and Gaussian Mixture Models. In: IEEE\/EMBS Intern\u2019l Conf., San Francisco, USA (2004)"},{"key":"14_CR4","unstructured":"Berglund, E.J.: Active Audition for Robots using Parameter-Less Self-Organising Maps. Ph. D Thesis, The University of Queensland, Australia (2005)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Barker, J., Cooke, M., Green, P.: Robust ASR Based on Clean Speech Models: An Evaluation of Missing Data Techniques for Connected Digit Recognition in Noise. In: 7th European Conference on Speech Communication Technology, pp. 213\u2013216 (2001)","DOI":"10.21437\/Eurospeech.2001-76"},{"key":"14_CR6","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/6391.001.0001","volume-title":"Spatial Hearing \u2013 The Psychophysics of Human Sound Localization","author":"J. Blauert","year":"1996","unstructured":"Blauert, J.: Spatial Hearing \u2013 The Psychophysics of Human Sound Localization. The MIT Press, Cambridge (1996) (revised edition)"},{"key":"14_CR7","unstructured":"Breazeal, C.: Emotive Qualities in Robot Speech. In: Proceeding of IEEE\/RSJ Intern\u2019l Conf. on Intelligent Robots and Systems, Hawaii, pp. 1389\u20131394 (2001)"},{"key":"14_CR8","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1486.001.0001","volume-title":"Auditory Scene Analysis","author":"A.S. Bregman","year":"1990","unstructured":"Bregman, A.S.: Auditory Scene Analysis. The MIT Press, Cambridge (1990)"},{"key":"14_CR9","first-page":"267","volume-title":"Robust Automatic Speech Recognition with Missing and Unreliable Acoustic Data. Speech Communication","author":"M. Cooke","year":"2001","unstructured":"Cooke, M., Green, P., Josifovski, L., Vizinho, A.: Robust Automatic Speech Recognition with Missing and Unreliable Acoustic Data. Speech Communication, vol.\u00a034, pp. 267\u2013285. Elsevier, Amsterdam (2001)"},{"issue":"6","key":"14_CR10","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","volume":"32","author":"Y. Ephraim","year":"1984","unstructured":"Ephraim, Y., Malah, D.: Speech enhancement using minimum mean-square error short-time spectral amplitude estimator. IEEE Trans. on ASSP\u00a032(6), 1109\u20131121 (1984)","journal-title":"IEEE Trans. on ASSP"},{"key":"14_CR11","unstructured":"Hara, I., Asano, F., Kawai, Y., Kanehiro, F., Yamamoto, K.: Robust speech interface based on audio and video information fusion for humanoid HRP-2. In: Proceeding of IEEE\/RSJ Intern\u2019l Conf. on Intelligent Robots and Systems, Sendai, Japan, pp. 2404\u20132410 (2004)"},{"key":"14_CR12","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-540-73325-6_28","volume-title":"New Trends in Applied Artificial Intelligence","author":"H.D. Kim","year":"2007","unstructured":"Kim, H.D., Komatani, K., Ogata, T., Okuno, H.G.: Real-Time Auditory and Visual Talker Tracking through integrating EM algorithm and Particle Filter. In: Okuno, H.G., Ali, M. (eds.) IEA\/AIE 2007. LNCS (LNAI), vol.\u00a04570, pp. 280\u2013290. Springer, Heidelberg (2007)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Kim, H.D., Komatani, K., Ogata, T., Okuno, H.G.: Human Tracking System Integrating Sound and Face Localization using EM Algorithm in Real Environments. Advanced Robotics, 23(6):629\u2013653 (2009) doi: 10.1163\/156855309X431659","DOI":"10.1163\/156855309X431659"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Kim, H.D., Komatani, K., Ogata, T., Okuno, H.G.: Binaural Active Audition for Humanoid Robots to Localize Speech over Entire Azimuth Range. Applied Bionic and Biomechanics (2009) (to appear)","DOI":"10.1155\/2009\/817874"},{"issue":"7","key":"14_CR15","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TSA.2002.804546","volume":"10","author":"L. Lu","year":"2002","unstructured":"Lu, L., Zhang, H.G., Jiang, H.: Content Analysis for Audio Classification and Segmentation. IEEE Trans. on Speech and Audio Processing\u00a010(7), 504\u2013516 (2002)","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"issue":"4","key":"14_CR16","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1109\/TRO.2007.900612","volume":"23","author":"F. Michaud","year":"2007","unstructured":"Michaud, F., et al.: Robust Recognition of Simultaneous Speech by a Mobile Robot. IEEE Trans. on Robotics\u00a023(4), 742\u2013752 (2007)","journal-title":"IEEE Trans. on Robotics"},{"issue":"6","key":"14_CR17","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/79.543975","volume":"13","author":"T.K. Moon","year":"1996","unstructured":"Moon, T.K.: The Expectation-Maximization algorithm. IEEE Signal Processing Magazine\u00a013(6), 47\u201360 (1996)","journal-title":"IEEE Signal Processing Magazine"},{"key":"14_CR18","first-page":"832","volume-title":"Proc. of 17th National Conference on Artificial Intelligence","author":"K. Nakadai","year":"2000","unstructured":"Nakadai, K., et al.: Active audition for humanoid. In: Proc. of 17th National Conference on Artificial Intelligence, pp. 832\u2013839. AAAI, Menlo Park (2000)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Nakadai, K., Hidai, K., Okuno, H.G., Kitano, H.: Real-Time Speaker Localization and Speech Separation by Audio-Visual Integration. In: Proc. of IEEE-RAS Intern\u2019l Conf. on Robotics and Automation, May 2002, pp. 1043\u20131049 (2002), doi:10.1109\/ROBOT.2002.1013493","DOI":"10.1109\/ROBOT.2002.1013493"},{"issue":"4","key":"14_CR20","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.specom.2004.10.010","volume":"44","author":"K. Nakadai","year":"2004","unstructured":"Nakadai, K., Matasuura, D., Okuno, H.G., Tsujino, H.: Improvement of recognition of simultaneous speech signals using AV integration and scattering theory for humanoid robots. Speech Communication\u00a044(4), 97\u2013112 (2004), doi:10.1016\/j.specom.2004.10.010","journal-title":"Speech Communication"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Nakadai, K., Okuno, H.G.: An Open Source Software System for Robot Audition HARK and Its Evaluation. In: IEEE\/RAS Intern\u2019l Conf. on Humanoid Robots, pp. 561\u2013566 (2008), doi:10.1109\/ICHR.2008.4756031","DOI":"10.1109\/ICHR.2008.4756031"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Nakajima, H., Nakadai, K., Hasegawa, Y., Tsujino, H.: Adaptive Step-Size Parameter Control for Real-World Blind Source Separation. In: IEEE Intern\u2019l Conf. on Acoustics, Speech and Signal Processing, pp. 149\u2013152 (2008)","DOI":"10.1109\/ICASSP.2008.4517568"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Nakajima, H., Nakadai, K., Hasegawa, Y., Tsujino, H.: High performance sound source separation adaptable to environmental changes for robot audition. In: IEEE\/RSJ Intern\u2019l Conf. on Intelligent Robots and Systems, pp.2165\u20132171 (2008)","DOI":"10.1109\/IROS.2008.4650597"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Nakajima, H., Nakadai, K., Hasegawa, Y., Tsujino, H.: Sound source separation of moving speakers for robot audition. In: IEEE Intern\u2019l Conf. on Acoustics, Speech and Signal Processing, pp. 3685\u20133688 (2009)","DOI":"10.1109\/ICASSP.2009.4960426"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Nishiura, T., Yamada, T., Nakamura, S., Shikano, K.: Localization of multiple sound sources based on a CSP analysis with a microphone array. In: Proceeding of IEEE Intern\u2019l Conf. on Acoustics, Speech and Signal Processing, Istanbul, Turkey, pp. 1053\u20131056 (2000)","DOI":"10.1109\/ICASSP.2000.859144"},{"key":"14_CR26","unstructured":"Nishimura, Y., Shinozaki, T., Iwano, K., Furui, S.: Noise-robust speech recognition using multi-band spectral features. In: 148th ASA Meeting, 1aSC7, ASA (2004)"},{"issue":"2","key":"14_CR27","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1163\/156855303321165088","volume":"17","author":"H.G. Okuno","year":"2003","unstructured":"Okuno, H.G., Nakadai, K., Hidai, K., Mizoguchi, H., Kitano, H.: Human-Robot Non-Verbal Interaction Empowered by Real-Time Auditory and Visual Multiple-Talker Tracking. Advanced Robotics\u00a017(2), 115\u2013130 (2003), VSP and RSJ, doi:10.1163\/156855303321165088","journal-title":"Advanced Robotics"},{"issue":"6","key":"14_CR28","first-page":"352","volume":"10","author":"L.C. Parra","year":"2002","unstructured":"Parra, L.C., Alvino, C.V.: Geometric source separation: Mergin convolutive source separation with geometric beamforming. IEEE Trans. on SAP 10(6), 352\u2013362 (2002)","journal-title":"IEEE Trans. on SAP"},{"issue":"5","key":"14_CR29","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/MSP.2005.1511828","volume":"22","author":"H. Raj","year":"2005","unstructured":"Raj, H., Sterm, R.M.: Missing-feature approaches in speech recognition. IEEE Signal Processing Magazine 22(5),101\u2013116 (2005)","journal-title":"IEEE Signal Processing Magazine"},{"key":"14_CR30","unstructured":"Rosenthal, D., Okuno, H.G.: Computational Auditory Scene Analysis. Lawrence Erlbaum Associates, Mahwah, New Jersey (1998)"},{"key":"14_CR31","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/TAP.1986.1143830","volume":"34","author":"R.O. Schmidt","year":"1986","unstructured":"Schmidt, R.O.: Multiple Emitter Location and Signals Parameter Estimation. IEEE Transactions on Antennas and Propagation, AP-34, 276\u2013280 (1986)","journal-title":"IEEE Transactions on Antennas and Propagation, AP-"},{"key":"14_CR32","unstructured":"Shah, J.K., Iyer, A.N., Smolenski, B.Y., Yantormo, R.E.: Robust Voiced\/Unvoiced classification using novel feature and Gaussian Mixture Model. In: Proc. of IEEE Intern\u2019l Conf. on Acoustics, Speech, and Signal Processing, Montreal, Canada (2004)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Valin, J.-M., Michaud, F., Hadjou, B., Rouat, J.: Localization of simultaneous moving sound sources for mobile robot using a frequency-domain steered beamformer approach. In: IEEE Intern\u2019l Conf. on Robotics and Automation, pp. 1033\u20131038 (2004)","DOI":"10.1109\/ROBOT.2004.1307286"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Valin, J.-M., Michaud, F., Hadjou, B., Rouat, J.: Enhanced Robot Audition Based on Microphone Array Source Separation with Post-Filter. In: IEEE\/RSJ Intern\u2019l Conf. on Intelligent Robots and Systems, pp.2123\u20132128 (2004)","DOI":"10.1109\/IROS.2004.1389723"},{"issue":"4","key":"14_CR35","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1109\/TRO.2007.900612","volume":"23","author":"J.-M. Valin","year":"2007","unstructured":"Valin, J.-M., Michaud, F., Hadjou, B., Rouat, J., Nakadai, K., Okuno, H.G.: Robust Recognition of Simultaneous Speech by a Mobile Robot. IEEE Transactions on Robotics\u00a023(4), 742\u2013752 (2007), doi:10.1109\/TRO.2007.900612","journal-title":"IEEE Transactions on Robotics"},{"issue":"3","key":"14_CR36","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.robot.2006.08.004","volume":"55","author":"J.-M. Valin","year":"2007","unstructured":"Valin, J.-M., Michaud, F., Hadjou, B., Rouat, J., Nakadai, K., Okuno, H.G.: Robust localization and tracking of simultaneous moving sound sources using beamforming and particle filtering. Robotics and Autonomous Systems J.\u00a055(3), 216\u2013228 (2007)","journal-title":"Robotics and Autonomous Systems J."},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Yamada, S., Lee, A., Saruwatari, H., Shikano, K.: Unsupervided speaker adaptation based on HMM sufficient statistics in various noisy environments. In: Proc. of Eurospeech 2003. ESCA, pp. 1493\u20131496 (2003)","DOI":"10.21437\/Eurospeech.2003-434"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Yamamoto, S., Valin, J.-M., Nakadai, K., Ogata, T., Okuno, H.G.: Enhanced Robot Speech Recognition Based on Microphone Array Source Separation and Missing Feature Theory. In: IEEE-RAS Intern\u2019l Conf. on Robotics and Automation, pp. 1477\u20131482 (April 2005)","DOI":"10.1109\/ROBOT.2005.1570323"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Yamamoto, S., et al.: Making A Robot Recognize Three Simultaneous Sentences in Real-Time. In: IEEE\/RSJ Intern\u2019l Conf. on Intelligent Robots and Systems, pp. 4040\u20134045 (2005)","DOI":"10.1109\/IROS.2005.1545094"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Yamamoto, S., et al.: Real-time robot audition system that recognizes simultaneous speech in the real world. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5333\u20135338 (2006)","DOI":"10.1109\/IROS.2006.282037"}],"container-title":["Springer Tracts in Advanced Robotics","Robotics Research"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-19457-3_14.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T05:42:43Z","timestamp":1741153363000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-19457-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642194566","9783642194573"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-19457-3_14","relation":{},"ISSN":["1610-7438","1610-742X"],"issn-type":[{"type":"print","value":"1610-7438"},{"type":"electronic","value":"1610-742X"}],"subject":[],"published":{"date-parts":[[2011]]}}}