{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:11:25Z","timestamp":1759939885468,"version":"3.40.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,2,5]],"date-time":"2013-02-05T00:00:00Z","timestamp":1360022400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2013,4]]},"DOI":"10.1007\/s10514-013-9323-6","type":"journal-article","created":{"date-parts":[[2013,2,4]],"date-time":"2013-02-04T14:20:46Z","timestamp":1359987646000},"page":"207-215","source":"Crossref","is-referenced-by-count":13,"title":["ROS open-source audio recognizer: ROAR environmental sound detection tools for robot programming"],"prefix":"10.1007","volume":"34","author":[{"given":"Joseph M.","family":"Romano","sequence":"first","affiliation":[]},{"given":"Jordan P.","family":"Brindza","sequence":"additional","affiliation":[]},{"given":"Katherine J.","family":"Kuchenbecker","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,2,5]]},"reference":[{"volume-title":"Springer handbook of speech processing","year":"2008","key":"9323_CR1","unstructured":"Benesty, J., Sondhi, M. M., & Huang, Y. (Eds.). (2008). Springer handbook of speech processing. Berlin: Springer."},{"key":"9323_CR2","doi-asserted-by":"crossref","unstructured":"Borst, C., Wimbock, T., Schmidt, F., Fuchs, M., Brunner, B., Zacharias, F., et al. (2009). Rollin\u2019 Justin\u2014mobile platform with variable base. In Proceedings of the IEEE international conference on robotics and automation.","DOI":"10.1109\/ROBOT.2009.5152586"},{"key":"9323_CR3","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1109\/TSA.2005.857575","volume":"14","author":"R Cai","year":"2006","unstructured":"Cai, R., Lu, L., Hanjalic, A., Zhang, H. J., & Cai, L. H. (2006). A flexible framework for key audio effects detection and auditory context inference. IEEE Transactions on Audio, Speech, and Language Processing, 14, 1026\u20131039.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9323_CR4","doi-asserted-by":"crossref","unstructured":"Chu, S., Narayanan, S., Kuo, C. C. J., Matari\u0107, M.J. (2006). Where am I? Scene recognition for mobile robots using audio features. In Proceedings of the IEEE international conference on multimedia and expo (pp. 885\u2013888).","DOI":"10.1109\/ICME.2006.262661"},{"key":"9323_CR5","unstructured":"Ciocarlie, M., Hsiao, K., Jones, G. E., Chitta, S., Rusu, R. B., & Sucan, I. A. (2010). Towards reliable grasping and manipulation in household environments. In Proceedings of the international symposium on experimental, robotics."},{"issue":"1","key":"9323_CR6","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1109\/97.988717","volume":"9","author":"I Cohen","year":"2002","unstructured":"Cohen, I. (2002). Noise estimation by minima controlled recursive averaging for robust speech enhancement. IEEE Signal Processing Letters, 9(1), 12\u201315.","journal-title":"IEEE Signal Processing Letters"},{"issue":"4","key":"9323_CR7","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"Davis, S. B., & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech and Signal Processing, 28(4), 357\u2013366.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"9323_CR8","unstructured":"Dufaux, A. (2001). Detection and recognition of impulsive sound signals. Ph.D. thesis, University of Neuch\u00e2tel."},{"key":"9323_CR9","unstructured":"Eaton, J. W. (2002). GNU Octave Manual. Network Theory Limited."},{"key":"9323_CR10","unstructured":"Ellis, D. P. W. (2005). PLP and RASTA (and MFCC, and inversion) in Matlab (2005). www.ee.columbia.edu\/~dpwe\/resources\/matlab\/rastamat . Online web resource."},{"issue":"2","key":"9323_CR11","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1023\/B:AURO.0000016865.35796.e9","volume":"16","author":"B Graf","year":"2004","unstructured":"Graf, B., Hans, M., & Schraft, R. D. (2004). Care-O-bot II\u2014development of a next generation robotic home assistant. Autonomous Robots, 16(2), 193\u2013205.","journal-title":"Autonomous Robots"},{"key":"9323_CR12","doi-asserted-by":"crossref","unstructured":"Gray, S. R., Romano, J. M., Brindza, J. P., Kim, S., Kuchenbecker, K. J., Kumar, V. (2011). Planning manipulation and grasping tasks with a redundant arm. In Proceedings of the ASME international design engineering technical conferences & computers and information in, engineering conference.","DOI":"10.1115\/DETC2011-47453"},{"issue":"4","key":"9323_CR13","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H Hermansky","year":"1990","unstructured":"Hermansky, H. (1990). Perceptual linear predictive (PLP) analysis of speech. Journal of the Acoustical Society of America, 87(4), 1738\u20131752.","journal-title":"Journal of the Acoustical Society of America"},{"issue":"1","key":"9323_CR14","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s10514-009-9148-5","volume":"28","author":"A Jain","year":"2010","unstructured":"Jain, A., & Kemp, C. C. (2010). EL-E: An assistive mobile manipulator that autonomously fetches objects from flat surfaces. Autonomous Robots, 28(1), 45\u201364.","journal-title":"Autonomous Robots"},{"key":"9323_CR15","doi-asserted-by":"crossref","unstructured":"Lim, A., Mizumoto, T., Cahier, L. K., Otsuka, T., Takahashi, T., Komatani, K., Ogata, T., Okuno, H. G. (2010). Robot musical accompaniment: Integrating audio and visual cues for real-time synchronization with a human flutist. In Proceedings of the IEEE international conference on intelligent robots and systems.","DOI":"10.1109\/IROS.2010.5650427"},{"key":"9323_CR16","unstructured":"Nakamura, T., Nagai, T., & Iwahashi, N. (2007). Multimodel object categorization by a robot. In Proceedings of the IEEE international conference on intelligent robots and systems."},{"key":"9323_CR17","doi-asserted-by":"crossref","unstructured":"Okuno, H. G., & Nakadai, K. (2007). Computational auditory scene analysis and its application to robot audition: Five years experience. In Proceedings of the second international conference on informatics research for development of knowledge society infrastructure (pp. 69\u201376).","DOI":"10.1109\/ICKS.2007.7"},{"issue":"5","key":"9323_CR18","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1109\/MSP.2004.1328092","volume":"21","author":"AV Oppenheim","year":"2004","unstructured":"Oppenheim, A. V., & Schafer, R. W. (2004). From frequency to quefrency: A history of the cepstrum. IEEE Signal Processing Magazine, 21(5), 95\u2013106.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9323_CR19","doi-asserted-by":"crossref","unstructured":"Port\u00ealo, J., Bugalho, M., Trancoso, I., Neto, J., Abad, A., & Serralheiro, A. (2009). Non-speech audio event detection. In Proceedings of the IEEE international conference on acoustics, speech and, signal processing (pp. 1973\u20131976).","DOI":"10.1109\/ICASSP.2009.4959998"},{"key":"9323_CR20","unstructured":"Quigley, M., Gerkey, B., Conley, K., Faust, J., Foote, T., Leibs, J., et al. (2009). ROS: An Open-source Robot Operating System. In Open-source software workshop of the IEEE international conference on robotics and automation."},{"key":"9323_CR21","doi-asserted-by":"crossref","unstructured":"Rabaoui, A., Davy, M., Rossignol, S., Lachiri, Z., & Ellouze, N. (2007). Improved one-class SVM classifier for sounds classification. In Proceedings of the IEEE conference on advanced video and signal based surveillance (pp. 117\u2013122).","DOI":"10.1109\/AVSS.2007.4425296"},{"key":"9323_CR22","doi-asserted-by":"crossref","unstructured":"Ramo, J., Siddiqi, A., Dubrawski, A., Gordon, G., & Sharma, A. (2010). Automatic state discovery for unstructured audio scene classification. In Proceedings of IEEE international conference on acoustic speech and signal processing.","DOI":"10.1109\/ICASSP.2010.5495605"},{"key":"9323_CR23","unstructured":"Rodemann, T., Joublin, F., & Goerick, C. (2009). Filtering environmental sounds using basic audio cues in robot audition. In Proceedings of the international conference on advanced robotics."},{"issue":"3\u20134","key":"9323_CR24","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1533\/abbi.2004.0057","volume":"2","author":"J Rojas","year":"2005","unstructured":"Rojas, J., & Peters, R. A, I. I. (2005). Sensory integration with articulated motion on a humanoid robot. Applied Bionics and Biomechanics, 2(3\u20134), 171\u2013178.","journal-title":"Applied Bionics and Biomechanics"},{"key":"9323_CR25","doi-asserted-by":"crossref","unstructured":"Romano, J. M., Hsiao, K., Niemeyer, G., Chitta, S., & Kuchenbecker, K. J. (2011). Human-inspired robotic grasp control with tactile sensing. IEEE Transactions on Robotics.","DOI":"10.1109\/TRO.2011.2162271"},{"key":"9323_CR26","doi-asserted-by":"crossref","unstructured":"Sakagami, Y., Watanabe, R., & Aoyama, C.: The intelligent ASIMO: System overview and integration. In Proceedings of the IEEE international conference on intelligent robotics and systems (pp. 2478\u20132483).","DOI":"10.1109\/IRDS.2002.1041641"},{"key":"9323_CR27","unstructured":"Sarle, W. S. (1997). Neural network FAQ. ftp:\/\/ftp.sas.com\/pub\/neural\/FAQ.html . Periodic posting to the Usenet newsgroup comp.ai.neural-nets."},{"key":"9323_CR28","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1162\/089976601750264965","volume":"13","author":"B Sch\u00f6lkopf","year":"2001","unstructured":"Sch\u00f6lkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural Computation, 13, 1443\u20131471.","journal-title":"Neural Computation"},{"key":"9323_CR29","unstructured":"Sinapov, J., & Stoytchev, A. (2009). From acoustic object recognition to object categorization by a humanoid robot. In Proceedings of the RSS 2009 workshop: Mobile manipulation in human, environments."},{"key":"9323_CR30","first-page":"1799","volume":"11","author":"S Sonnenburg","year":"2010","unstructured":"Sonnenburg, S., Raetsch, G., Henschel, S., Widmer, C., Behr, J., Zien, A., et al. (2010). The SHOGUN machine learning toolbox. Journal of Machine Learning Research, 11, 1799\u20131802.","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"9323_CR31","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10514-009-9160-9","volume":"28","author":"S Srinivasa","year":"2009","unstructured":"Srinivasa, S., Ferguson, D., Helfrich, C., Berenson, D., Collet, A., Diankov, R., et al. (2009). Herb: A home exploring robotic butler. Autonomous Robots, 28(1), 5\u201320.","journal-title":"Autonomous Robots"},{"key":"9323_CR32","unstructured":"Torres-Jara, E., Natale, L., & Fitzpatrick, P. (2005). Tapping into touch. In Proceedings of the fifth international workshop on epigenetic robotics: Modeling cognitive development in robotic systems (pp. 79\u201386)."},{"key":"9323_CR33","doi-asserted-by":"crossref","unstructured":"Valin, J. M., Michaud, F., & Rouat, J. (2007). Robust localization and tracking of simultaneous moving sound sources using beamforming and particle filtering. Robotics and Autonomous Systems, 55(3), 216\u2013228.","DOI":"10.1016\/j.robot.2006.08.004"},{"key":"9323_CR34","doi-asserted-by":"crossref","unstructured":"Valin, J. M., Yamamoto, S., Rouat, J., Michaud, F., Nakadai, K., & Okuno, H. G. (2007). Robust recognition of simultaneous speech by a mobile robot. IEEE Transactions on Robotics, 23(4), 742\u2013752.","DOI":"10.1109\/TRO.2007.900612"},{"key":"9323_CR35","unstructured":"Vaseghi, S. V. (2000). Advanced digital signal processing and noise reduction. Chichester: Wiley."},{"key":"9323_CR36","doi-asserted-by":"crossref","unstructured":"Wu, X., Gong, H., Chen, P., Zhong, Z., & Xu, Y. (2009). Surveillance robot utilizing video and audio information. Journal of Intelligent & Robotic Systems, 55, 403\u2013421.","DOI":"10.1007\/s10846-008-9297-3"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-013-9323-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10514-013-9323-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-013-9323-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T19:26:04Z","timestamp":1745954764000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10514-013-9323-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,5]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,4]]}},"alternative-id":["9323"],"URL":"https:\/\/doi.org\/10.1007\/s10514-013-9323-6","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"type":"print","value":"0929-5593"},{"type":"electronic","value":"1573-7527"}],"subject":[],"published":{"date-parts":[[2013,2,5]]}}}