{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T11:02:16Z","timestamp":1740135736981,"version":"3.37.3"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s00034-023-02433-z","type":"journal-article","created":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T12:02:31Z","timestamp":1687953751000},"page":"7004-7021","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Direction Estimation of Instrumental Sound Sources Using Regression Analysis by Convolutional Neural Network"],"prefix":"10.1007","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6893-4959","authenticated-orcid":false,"given":"Kaho","family":"Yamamoto","sequence":"first","affiliation":[]},{"given":"Akio","family":"Ogihara","sequence":"additional","affiliation":[]},{"given":"Harumi","family":"Murata","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,28]]},"reference":[{"issue":"1","key":"2433_CR1","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/JSTSP.2019.2901664","volume":"13","author":"S Chakrabarty","year":"2019","unstructured":"S. Chakrabarty, E.A.P. Habets, Multi-speaker DOA estimation using deep convolutional networks trained with noise signals. IEEE J. Select. Topics Signal Process. 13(1), 8\u201321 (2019). https:\/\/doi.org\/10.1109\/JSTSP.2019.2901664","journal-title":"IEEE J. Select. Topics Signal Process."},{"key":"2433_CR2","doi-asserted-by":"publisher","unstructured":"Y.N. Dauphin, A. Fan, M. Auli, D. Grangier, Language modeling with gated convolutional networks, in Proceedings of the 34th International Conference on Machine Learning (2017), pp. 933\u2013941. https:\/\/doi.org\/10.48550\/arXiv.1612.08083","DOI":"10.48550\/arXiv.1612.08083"},{"issue":"3","key":"2433_CR3","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1093\/ietisy\/e89-d.3.1050","volume":"E89-D","author":"Y Denda","year":"2006","unstructured":"Y. Denda, T. Nishiura, Y. Yamashita, Robust talker direction estimation based on weighted CSP analysis and maximum likelihood estimation. IEICE Trans. Inf. Syst. E89-D(3), 1050\u20131057 (2006). https:\/\/doi.org\/10.1093\/ietisy\/e89-d.3.1050","journal-title":"IEICE Trans. Inf. Syst."},{"key":"2433_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2020.2980384","author":"AM Elbir","year":"2020","unstructured":"A.M. Elbir, DeepMUSIC: multiple signal classification via deep learning. IEEE Sens. Lett. (2020). https:\/\/doi.org\/10.1109\/LSENS.2020.2980384","journal-title":"IEEE Sens. Lett."},{"key":"2433_CR5","doi-asserted-by":"publisher","unstructured":"E.L. Ferguson, S.B. Williams, C.T. Jin, Sound source localization in a multipath environment using convolutional neural networks, in Proceedings of 2018 IEEE International Conference on Acoustic, Speech and Signal Process (2018), pp. 2386\u20132390. https:\/\/doi.org\/10.1109\/ICASSP.2018.8462024","DOI":"10.1109\/ICASSP.2018.8462024"},{"issue":"1","key":"2433_CR6","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1121\/10.0011809","volume":"152","author":"P-A Grumiaux","year":"2022","unstructured":"P.-A. Grumiaux, S. Kiti\u0107, L. Girin, A. Gu\u00e9rin, A survey of sound source localization with deep learning methods. J. Acoust. Soc. Am. 152(1), 107\u2013151 (2022). https:\/\/doi.org\/10.1121\/10.0011809","journal-title":"J. Acoust. Soc. Am."},{"key":"2433_CR7","doi-asserted-by":"publisher","unstructured":"M. Ikeuchi, H. Tanji, T. Murakami, Improvement of the direction-of-arrival estimation method using a single channel microphone by correcting a spectral slope of speech, in Proceedings of APSIPA ASC 2022 (2022), pp. 186\u2013393. https:\/\/doi.org\/10.23919\/APSIPAASC55919.2022.9980291","DOI":"10.23919\/APSIPAASC55919.2022.9980291"},{"issue":"9","key":"2433_CR8","doi-asserted-by":"publisher","first-page":"525","DOI":"10.20697\/jasj.75.9_525","volume":"75","author":"H Kameoka","year":"2019","unstructured":"H. Kameoka, Deep learning approach to audio source separation. J. Acoust. Soc. Jpn. 75(9), 525\u2013531 (2019). https:\/\/doi.org\/10.20697\/jasj.75.9_525","journal-title":"J. Acoust. Soc. Jpn."},{"key":"2433_CR9","unstructured":"K. Kikuma, Adaptive signal processing with array antenna. (Science and Technology Publishing Company, 1999)"},{"issue":"2","key":"2433_CR10","doi-asserted-by":"publisher","first-page":"242","DOI":"10.20965\/jaciii.2018.p0242","volume":"22","author":"M Kitahashi","year":"2018","unstructured":"M. Kitahashi, H. Handa, Estimating classroom situations by using CNN with environmental sound spectrograms. J. Adv. Comput. Intell. Intell. Inf. 22(2), 242\u2013248 (2018). https:\/\/doi.org\/10.20965\/jaciii.2018.p0242","journal-title":"J. Adv. Comput. Intell. Intell. Inf."},{"issue":"2","key":"2433_CR11","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s42401-019-00026-w","volume":"2","author":"W Ma","year":"2019","unstructured":"W. Ma, X. Liu, Phased microphone array for sound source localization with deep learning. Aerosp. Syst. 2(2), 71\u201381 (2019). https:\/\/doi.org\/10.1007\/s42401-019-00026-w","journal-title":"Aerosp. Syst."},{"issue":"1","key":"2433_CR12","doi-asserted-by":"publisher","first-page":"39","DOI":"10.20697\/jasj.73.1_39","volume":"73","author":"R Masumura","year":"2017","unstructured":"R. Masumura, Language modeling and spoken language understanding based on deep learning. J. Acoust. Soc. Jpn. 73(1), 39\u201346 (2017). https:\/\/doi.org\/10.20697\/jasj.73.1_39","journal-title":"J. Acoust. Soc. Jpn."},{"issue":"2","key":"2433_CR13","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3135\/jmasj.32.89","volume":"32","author":"K Mori","year":"2005","unstructured":"K. Mori, T. Yokoyama, A. Hasegawa, Comparison of high-resolution techniques for array signal processing method in silent target detection using ambient noise. J. Marine Acoust. Soc. Jpn. 32(2), 89\u201397 (2005). https:\/\/doi.org\/10.3135\/jmasj.32.89","journal-title":"J. Marine Acoust. Soc. Jpn."},{"key":"2433_CR14","doi-asserted-by":"publisher","unstructured":"R. Nishimura, Y. Suzuki, Source and direction of arrival estimation based on maximum likelihood combined with GMM and eigenanalysis, in Proceedings of 2018 IEEE International Conference on Acoustic, Speech and Signal Processing (2018), pp. 3434\u20133438. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461658","DOI":"10.1109\/ICASSP.2018.8461658"},{"issue":"7","key":"2433_CR15","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1109\/29.32276","volume":"ASSP-37","author":"R Roy","year":"1989","unstructured":"R. Roy, T. Kailath, ESPRIT-estimation of signal parameters via rotational invariance techniques. IEEE Trans. Acoust. Speech Signal Process. ASSP-37(7), 984\u2013995 (1989). https:\/\/doi.org\/10.1109\/29.32276","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"3","key":"2433_CR16","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1109\/TAP.1986.1143830","volume":"AP-34","author":"RO Schmidt","year":"1986","unstructured":"R.O. Schmidt, Multiple emitter location and signal parameter estimation. IEEE Trans. Antennas Propag. AP-34(3), 276\u2013280 (1986). https:\/\/doi.org\/10.1109\/TAP.1986.1143830","journal-title":"IEEE Trans. Antennas Propag."},{"issue":"10","key":"2433_CR17","doi-asserted-by":"publisher","first-page":"513","DOI":"10.20697\/jasj.65.10_513","volume":"65","author":"T Suzuki","year":"2009","unstructured":"T. Suzuki, Y. Kaneda, Sound source direction estimation based on subband peak-hold processing. J. Acoust. Soc. Jpn. 65(10), 513\u2013522 (2009). https:\/\/doi.org\/10.20697\/jasj.65.10_513","journal-title":"J. Acoust. Soc. Jpn."},{"issue":"8","key":"2433_CR18","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.2493\/jspe.70.1111","volume":"70","author":"M Uneda","year":"2004","unstructured":"M. Uneda, K. Ishikawa, Study on high resolvable location finding of near sound source using MUSIC algorithm. J. Jpn. Soc. Precis. Eng. 70(8), 1111\u20131116 (2004). https:\/\/doi.org\/10.2493\/jspe.70.1111","journal-title":"J. Jpn. Soc. Precis. Eng."},{"issue":"12","key":"2433_CR19","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.2493\/jjspe.77.1158","volume":"77","author":"M Uneda","year":"2011","unstructured":"M. Uneda, H. Kondo, K. Ishikawa, O. Ohnishi, S. Kurokawa, T. Doi, Location finding function of high correlation sound sources, using combined methods of spatial smoothing processing and MUSIC-development of handy microphone array system for high efficiency location finding-. J. Jpn. Soc. Precis. Eng. 77(12), 1158\u20131164 (2011). https:\/\/doi.org\/10.2493\/jjspe.77.1158","journal-title":"J. Jpn. Soc. Precis. Eng."},{"key":"2433_CR20","doi-asserted-by":"publisher","unstructured":"M. Unoki, M. Akagi, Signal extraction from noisy signal based on auditory scene analysis, in Proceedings of 5th International Conference on Spoken Language Process (1998). https:\/\/doi.org\/10.21437\/ICSLP.1998-342","DOI":"10.21437\/ICSLP.1998-342"},{"key":"2433_CR21","unstructured":"K. Yamamoto, A. Ogihara, H. Murata, Direction estimation of virtual sound source by MUSIC method using fundamental frequency components in stereo sound, in The 2019 (70th) Chugoku-branch Joint Convention of the Institutes of Electrical and Information Engineers, R19-08-01-05 (2019)"},{"key":"2433_CR22","doi-asserted-by":"publisher","unstructured":"K. Yamamoto, A. Ogihara, H. Murata, Direction estimation of sound source by MUSIC method and CNN considering overtone structure, in Proceedings of 2022 international technical conference on circuits\/systems, computers and communications (2022), pp. 671\u2013674. https:\/\/doi.org\/10.1109\/ITC-CSCC55581.2022.9895088","DOI":"10.1109\/ITC-CSCC55581.2022.9895088"},{"issue":"10","key":"2433_CR23","doi-asserted-by":"publisher","first-page":"780","DOI":"10.14923\/transinfj.2020JDL8018","volume":"J104-D","author":"K Yamamoto","year":"2021","unstructured":"K. Yamamoto, A. Ogihara, H. Murata, Direction estimation of sound source using MUSIC method and FFNN focusing on the overtone structure of instrumental sounds. IEICE Trans. Inf. Syst. J104-D(10), 780\u2013783 (2021). https:\/\/doi.org\/10.14923\/transinfj.2020JDL8018","journal-title":"IEICE Trans. Inf. Syst."},{"issue":"3","key":"2433_CR24","doi-asserted-by":"publisher","first-page":"161","DOI":"10.20697\/jasj.62.3_161","volume":"62","author":"K Yamamoto","year":"2006","unstructured":"K. Yamamoto, F. Asano, I. Hara, J. Ogata, H. Asoh, T. Yamada, N. Kitawaki, Real-time speech interface based on the fusion of audio and video information for humanoid robot HRP-2. J. Acoust. Soc. Jpn 62(3), 161\u2013172 (2006). https:\/\/doi.org\/10.20697\/jasj.62.3_161","journal-title":"J. Acoust. Soc. Jpn"},{"issue":"3","key":"2433_CR25","doi-asserted-by":"publisher","first-page":"375","DOI":"10.20965\/jaciii.2021.p0375","volume":"25","author":"YX Zhu","year":"2021","unstructured":"Y.X. Zhu, H.R. Jin, Speaker localization based on audio-visual bimodal fusion. JACIII 25(3), 375\u2013382 (2021). https:\/\/doi.org\/10.20965\/jaciii.2021.p0375","journal-title":"JACIII"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02433-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-023-02433-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02433-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T19:07:11Z","timestamp":1696532831000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-023-02433-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,28]]},"references-count":25,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["2433"],"URL":"https:\/\/doi.org\/10.1007\/s00034-023-02433-z","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2023,6,28]]},"assertion":[{"value":"5 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared that they have no conflict of interest to this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}