{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T02:30:08Z","timestamp":1709260208541},"reference-count":32,"publisher":"Pleiades Publishing Ltd","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Autom Remote Control"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1134\/s0005117922060042","type":"journal-article","created":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T11:10:05Z","timestamp":1657019405000},"page":"857-868","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Method for Reducing the Feature Space Dimension in Speech Emotion Recognition Using Convolutional Neural Networks"],"prefix":"10.1134","volume":"83","author":[{"given":"A. O.","family":"Iskhakova","sequence":"first","affiliation":[]},{"given":"D. A.","family":"Vol\u2019f","sequence":"additional","affiliation":[]},{"given":"R. V.","family":"Meshcheryakov","sequence":"additional","affiliation":[]}],"member":"137","published-online":{"date-parts":[[2022,7,5]]},"reference":[{"key":"2287_CR1","doi-asserted-by":"crossref","unstructured":"Meshcheryakov, R.V. and Bondarenko, V.P., Dialog as a basis for\nconstructing speech systems, Kibern. Sist. Anal., 2008,\nno. 2, pp. 30\u201341.","DOI":"10.1007\/s10559-008-0018-5"},{"key":"2287_CR2","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/978-3-319-57348-9_12","volume":"989","author":"M. Papakotas","year":"2016","unstructured":"Papakotas, M., Siantikos, G., Giannakopoulos, T., et al., IoT applications with\n5G connectivity in medical tourism sector management: third-party service scenarios, GeNeDis 2016. Adv. Exp. Med. Biol., 2016, vol. 989, pp. 155\u2013164.\nhttps:\/\/doi.org\/10.1007\/978-3-319-57348-9_12","journal-title":"GeNeDis 2016. Adv. Exp. Med. Biol."},{"key":"2287_CR3","unstructured":"Okhapkin, V., Okhapkina, E., Iskhakova, A. et. al., Application of neural\nnetwork modeling in the task of destructive content detecting, CEUR\nWorkshop Proc. Proc. 3rd Int. Conf. R. Piotrowski\u2019s Read. Lang. Eng. Appl. Linguist.,\nPRLEAL 2019 (St. Petersburg, Russia, 2020), pp. 85\u201394."},{"key":"2287_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1088\/1742-6596\/1203\/1\/012065","volume":"1203","author":"A. Iskhakova","year":"2019","unstructured":"Iskhakova, A., Iskhakov, A., and Meshcheryakov, R., Research of the\nestimated emotional components for the content analysis, J. Phys.:\nConf. Series, 2019, vol. 1203, pp. 1\u201310.\nhttps:\/\/doi.org\/10.1088\/1742-6596\/1203\/1\/012065","journal-title":"J. Phys.: Conf. Series"},{"key":"2287_CR5","doi-asserted-by":"publisher","unstructured":"Scheirer, E. and Slaney, M., Construction and evaluation of a robust\nmultifeature speech\/music discriminator, IEEE Int. Conf. Acoust.\nSpeech Signal Process. (Munich, Germany, 2002), pp. 1331\u20131334.\nhttps:\/\/doi.org\/10.1109\/ICASSP.1997.596192","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"2287_CR6","doi-asserted-by":"publisher","unstructured":"Hossan, M.A., Memon, S., and Gregory, M.A., A novel approach for MFCC\nfeature extraction, 2010 4th Int. Conf. Signal Process. Commun.\nSyst. (Gold Coast, QLD, Australia, 2010), pp. 1\u20135.\nhttps:\/\/doi.org\/10.1109\/ICSPCS.2010.5709752","DOI":"10.1109\/ICSPCS.2010.5709752"},{"key":"2287_CR7","unstructured":"Logan, B., Mel frequency cepstral coefficients for music modeling.\n https:\/\/ismir2000.ismir.net\/papers\/logan_abs.pdf\n."},{"key":"2287_CR8","unstructured":"Rabiner, L.R. and Juang, B.H., Fundamental of\nSpeech Recognition, Prentice Hall, 1993."},{"issue":"4","key":"2287_CR9","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"T.L. Nwe","year":"2003","unstructured":"Nwe, T.L., Foo, S.W., and Silva, L.C., Speech emotion recognition using\nhidden Markov models, Speech Commun., 2003, vol. 41,\nno. 4, pp. 603\u2013623.\nhttps:\/\/doi.org\/10.1016\/S0167-6393(03)00099-2","journal-title":"Speech Commun."},{"key":"2287_CR10","unstructured":"Zou, D., Niu, Y., He, Z., and Tan, H., A breakthrough in speech emotion\nrecognition using deep retinal convolution neural networks. ."},{"key":"2287_CR11","doi-asserted-by":"publisher","unstructured":"Lim, W., Jang, D., and Lee, T., Speech emotion recognition using\nconvolutional and recurrent neural networks, 2016 Asia-Pac. Signal\nInf. Process. Assoc. Annu. Summit Conf. (APSIPA) (Jeju, Korea (South), 2016),\npp. 1\u20134.\nhttps:\/\/doi.org\/10.1109\/APSIPA.2016.7820699","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"2287_CR12","doi-asserted-by":"publisher","unstructured":"Prasomphan, S., Improvement of speech emotion recognition with neural\nnetwork classifier by using speech spectrogram, 2015 Int. Conf. Syst.\nSignals Image Process. (IWSSIP) (London, UK, 2015), pp. 73\u201376.\nhttps:\/\/doi.org\/10.1109\/IWSSIP.2015.7314180","DOI":"10.1109\/IWSSIP.2015.7314180"},{"key":"2287_CR13","doi-asserted-by":"publisher","first-page":"53","DOI":"10.15622\/sp.58.3","volume":"3(58)","author":"E. Pakoci","year":"2018","unstructured":"Pakoci, E., Popovic, B., and Pekar, D., Improvements in Serbian speech\nrecognition using sequence-trained deep neural networks, SPIIRAS\nProc., 2018, vol. 3(58), pp. 53\u201376.\nhttps:\/\/doi.org\/10.15622\/sp.58.3","journal-title":"SPIIRAS Proc."},{"key":"2287_CR14","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y. Bengio","year":"2015","unstructured":"Bengio, Y. and Hinton, G., Deep learning, Nature, 2015, vol. 521, pp. 436\u2013444.\nhttps:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"key":"2287_CR15","doi-asserted-by":"publisher","unstructured":"Valenti, M., Squartini, S., Diment, A., et. al., A convolutional neural network\napproach for acoustic scene classification, 2017 Int. Joint Conf.\nNeural Networks (IJCNN) (Anchorage, AK, 2017), pp. 1547\u20131554.\nhttps:\/\/doi.org\/10.1109\/IJCNN.2017.7966035","DOI":"10.1109\/IJCNN.2017.7966035"},{"key":"2287_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/e21050479","volume":"21(5) 479","author":"N. Hajarolasvadi","year":"2019","unstructured":"Hajarolasvadi, N. and Demirel, H., 3D CNN-based speech emotion recognition\nusing K-means clustering and spectrograms, Entropy,\n2019, vol. 21(5) 479, pp. 1\u201317.\nhttps:\/\/doi.org\/10.3390\/e21050479","journal-title":"Entropy"},{"key":"2287_CR17","unstructured":"Niu, Y., Zou, D., Niu, Y., He, Z., and Tan, H., A breakthrough in speech\nemotion recognition using deep retinal convolution neural networks, Preprint. ."},{"key":"2287_CR18","doi-asserted-by":"publisher","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., and Weiss, B., A\ndatabase of German emotional speech, INTERSPEECH\n2005\u2014Eurospeech. 9th Eur. Conf. Speech Commun. Technol. (Lisbon,\nPortugal, 2005), pp. 1\u20134.\nhttps:\/\/doi.org\/10.21437\/Interspeech.2005-446","DOI":"10.21437\/Interspeech.2005-446"},{"key":"2287_CR19","unstructured":"Haq, S., Jackson, P.J.B., and Edge, J.D., Audio-visual feature selection and\nreduction for emotion, Proc. Int. Conf. Auditory-Visual Speech\nProcess. (Tangalooma Wild Dolphin Resort, Moreton Island, Queensland, Australia,\n2008), pp. 185\u2013190."},{"key":"2287_CR20","unstructured":"Haq, S. and Jackson, P.J.B., Speaker-dependent audio-visual emotion\nrecognition, Proc. Int. Conf. Auditory-Visual Speech\nProcess. (Norwich, UK, 2009), pp. 53\u201358."},{"key":"2287_CR21","doi-asserted-by":"publisher","unstructured":"Huang, Z., Dong, M., Mao, Q., and Zhan, Y., Speech emotion recognition\nusing CNN, MM\u201914: Proc. 22nd ACM Int. Conf.\nMultimedia (Orlando, Florida, USA, 2014), pp. 801\u2013804.\nhttps:\/\/doi.org\/10.1145\/2647868.2654984","DOI":"10.1145\/2647868.2654984"},{"key":"2287_CR22","doi-asserted-by":"publisher","unstructured":"Prasomphan, S., Improvement of speech emotion recognition with neural\nnetwork classifier by using speech spectrogram, 2015 IEEE Int. Conf.\nSyst. Signals Image Process. (London, UK, 2015), pp. 73\u201376.\nhttps:\/\/doi.org\/10.1109\/IWSSIP.2015.7314180","DOI":"10.1109\/IWSSIP.2015.7314180"},{"key":"2287_CR23","doi-asserted-by":"crossref","unstructured":"Semwal, N., Kumar, A., and Narayanan, S., Automatic speech emotion\ndetection system using multi-domain acoustic feature selection and classification models,\n2017 IEEE Int. Conf. Identity Secur. Behav. Anal.\n(ISBA) (New Delhi, India, 2017), pp. 1\u20136.","DOI":"10.1109\/ISBA.2017.7947681"},{"key":"2287_CR24","unstructured":"Chu, R., Speech emotion recognition with convolutional neural network, 2019. https:\/\/towardsdatascience.com\/speech-emotion-recognition-with-convolution-neuralnetwork-1e6bb7130ce3."},{"key":"2287_CR25","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"Z. Jianfeng","year":"2019","unstructured":"Jianfeng, Z., Mao, X., and Chen, L., Speech emotion recognition using deep\n1D & 2D CNN LSTM networks, Biomed. Signal Process.\nControl, 2019, vol. 47, pp. 312\u2013323.\nhttps:\/\/doi.org\/10.1016\/j.bspc.2018.08.035","journal-title":"Biomed. Signal Process. Control"},{"key":"2287_CR26","unstructured":"Rajan, V., 1D speech emotion recognition, 2021.\n https:\/\/github.com\/vandana-rajan\/1D-Speech-Emotion-Recognition ."},{"key":"2287_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0196391","volume":"13(5)","author":"S.R. Livingstone","year":"2018","unstructured":"Livingstone, S.R. and Russo, F.A., The Ryerson audio-visual database of\nemotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions\nin North American English, PLoS ONE, 2018,\nvol. 13(5), pp. 1\u201335.\nhttps:\/\/doi.org\/10.1371\/journal.pone.0196391","journal-title":"PLoS ONE"},{"key":"2287_CR28","doi-asserted-by":"publisher","unstructured":"Dupuis, K. and Pichora-Fuller, M.K., Toronto emotional speech set (TESS).\nhttps:\/\/doi.org\/10.5683\/SP2\/E8H2MF","DOI":"10.5683\/SP2\/E8H2MF"},{"key":"2287_CR29","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5(4)","author":"H. Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., and et., al., CREMA-D:\ncrowd-sourced emotional multimodal actors dataset, IEEE Trans.\nAffective Comput., 2014, vol. 5(4), pp. 377\u2013390.\nhttps:\/\/doi.org\/10.1109\/TAFFC.2014.2336244","journal-title":"IEEE Trans. Affective Comput."},{"key":"2287_CR30","first-page":"222","volume":"20(3)","author":"E. Franti","year":"2018","unstructured":"Franti, E., Ispas, I., Dragomir, V., et al., Voice based emotion recognition\nwith convolutional neural networks for companion robots, Rom.\nJ. Inf. Sci. Technol., 2018, vol. 20(3), pp. 222\u2013240.","journal-title":"Rom. J. Inf. Sci. Technol."},{"key":"2287_CR31","doi-asserted-by":"publisher","unstructured":"Iskhakova, A., Wolf, D., an Meshcheryakov, R., Automated destructive\nbehavior state detection on the 1D CNN-based voice analysis, Speech\nComput. SPECOM 2020. Lect. Notes Comput. Sci., 2020, vol. 12335, pp. 184\u2013193.\nhttps:\/\/doi.org\/10.1007\/978-3-030-60276-5_19","DOI":"10.1007\/978-3-030-60276-5_19"},{"issue":"1","key":"2287_CR32","first-page":"166","volume":"5","author":"A.O. Iskhakova","year":"2021","unstructured":"Iskhakova, A.O., Wolf, D.A., and Iskhakov, A.Yu., Noninvasive\nbrain\u2013computer interface for robot control, Vysokoproizvod. Vychisl.\nSist. Tekhnol., 2021, vol. 5, no. 1, pp. 166\u2013171.","journal-title":"Vysokoproizvod. Vychisl. Sist. Tekhnol."}],"container-title":["Automation and Remote Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1134\/S0005117922060042.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1134\/S0005117922060042\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1134\/S0005117922060042.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T11:11:02Z","timestamp":1657019462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1134\/S0005117922060042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["2287"],"URL":"https:\/\/doi.org\/10.1134\/s0005117922060042","relation":{},"ISSN":["0005-1179","1608-3032"],"issn-type":[{"value":"0005-1179","type":"print"},{"value":"1608-3032","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]},"assertion":[{"value":"17 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}