{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T21:03:44Z","timestamp":1730322224013,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,9,25]]},"DOI":"10.1145\/3386164.3389100","type":"proceedings-article","created":{"date-parts":[[2020,6,7]],"date-time":"2020-06-07T01:30:15Z","timestamp":1591493415000},"page":"1-6","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Image Approach to Speech Recognition on CNN"],"prefix":"10.1145","author":[{"given":"Muhammadjon","family":"Musaev","sequence":"first","affiliation":[{"name":"Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan"}]},{"given":"Ilyos","family":"Khujayorov","sequence":"additional","affiliation":[{"name":"Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan"}]},{"given":"Mannon","family":"Ochilov","sequence":"additional","affiliation":[{"name":"Computer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan"}]}],"member":"320","published-online":{"date-parts":[[2020,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SISY.2018.8524677"},{"volume-title":"2017 International Conference on Platform Technology and Service, PlatCon 2017 - Proceedings.","author":"Badshah A.M.","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","unstructured":"Adrian Rosebrock. Deep Learning for Computer Vision with Python Starter Bundle. 1st Edition (1.2.2). PyImageSearch.com. 2017. Adrian Rosebrock. Deep Learning for Computer Vision with Python Starter Bundle. 1st Edition (1.2.2). PyImageSearch.com. 2017."},{"key":"e_1_3_2_1_4_1","unstructured":"Al-Darkazali Mohammed. Image processing methods to segment speech spectrograms for word level recognition. Doctoral thesis (PhD) University of Sussex. (2017). Al-Darkazali Mohammed. Image processing methods to segment speech spectrograms for word level recognition. Doctoral thesis (PhD) University of Sussex. (2017)."},{"key":"e_1_3_2_1_5_1","unstructured":"Andrew Ng Yan Zhang. Speech Recognition Using Deep Learning Algorithms. Published in 2013. Andrew Ng Yan Zhang. Speech Recognition Using Deep Learning Algorithms. Published in 2013."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"B.D. Sarma S.R.M. Prasanna. Acoustic--Phonetic Analysis for Speech Recognition: A Review. IETE Technical Review (Institution of Electronics and Telecommunication Engineers India). 2018. pp.305--327. B.D. Sarma S.R.M. Prasanna. Acoustic--Phonetic Analysis for Speech Recognition: A Review. IETE Technical Review (Institution of Electronics and Telecommunication Engineers India). 2018. pp.305--327.","DOI":"10.1080\/02564602.2017.1293570"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5220\/0006653001900195"},{"key":"e_1_3_2_1_8_1","first-page":"1","volume-title":"2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings.","author":"Polap D.","year":"2018"},{"issue":"2","key":"e_1_3_2_1_9_1","first-page":"130","article-title":"Spectrogram Image Feature for Sound Event Classification","volume":"18","author":"H.","journal-title":"Mismatched Conditions. IEEE Signal Processing Letters"},{"key":"e_1_3_2_1_10_1","unstructured":"Diederik P. Kingma Jimmy Lei Ba. ADAM: A Method for stochastic optimization. Published as a conference paper at ICLR 2015. Diederik P. Kingma Jimmy Lei Ba. ADAM: A Method for stochastic optimization. Published as a conference paper at ICLR 2015."},{"key":"e_1_3_2_1_11_1","unstructured":"Fisher William M.; Doddington George R.; Goudie-Marshall Kathleen M. (1986). The DARPA Speech Recognition Research Database: Specifications and Status. pp. 93--99. Fisher William M.; Doddington George R.; Goudie-Marshall Kathleen M. (1986). The DARPA Speech Recognition Research Database: Specifications and Status. pp. 93--99."},{"issue":"1","key":"e_1_3_2_1_12_1","first-page":"1929","article-title":"A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Hinton Geoffrey E.","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_13_1","first-page":"620","article-title":"A novel approach to isolated word recognition","author":"M.B.","year":"1999","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"H. R. Hahnloser R. Sarpeshkar M. A. Mahowald R. J. Douglas & H. S. Seung (2000). Erratum: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405(6789) 947--951. doi:10.1038\/35016072. H. R. Hahnloser R. Sarpeshkar M. A. Mahowald R. J. Douglas & H. S. Seung (2000). Erratum: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405(6789) 947--951. doi:10.1038\/35016072.","DOI":"10.1038\/35016072"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Ibrahim Patel Dr. Y. Srinivas Rao. Speech recognition using HMM with MFCC-an analysis using frequency Spectral decomposing technique. Signal & Image Processing: An International Journal (SIPIJ) Vol.1 No.2 December 2010. Ibrahim Patel Dr. Y. Srinivas Rao. Speech recognition using HMM with MFCC-an analysis using frequency Spectral decomposing technique. Signal & Image Processing: An International Journal (SIPIJ) Vol.1 No.2 December 2010.","DOI":"10.5121\/sipij.2010.1209"},{"key":"e_1_3_2_1_16_1","first-page":"351","article-title":"Gender Identification using MFCC for Telephone Applications - A Comparative Study","volume":"3","author":"J.","year":"2015","journal-title":"International Journal of Computer Science and Electronics Engineering"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.932166"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"J. Padmanabhan M.J.J. Premkumar. Machine learning in automatic speech recognition: A survey. IETE Technical Review (Institution of Electronics and Telecommunication Engineers India).2015. pp. 240--251. J. Padmanabhan M.J.J. Premkumar. Machine learning in automatic speech recognition: A survey. IETE Technical Review (Institution of Electronics and Telecommunication Engineers India).2015. pp. 240--251.","DOI":"10.1080\/02564602.2015.1010611"},{"key":"e_1_3_2_1_19_1","first-page":"336","volume-title":"Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI.","author":"Zhang J.","year":"2018"},{"key":"e_1_3_2_1_20_1","unstructured":"Jaron Collis. \"Glossary of Deep Learning: Batch Normalization\". medium.com. Retrieved 24 April 2018. Jaron Collis. \"Glossary of Deep Learning: Batch Normalization\". medium.com. Retrieved 24 April 2018."},{"volume-title":"5th European Conference of the International Federation for Medical and Biological Engineering. Springer","year":"2011","author":"M.","key":"e_1_3_2_1_21_1"},{"key":"e_1_3_2_1_22_1","unstructured":"Lonce Wyse. Audio Spectrogram Representations for Processing with Convolutional Neural Networks. Published 2017 in ArXiv.org. Lonce Wyse. Audio Spectrogram Representations for Processing with Convolutional Neural Networks. Published 2017 in ArXiv.org."},{"volume-title":"Conference: International Conference on Intelligent Decision Technologies. DOI: 10","author":"Yuan Longhao","key":"e_1_3_2_1_23_1"},{"volume-title":"Published in IEEE: Proceedings of Third International Conference on Signal Processing (ICSP'96)","author":"Ahmadi M","key":"e_1_3_2_1_24_1"},{"key":"e_1_3_2_1_25_1","unstructured":"M.M.Musaev U.A.Berdanov M.F.Rahimov Shukurov K.E \"Parallel algorithms for acoustic processing of speech signals\" International Conference on Signal and Image Processing (ICSIP 2016). China during August 13--15. M.M.Musaev U.A.Berdanov M.F.Rahimov Shukurov K.E \"Parallel algorithms for acoustic processing of speech signals\" International Conference on Signal and Image Processing (ICSIP 2016). China during August 13--15."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1561\/2000000004"},{"key":"e_1_3_2_1_27_1","first-page":"20","article-title":"Constructing accurate and robust HMM\/GMM models for an Arabic speech recognition system","author":"Khelifa Mohamed O.M.","year":"2017","journal-title":"International Journal of Speech Technology."},{"volume-title":"NO.","year":"2014","author":"Abdel-Hamid Ossama","key":"e_1_3_2_1_28_1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40595-016-0071-3"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2012-20"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2209826.2210809"},{"key":"e_1_3_2_1_32_1","unstructured":"Sergey Ioffe Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv.org > cs > arXiv:1502.03167. Sergey Ioffe Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv.org > cs > arXiv:1502.03167."},{"volume-title":"Proceeding of 5th International Seminar on New Paradigm and Innovation on Natural Science and Its Application (5th ISNPINSA)","year":"2015","author":"Endah Sukmawati Nur","key":"e_1_3_2_1_33_1"},{"volume-title":"SYSTEM","year":"2016","author":"Mokashi V.V.","key":"e_1_3_2_1_34_1"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.08.250"},{"volume-title":"Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair. Conference: Proceedings of the 27th International Conference on Machine Learning (ICML-10)","year":"2010","author":"Nair Vinod","key":"e_1_3_2_1_36_1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"issue":"1","key":"e_1_3_2_1_38_1","first-page":"69","article-title":"Matching demodulation transform and synchro squeezing in time-frequency analysis","volume":"62","year":"2013","journal-title":"IEEE Trans. Signal Process."},{"volume-title":"Deep Sparse Rectifier Neural Networks. Conference: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS).","year":"2015","author":"Glorot X.","key":"e_1_3_2_1_39_1"},{"volume":"1","volume-title":"Nanfeng Xiao. Speech Recognition Method Based on Spectrogram. Proceedings of the International Conference on Mechatronics and Intelligent Robotics (ICMIR2017)","author":"Li Yingying","key":"e_1_3_2_1_40_1"}],"event":{"name":"ISCSIC 2019: 2019 3rd International Symposium on Computer Science and Intelligent Control","acronym":"ISCSIC 2019","location":"Amsterdam Netherlands"},"container-title":["Proceedings of the 2019 3rd International Symposium on Computer Science and Intelligent Control"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386164.3389100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,14]],"date-time":"2023-01-14T23:44:57Z","timestamp":1673739897000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386164.3389100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,25]]},"references-count":40,"alternative-id":["10.1145\/3386164.3389100","10.1145\/3386164"],"URL":"https:\/\/doi.org\/10.1145\/3386164.3389100","relation":{},"subject":[],"published":{"date-parts":[[2019,9,25]]},"assertion":[{"value":"2020-06-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}