{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T00:28:08Z","timestamp":1768004888775,"version":"3.49.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T00:00:00Z","timestamp":1623110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T00:00:00Z","timestamp":1623110400000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s10772-021-09805-3","type":"journal-article","created":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T04:02:47Z","timestamp":1623124967000},"page":"993-1006","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Text-dependent and text-independent speaker recognition of reverberant speech based on CNN"],"prefix":"10.1007","volume":"24","author":[{"given":"Samia Abd","family":"El-Moneim","sequence":"first","affiliation":[]},{"given":"Ahmed","family":"Sedik","sequence":"additional","affiliation":[]},{"given":"M. A.","family":"Nassar","sequence":"additional","affiliation":[]},{"given":"Adel S.","family":"El-Fishawy","sequence":"additional","affiliation":[]},{"given":"A. M.","family":"Sharshar","sequence":"additional","affiliation":[]},{"given":"Shaimaa E. A.","family":"Hassan","sequence":"additional","affiliation":[]},{"given":"Adel Zaghloul","family":"Mahmoud","sequence":"additional","affiliation":[]},{"given":"Moawd I.","family":"Dessouky","sequence":"additional","affiliation":[]},{"given":"Ghada M.","family":"El-Banby","sequence":"additional","affiliation":[]},{"given":"Fathi E. Abd","family":"El-Samie","sequence":"additional","affiliation":[]},{"given":"El-Sayed M.","family":"El-Rabaie","sequence":"additional","affiliation":[]},{"given":"Badawi","family":"Neyazi","sequence":"additional","affiliation":[]},{"given":"H. S.","family":"Seddeq","sequence":"additional","affiliation":[]},{"given":"Nabil A.","family":"Ismail","sequence":"additional","affiliation":[]},{"given":"Ashraf A. M.","family":"Khalaf","sequence":"additional","affiliation":[]},{"given":"G. S. M.","family":"Elabyad","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,8]]},"reference":[{"key":"9805_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9698-5","volume-title":"Information Security for Automatic Speaker Identification.\u201d Springer briefs in electrical and computer engineering","author":"FE Abd El-Samie","year":"2011","unstructured":"Abd El-Samie, F. E. (2011). Information Security for Automatic Speaker Identification.\u201d Springer briefs in electrical and computer engineering. Berlin: Springer."},{"key":"9805_CR3","first-page":"2726","volume":"1","author":"T Barbu","year":"2007","unstructured":"Barbu, T. (2007). A supervised text-independent speaker recognition approach. International Journal of Electronics and Communication Engineering, 1, 2726\u20132730.","journal-title":"International Journal of Electronics and Communication Engineering"},{"key":"9805_CR4","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.apacoust.2016.07.014","volume":"114","author":"Y Hioka","year":"2016","unstructured":"Hioka, Y., Tang, J. W., & Wan, J. (2016). Effect of adding artificial reverberation to speech-like masking sound. Applied Acoustics, 114, 171\u2013178.","journal-title":"Applied Acoustics"},{"issue":"7","key":"9805_CR5","first-page":"325","volume":"5","author":"VA Hiremani","year":"2015","unstructured":"Hiremani, V. A. (2015). Speaker recognition: A survey. International Journal of Emerging Technology and Advanced Engineering, 5(7), 325\u2013335.","journal-title":"International Journal of Emerging Technology and Advanced Engineering"},{"key":"9805_CR6","unstructured":"KINGMA, Diederik P., & Jimmy, B. A. (2014). Adam: A method for stochastic Ooptimization. arXiv preprint arXiv:1412.6980.\u200f"},{"issue":"11","key":"9805_CR7","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"9805_CR8","doi-asserted-by":"crossref","unstructured":"Lukic, Y., Vogt, C., Durr, O., & Stadelmann, T. (2016). Speaker identification and clustering using convolutional neural networks. In IEEE international workshop on machine learning for signal processing (pp. 13\u201316).","DOI":"10.1109\/MLSP.2016.7738816"},{"key":"9805_CR9","doi-asserted-by":"crossref","unstructured":"Lukic, Y., Vogt, C. Durr, O., Stadelmann, T. (2016). Speaker identification and clustering using convolutional neural networks. In IEEE international workshop on machine learning for signal processing, Sept. 13\u201316, 2016.","DOI":"10.1109\/MLSP.2016.7738816"},{"key":"9805_CR1","unstructured":"Magic Data Technology Co., Ltd. Retrieved May 2019 from http:\/\/www.imagicdatatech.com\/index.php\/home\/dataopensource\/data_info\/id\/101."},{"key":"9805_CR10","first-page":"2151","volume":"2","author":"L Muda","year":"2010","unstructured":"Muda, L., Begam, M., & Elamvazuthi, I. (2010). Voice Recognition Algorithms using Mel-Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) techniques. Journal of Computing, 2, 2151\u20139617.","journal-title":"Journal of Computing"},{"key":"9805_CR11","doi-asserted-by":"crossref","unstructured":"Nayana P. K. et al. (2017). Comparison of text independent speaker identification systems using GMM and i-vector methods. In 7th international conference on advances in computing & communications, ICACC-2017 India (pp.47\u201354), August 2017.","DOI":"10.1016\/j.procs.2017.09.075"},{"key":"9805_CR12","doi-asserted-by":"crossref","unstructured":"Neammalai, P., Phimoltares, S, & Lursinsap, C. (2015). Speech and music classification using hybrid form of spectrogram and Fourier transformation. In IEEE international conference, Siem Reap, Cambodia, accepted 16 February 2015","DOI":"10.1109\/APSIPA.2014.7041658"},{"key":"9805_CR13","first-page":"319","volume":"33","author":"K Nishanth","year":"2015","unstructured":"Nishanth, K., & Karthik, G. (2015). Identification of diabetic maculopathy stages using fundus images. Journal of Molecular Image and Dynamics, 33, 319\u2013119.","journal-title":"Journal of Molecular Image and Dynamics"},{"key":"9805_CR14","doi-asserted-by":"crossref","unstructured":"Oppenheim, A. V. (1970). Speech spectrograms using the fast Fourier transform. In IEEE spectrum, international conference, September 1970.","DOI":"10.1109\/MSPEC.1970.5213512"},{"key":"9805_CR15","doi-asserted-by":"crossref","unstructured":"Palaz, D., Magimai-Doss, M., & Collobert, R. (2015). Analysis of CNN-based speech recognition system using raw speech as Iinput, Interspeech (pp. 11\u201315).","DOI":"10.21437\/Interspeech.2015-3"},{"key":"9805_CR16","doi-asserted-by":"crossref","unstructured":"Parada, P. P., Sharma, D., Naylor, P. A., & Waterschoot, T. V. (2014). Reverberant speech recognition: A phoneme analysis. In Proceedings on 2014 IEEE global conference signal information process (pp. 567\u2013571).","DOI":"10.1109\/GlobalSIP.2014.7032181"},{"issue":"04","key":"9805_CR17","first-page":"709","volume":"03","author":"JB Ramgire","year":"2016","unstructured":"Ramgire, J. B., & Jagdale, S. M. (2016). A survey on speaker recognition with various feature extraction and classification techniques. International Research Journal of Engineering and Technology, 03(04), 709\u2013712.","journal-title":"International Research Journal of Engineering and Technology"},{"key":"9805_CR18","doi-asserted-by":"crossref","unstructured":"Ranzato, M. A., Huang, F. J., Boureau, Y. L., & LeCun, Y. (2007). Unsupervised learning of invariant feature hierarchies with applications to object recognition. In Computer vision and pattern recognition, 2007. CVPR'07. IEEE conference (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383157"},{"key":"9805_CR19","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/978-3-642-17641-8_18","volume":"123","author":"Z Saquib","year":"2010","unstructured":"Saquib, Z., Salam, N., Nair, R. P., Pandey, N., & Joshi, A. (2010). A survey on automatic speaker recognition systems. Communications in Computer and Information Science, 123, 134\u2013145.","journal-title":"Communications in Computer and Information Science"},{"key":"9805_CR20","unstructured":"Su, H. (2018). Combining speech and speaker recognition: A joint modeling approach. Electrical Engineering and Computer Sciences, 10 August 2018."},{"issue":"250\u2013271","key":"9805_CR21","first-page":"2017","volume":"90","author":"SS Tirumala","year":"2017","unstructured":"Tirumala, S. S., Shahamiri, S. R., Garhwal, A. S., & Wang, R. (2017). Speaker identification features extraction methods: A systematic review. Expert Systems with Applications, 90(250\u2013271), 2017.","journal-title":"Expert Systems with Applications"},{"key":"9805_CR22","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/MCAS.2011.941079","volume":"11","author":"R Togneri","year":"2011","unstructured":"Togneri, R., & Pullella, D. (2011). An overview of speaker identification: Accuracy and robustness issues. IEEE Circuits and Systems Magazine, 11, 23\u201361.","journal-title":"IEEE Circuits and Systems Magazine"},{"key":"9805_CR23","unstructured":"Unoki, M., & Hiramatsu, S. (2008). MTF-based method of blind estimation of reverberation in room acoustics. In: 16th European signal processing conference (EUSIPCO 2008), August 2008."},{"issue":"9","key":"9805_CR24","first-page":"1975","volume":"7","author":"Y Wang","year":"2012","unstructured":"Wang, Y. (2012). Robust text-independent speaker identification in a time-varying noisy environment. Journal of Software, 7(9), 1975\u20131980.","journal-title":"Journal of Software"},{"key":"9805_CR25","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1109\/89.841209","volume":"8","author":"B Yegnanarayana","year":"2000","unstructured":"Yegnanarayana, B., & Murthy, P. S. (2000). Enhancement of reverberant speech using LP residual signal. IEEE Transactions on Speech Audio Processing, 8, 267\u2013281.","journal-title":"IEEE Transactions on Speech Audio Processing"},{"issue":"1\u201311","key":"9805_CR26","first-page":"2016","volume":"99","author":"C Zhang","year":"2016","unstructured":"Zhang, C., Yu, C., & Hansen, J. H. L. (2016). An investigation of deep learning frameworks for speaker verification anti-spoofing. IEEE Journal of Selected Topics in Signal Processing, 99(1\u201311), 2016.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09805-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09805-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09805-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T10:22:31Z","timestamp":1637230951000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09805-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,8]]},"references-count":26,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["9805"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09805-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,8]]},"assertion":[{"value":"2 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}