{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:04:31Z","timestamp":1760709871718,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,4,3]],"date-time":"2019-04-03T00:00:00Z","timestamp":1554249600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s00034-019-01103-3","type":"journal-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T05:42:54Z","timestamp":1554356574000},"page":"3548-3572","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Integrating DNN\u2013HMM Technique with Hierarchical Multi-layer Acoustic Model for Text-Dependent Speaker Verification"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6903-1943","authenticated-orcid":false,"given":"Mohammad Azharuddin","family":"Laskar","sequence":"first","affiliation":[]},{"given":"Rabul Hussain","family":"Laskar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,4,3]]},"reference":[{"issue":"6","key":"1103_CR1","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s00521-016-2501-7","volume":"29","author":"H Ali","year":"2018","unstructured":"H. Ali, S.N. Tran, E. Benetos, A.S.D.A. Garcez, Speaker recognition with hybrid features from a deep belief network. Neural Comput. Appl. 29(6), 13\u201319 (2018)","journal-title":"Neural Comput. Appl."},{"key":"1103_CR2","unstructured":"O. Buyuk, Telephone-based text-dependent speaker verification. Ph.D. Thesis (2011)"},{"key":"1103_CR3","doi-asserted-by":"crossref","unstructured":"L. Chen, Y. Zhao, S.X. Zhang, J. Li, G. Ye, F. Soong, Exploring sequential characteristics in speaker bottleneck feature for text-dependent speaker verification, in Acoustics, Speech and Signal Processing (ICASSP) (2017)","DOI":"10.1109\/ICASSP.2018.8462467"},{"key":"1103_CR4","doi-asserted-by":"crossref","unstructured":"N. Chen, Y. Qian, K. Yu, Multi-task learning for text-dependent speaker verification, in International Speech Communication Association (Interspeech) (2015)","DOI":"10.21437\/Interspeech.2015-81"},{"key":"1103_CR5","unstructured":"S. Dey, S. Madikeri, M. Ferras, P. Motlicek, Deep neural network based posteriors for text-dependent speaker verification, in Acoustics, Speech and Signal Processing (ICASSP) (2016), pp. 5050\u20135054"},{"key":"1103_CR6","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.specom.2017.01.009","volume":"88","author":"S Dey","year":"2017","unstructured":"S. Dey, P. Motlicek, S. Madikeri, M. Ferras, Template-matching for text-dependent speaker verification. Speech Commun. 88, 96\u2013105 (2017)","journal-title":"Speech Commun."},{"key":"1103_CR7","doi-asserted-by":"crossref","unstructured":"T. Fu, Y. Qian, Y. Liu, K. Yu, Tandem deep features for text-dependent speaker verification, in International Speech Communication Association (Interspeech) (2014)","DOI":"10.21437\/Interspeech.2014-329"},{"key":"1103_CR8","doi-asserted-by":"crossref","unstructured":"C. Hanil\u00e7i, H. \u00c7elikta\u015f, Turkish text-dependent speaker verification using i-vector\/PLDA approach, in 26th Signal Processing and Communications Applications Conference (SIU) (IEEE, 2018)","DOI":"10.1109\/SIU.2018.8404605"},{"key":"1103_CR9","unstructured":"G. Heigold, I. Moreno, S. Bengio, N. Shazeer, End-to-end text-dependent speaker verification, in Acoustics, Speech and Signal Processing (ICASSP) (2016), pp. 5115\u20135119"},{"issue":"6","key":"1103_CR10","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"G. Hinton, L. Deng, D. Yu, G.E. Dahl, A.R. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T.N. Sainath, B. Kingsbury, Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"1103_CR11","unstructured":"P. Kenny, T. Stafylakis, J. Alam, P. Ouellet, M. Kockmann, Joint factor analysis for text-dependent speaker verification, in Proceedings of Odyssey Workshop (2014), pp. 1\u20138"},{"key":"1103_CR12","doi-asserted-by":"crossref","unstructured":"T. Kinnunen, Designing a speaker-discriminative adaptive filter bank for speaker recognition, in International Conference on Spoken Language Processing (2002)","DOI":"10.21437\/ICSLP.2002-630"},{"key":"1103_CR13","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.patrec.2014.01.008","volume":"42","author":"M L\u00e4ngkvist","year":"2014","unstructured":"M. L\u00e4ngkvist, L. Karlsson, A. Loutfi, A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognit. Lett. 42, 11\u201324 (2014)","journal-title":"Pattern Recognit. Lett."},{"key":"1103_CR14","unstructured":"A. Larcher, J.F. Bonastre, J.S. Mason, Reinforced temporal structure information for embedded utterance-based speaker recognition, in International Speech and Communication Association (Interspeech) (2008), pp. 371\u2013374"},{"key":"1103_CR15","unstructured":"A. Larcher, K.A. Lee, B. Ma, H. Li, Modelling the alternative hypothesis for text-dependent speaker verification, in Acoustics, Speech and Signal Processing (ICASSP) (2014), pp. 734\u2013738"},{"key":"1103_CR16","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2014.03.001","volume":"60","author":"A Larcher","year":"2014","unstructured":"A. Larcher, K.A. Lee, B. Ma, H. Li, Text-dependent speaker verification: classifiers, databases and RSR2015. Speech Commun. 60, 56\u201377 (2014)","journal-title":"Speech Commun."},{"issue":"1","key":"1103_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0167-6393(97)00021-6","volume":"22","author":"RP Lippmann","year":"1997","unstructured":"R.P. Lippmann, Speech recognition by machines and humans. Speech Commun. 22(1), 1\u201315 (1997)","journal-title":"Speech Commun."},{"key":"1103_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2015.07.003","volume":"73","author":"Y Liu","year":"2015","unstructured":"Y. Liu, Y. Qian, N. Chen, T. Fu, Y. Zhang, K. Yu, Deep feature for text-dependent speaker verification. Speech Commun. 73, 1\u201313 (2015)","journal-title":"Speech Commun."},{"key":"1103_CR19","unstructured":"National Institute of Standards and Technology, Speaker recognition evaluation. http:\/\/www.nist.gov\/speech\/tests\/spk . Accessed Sept 2015"},{"key":"1103_CR20","unstructured":"T.N. Sainath, B. Kingsbury, B. Ramabhadran, Improving training time of deep belief networks through hybrid pre-training and larger batch sizes, in Proceedings of NIPS Workshop on Log-Linear Models (2012)"},{"issue":"7","key":"1103_CR21","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.1007\/s00521-011-0620-8","volume":"21","author":"M Sheikhan","year":"2012","unstructured":"M. Sheikhan, D. Gharavian, F. Ashoftedel, Using DTW neural-based MFCC warping to improve emotional speech recognition. Neural Comput. Appl. 21(7), 1765\u20131773 (2012)","journal-title":"Neural Comput. Appl."},{"key":"1103_CR22","unstructured":"D. Snyder, SRE16 Xvector Model 1a. http:\/\/kaldi-asr.org\/models.html . Accessed Dec 2018"},{"key":"1103_CR23","unstructured":"D. Snyder, D. Garcia-Romero, D. Povey, S. Khudanpur, Deep neural network embeddings for text-independent speaker verification, in Proceedings of Interspeech (2017), pp. 999\u20131003"},{"key":"1103_CR24","doi-asserted-by":"crossref","unstructured":"D. Snyder, D. Garcia-Romero, G. Sell, D. Povey, S. Khudanpur, X-vectors: robust DNN embeddings for speaker recognition, in ICASSP (2018) (Submitted)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"1103_CR25","doi-asserted-by":"crossref","unstructured":"T. Stafylakis, P. Kenny, P. Ouellet, J. Perez, M. Kockmann, P. Dumouchel, Text-dependent speaker recognition using PLDA with uncertainty propagation, in Matrix, vol. 500 (2013)","DOI":"10.21437\/Interspeech.2013-691"},{"key":"1103_CR26","unstructured":"E. Variani, X. Lei, E. McDermott, I. Lopez-Moreno, J. Gonzalez-Dominguez, Deep neural networks for small footprint text-dependent speaker verification, in Acoustics, Speech and Signal Processing (ICASSP), vol. 14 (2014), pp. 4052\u20134056"},{"issue":"9","key":"1103_CR27","doi-asserted-by":"publisher","first-page":"3393","DOI":"10.1007\/s00034-015-0206-2","volume":"35","author":"Y Xu","year":"2016","unstructured":"Y. Xu, I. McLoughlin, Y. Song, K. Wu, Improved i-vector representation for speaker diarization. Circuits Syst. Signal Process. 35(9), 3393\u20133404 (2016)","journal-title":"Circuits Syst. Signal Process."},{"key":"1103_CR28","volume-title":"The HTK Hidden Markov Model Toolkit: Design and Philosophy","author":"SJ Young","year":"1993","unstructured":"S.J. Young, S. Young, The HTK Hidden Markov Model Toolkit: Design and Philosophy, vol. 28 (University of Cambridge, Department of Engineering, Cambridge, 1993)"},{"issue":"7","key":"1103_CR29","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1109\/TASLP.2017.2694708","volume":"25","author":"H Zeinali","year":"2017","unstructured":"H. Zeinali, H. Sameti, L. Burget, HMM-based phrase-independent i-vector extractor for text-dependent speaker verification. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(7), 1421\u20131435 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"1103_CR30","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.csl.2017.04.005","volume":"46","author":"H Zeinali","year":"2017","unstructured":"H. Zeinali, H. Sameti, L. Burget, Text-dependent speaker verification based on i-vectors, neural networks and hidden Markov models. Comput. Speech Lang. 46, 53\u201371 (2017)","journal-title":"Comput. Speech Lang."},{"key":"1103_CR31","doi-asserted-by":"publisher","first-page":"4034","DOI":"10.1007\/s00034-018-0757-0","volume":"37","author":"Z Zhou","year":"2018","unstructured":"Z. Zhou, G. Huang, H. Chen, J. Gao, Automatic radar waveform recognition based on deep convolutional denoising auto-encoders. Circuits Syst. Signal Process. 37, 4034\u20134048 (2018)","journal-title":"Circuits Syst. Signal Process."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01103-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-019-01103-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01103-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T06:12:01Z","timestamp":1663222321000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-019-01103-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,3]]},"references-count":31,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["1103"],"URL":"https:\/\/doi.org\/10.1007\/s00034-019-01103-3","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2019,4,3]]},"assertion":[{"value":"1 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}