{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T13:54:47Z","timestamp":1775742887495,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Singapore","isbn-type":[{"value":"9789811337017","type":"print"},{"value":"9789811337024","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-981-13-3702-4_9","type":"book-chapter","created":{"date-parts":[[2019,1,16]],"date-time":"2019-01-16T10:50:43Z","timestamp":1547635843000},"page":"143-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Natural Language Processing: Speaker, Language, and Gender Identification with LSTM"],"prefix":"10.1007","author":[{"given":"Mohammad K.","family":"Nammous","sequence":"first","affiliation":[]},{"given":"Khalid","family":"Saeed","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,17]]},"reference":[{"key":"9_CR1","unstructured":"Jurafsky, D., Martin, J.H.: Speech and Language Processing, 2nd edn. Pearson Prentice Hall (2008)"},{"issue":"2016","key":"9_CR2","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1613\/jair.4992","volume":"57","author":"Y Goldberg","year":"2016","unstructured":"Goldberg, Y.: A primer on neural network models for natural language processing. J. Artif. Intell. Res. 57(2016), 345\u2013420 (2016)","journal-title":"J. Artif. Intell. Res."},{"issue":"2","key":"9_CR3","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1109\/TIE.2007.891647","volume":"54","author":"K Saeed","year":"2007","unstructured":"Saeed, K., Nammous, M.K.: A speech-and-speaker identification system: feature extraction, description, and classification of speech-signal image. IEEE Trans. Ind. Electron. 54(2), 887\u2013897 (2007)","journal-title":"IEEE Trans. Ind. Electron."},{"key":"9_CR4","first-page":"412","volume-title":"Lecture Notes in Computer Science","author":"Mohammad Kheir Nammous","year":"2011","unstructured":"Nammous, M.K., Szczepanski, A., Saeed, K.: An exploratory research on text-independent speaker recognition. In: HAIS, Part 1, pp. 412\u2013419 (2011)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Ahmed, H., Elaraby, M.S., Moussa, A.M., Abdallah, M., Abdou, S.M., Rashwan, M.: An unsupervised speaker clustering technique based on SOM and I-vectors for speech recognition systems. In: The Third Arabic Natural Language Processing Workshop, EACL, Valencia, Spain (2017)","DOI":"10.18653\/v1\/W17-1310"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Sarria-Paja, M., Falk, T.H.: Variants of mel-frequency cepstral coefficients for improved whispered speech speaker verification in mismatched conditions. In: 25th European Signal Processing Conference (EUSIPCO) (2017)","DOI":"10.23919\/EUSIPCO.2017.8081175"},{"key":"9_CR7","first-page":"50","volume":"45","author":"P Lopez-Otero","year":"2014","unstructured":"Lopez-Otero, P., Docio-Fernandez, L., Garcia-Mateo, C.: I-vectors for continuous emotion recognition. Training 45, 50 (2014)","journal-title":"Training"},{"key":"9_CR8","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.engappai.2014.05.003","volume":"34","author":"MH Bahari","year":"2014","unstructured":"Bahari, M.H., Mclaren, M., Van Hamme, H., Van Leeuwen, D.A.: Speaker age estimation using I-vectors. Eng. Appl. Artif. Intell. 34, 99\u2013108 (2014)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Motlicek, P., Dey, S., Madikeri, S., Burget, L.: Employment of subspace gaussian mixture models in speaker recognition. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, pp. 4445\u20134449 (2015)","DOI":"10.1109\/ICASSP.2015.7178811"},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.apnum.2012.05.004","volume":"75","author":"Khalid Saeed","year":"2014","unstructured":"Saeed, K.: Carath\u00e9odory\u2013Toeplitz based mathematical methods and their algorithmic applications in biometric image processing. Appl. Numer. Math. 75, 2\u201321 (2014)","journal-title":"Applied Numerical Mathematics"},{"key":"9_CR11","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/72.80210","volume":"1","author":"DF Specht","year":"1990","unstructured":"Specht, D.F.: Probabilistic neural networks and the polynomial adaline as complementary techniques for classification. IEEE Trans. Neural Netw. 1, 11\u2013121 (1990)","journal-title":"IEEE Trans. Neural Netw."},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Low, R., Togneri, R.: Speech recognition using the probabilistic neural network. In: Proceedings of ICSLP98 (1998)","DOI":"10.21437\/ICSLP.1998-840"},{"key":"9_CR13","unstructured":"Phan, H., Koch, P., Katzberg, F., Maass, M., Mazur, R., Mertins, A.: Audio scene classification with deep recurrent neural networks (2017). arXiv:1703.04770"},{"key":"9_CR14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.knosys.2016.10.008","volume":"115","author":"Z Qawaqneh","year":"2017","unstructured":"Qawaqneh, Z., Mallouh, A.A., Barkana, B.D.: Deep neural network framework and transformed MFCCs for speaker\u2019s age and gender classification. Knowl. Based Syst. 115, 5\u201314 (2017)","journal-title":"Knowl. Based Syst."},{"key":"9_CR15","unstructured":"Becerra, A., de la Rosa, J.I., Gonz\u00e1lez, E.: Speech recognition in a dialog system: from conventional to deep processing. In: Multimedia Tools and Applications, pp. 1\u201337. Springer (2017)"},{"key":"9_CR16","unstructured":"L\u00f3pez Moreno, I.: Deep neural network architectures for large-scale, robust and small-footprint speaker and language recognition. Ph.D. thesis. Universidad Polit\u00e9cnica de Madrid (2017)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Bell, P., Gales, M., Hain, T., Kilgour, J., Lanchantin, P., Liu, X., McParland, A., Renals, S., Saz, O., Wester, M., Woodland, P.: The MGB challenge: evaluating multi-genre broadcast media recognition. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 687\u2013693. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404863"},{"key":"9_CR18","unstructured":"Feng, L., Hansen, L.K.: A new database for speaker recognition. Technical report (2005)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"McLaren, M., Ferrer, L., Cast\u00e1n, D., Lawson, A.: The speakers in the wild (SITW) speaker recognition database. In: INTERSPEECH, vol. 2016, pp. 818\u2013822 (2016)","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Woo, R.H., Park, A., Hazen, T.J.: The MIT mobile device speaker verification corpus: data collection and preliminary experiments. In: The Speaker and Language Recognition Workshop (2006)","DOI":"10.1109\/ODYSSEY.2006.248083"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Godfrey, J.J., Holliman, E.C., McDaniel, J.: Switchboard: telephone speech corpus for research and development. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 1, pp. 517\u2013520. IEEE (1992)","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Greenberg, C.S.: The NIST year 2012 speaker recognition evaluation plan. NIST, Technical report (2012)","DOI":"10.21437\/Interspeech.2012-19"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Poignant, J., Besacier, L., Qu\u00e9not, G.: Unsupervised speaker identification in TV broadcast based on written names. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1) (2015)","DOI":"10.1109\/TASLP.2014.2367822"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Nagraniy, A., Chungy, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"9_CR25","unstructured":"Nammous M., Saeed K.: Voice-print and text-independent speaker identification. In: International Conference on Electrical Engineering Design and Technologies\u2014ICEEDT\u201907, 1 Jan 2007. International Conference on Electrical Engineering Design and Technologies\u2014ICEEDT\u201908, Tunisia (2007)"},{"key":"9_CR26","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York, NY (2006)"},{"issue":"3","key":"9_CR27","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1007\/s10489-014-0562-9","volume":"41","author":"Maciej Kusy","year":"2014","unstructured":"Kusy, M., Zajdel, R.: Probabilistic neural network training procedure based on Q(0)-learning algorithm in medical data classification. Appl. Intell. 41, 837\u2013854 (2014)","journal-title":"Applied Intelligence"},{"issue":"1","key":"9_CR28","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/0893-6080(90)90049-Q","volume":"3","author":"DF Specht","year":"1990","unstructured":"Specht, D.F.: Probabilistic neural networks. Neural Netw. 3(1), 109\u2013118 (1990)","journal-title":"Neural Netw."},{"key":"9_CR29","volume-title":"Statistics: Methods and Applications: a Comprehensive Reference for Science, Industry, and Data Mining","author":"P Lewicki","year":"2006","unstructured":"Lewicki, P., Hill, T.: Statistics: Methods and Applications: a Comprehensive Reference for Science, Industry, and Data Mining. StatSoft Inc, Tulsa, OK (2006)"},{"issue":"8","key":"9_CR30","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"9_CR31","unstructured":"Zhou, P., Qi, Z., Zheng, S., Xu, J., Bao, H., Xu, B.: Text classification improved by integrating bidirectional LSTM with two-dimensional max pooling. In: COLING 2016, pp. 3485\u20133495 (2016)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Lu, Y., Lu, C., Tang, C.-K.: Online video object detection using association LSTM. In: The IEEE International Conference on Computer Vision (ICCV), pp. 2344\u20132352 (2017)","DOI":"10.1109\/ICCV.2017.257"},{"key":"9_CR33","unstructured":"Akopyan, M., Khashba, E.: Large-scale YouTube-8M video understanding with deep neural networks (2017). arXiv:1706.04488"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Xu, J., Chen, D., Qiu, X., Huang, X.: Cached long short-term memory neural networks for document-level sentiment classification. In: EMNLP 2016, pp. 1660\u20131669 (2016)","DOI":"10.18653\/v1\/D16-1172"},{"issue":"7","key":"9_CR35","doi-asserted-by":"publisher","first-page":"1502","DOI":"10.1109\/TASLP.2017.2698723","volume":"25","author":"L Lu","year":"2017","unstructured":"Lu, L., Renals, S.: Small-footprint highway deep neural networks for speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(7), 1502\u20131511 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, D.L.: Long short-term memory for speaker generalization in supervised speech separation. In: INTERSPEECH, pp. 3314\u20133318 (2016)","DOI":"10.21437\/Interspeech.2016-551"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Saeed, K., Adamski, M., Bhattasali, T., Nammous, M.K., Panasiuk, P., Rybnik, M., Shaikh, S.H.: New Directions in Behavioral Biometrics. CRC Press (2016)","DOI":"10.1201\/9781315366760"}],"container-title":["Advances in Intelligent Systems and Computing","Advanced Computing and Systems for Security"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-13-3702-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,10]],"date-time":"2022-09-10T10:46:44Z","timestamp":1662806804000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-13-3702-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9789811337017","9789811337024"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-13-3702-4_9","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"value":"2194-5357","type":"print"},{"value":"2194-5365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"17 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}