{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T14:58:19Z","timestamp":1783004299716,"version":"3.54.5"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T00:00:00Z","timestamp":1541635200000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s10772-018-09573-7","type":"journal-article","created":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T14:30:24Z","timestamp":1541687424000},"page":"21-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":125,"title":["Long short-term memory recurrent neural network architectures for Urdu acoustic modeling"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8176-3373","authenticated-orcid":false,"given":"Tehseen","family":"Zia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Usman","family":"Zahid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,11,8]]},"reference":[{"key":"9573_CR1","doi-asserted-by":"crossref","unstructured":"Ahad, A., Fayyaz, A., & Mehmood, T. (2002). Speech recognition using multilayer perceptron. In Proceedings of IEEE students conference (Vol.\u00a01, pp\u00a0103\u2013109).","DOI":"10.1109\/ISCON.2002.1215948"},{"key":"9573_CR2","unstructured":"Ali, H., Ahmad, N., & Hafeez, A. (2016). Urdu speech corpus and preliminary results on speech recognition. In International conference on engineering applications of neural networks (pp\u00a0317\u2013325). New York: Springer."},{"key":"9573_CR3","unstructured":"Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G., & Chen, J. (2016). Deep speech 2: End-to-end speech recognition in English and Mandarin. In International conference on machine Learning (pp\u00a0173\u2013182)."},{"key":"9573_CR4","doi-asserted-by":"crossref","unstructured":"Ashraf, J., Iqbal, N., Khattak, N. S., & Zaidi, A. M. (2010). Speaker independent Urdu speech recognition using HMM. In 7th IEEE international conference on informatics and systems (INFOS) (pp\u00a01\u20135).","DOI":"10.1007\/978-3-642-13881-2_14"},{"key":"9573_CR5","doi-asserted-by":"crossref","unstructured":"Azam, S. M., Mansoor, Z. A., Mughal, M. S., & Mohsin, S. (2007). Urdu spoken digits recognition using classified MFCC and backpropgation neural network. In IEEE conference on computer graphics, imaging and visualisation (pp\u00a0414\u2013418).","DOI":"10.1109\/CGIV.2007.85"},{"key":"9573_CR6","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., & Bengio, Y. (2016). End-to-end attention-based large vocabulary speech recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp.\u00a04945\u20134949). IEEE.","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"9573_CR9","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., & Vinyals, O. (2016). Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp.\u00a04960\u20134964). IEEE.","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"9573_CR10","unstructured":"Chan, W., & Lane, I. (2015), Deep recurrent neural networks for acoustic modelling. arXiv Preprint arXiv:1504.01482."},{"key":"9573_CR11","unstructured":"Chiu, C. C., Sainath, T. N., Wu, Y., Prabhavalkar, R., Nguyen, P., Chen, Z., & Jaitly, N. (2017). State-of-the-art speech recognition with sequence-to-sequence models. arXiv Preprint arXiv:1712.01769."},{"key":"9573_CR12","unstructured":"Chollet, F. (2015). Keras."},{"key":"9573_CR13","unstructured":"Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv Preprint arXiv:1412.3555."},{"key":"9573_CR14","unstructured":"Graves, A., & Jaitly, N. (2014). Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of the 31st international conference on machine learning (ICML-14) (pp\u00a01764\u20131772)."},{"key":"9573_CR16","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A. R., & Hinton, G. (2013a). Speech recognition with deep recurrent neural networks. In IEEE international conference on acoustics, speech and signal processing (pp\u00a06645\u20136649).","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"9573_CR15","doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N., & Mohamed, A. R. (2013b). Hybrid speech recognition with deep bidirectional LSTM. In IEEE workshop on automatic speech recognition and understanding (ASRU), pp\u00a0273\u2013278.","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"9573_CR17","unstructured":"Graves, A., & Schmidhuber, J. (2009). Offline handwriting recognition with multidimensional recurrent neural networks. In Advances in neural information processing systems (pp\u00a0545\u2013552)."},{"key":"9573_CR18","unstructured":"Greff, K., Srivastava, R. K., Koutn\u00edk, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. In IEEE transactions on neural networks and learning systems."},{"key":"9573_CR19","unstructured":"Hannun, A., Case, C., Casper, J., Catanzaro, B., Diamos, G., Elsen, E., Prenger, R., Satheesh, S., Sengupta, S., Coates, A., & Ng, A. Y. (2014). Deep speech: Scaling up end-to-end speech recognition. arXiv Preprint arXiv:1412.5567."},{"key":"9573_CR20","doi-asserted-by":"crossref","unstructured":"Hasnain, S. K., & Awan, M. S. (2008). Recognizing spoken Urdu numbers using Fourier descriptor and neural networks with Matlab. In Second international IEEE conference on electrical engineering (pp\u00a01\u20136).","DOI":"10.1109\/ICEE.2008.4553937"},{"issue":"6","key":"9573_CR21","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A. R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T. N., & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"8","key":"9573_CR22","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. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"issue":"3","key":"9573_CR23","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1080\/00401706.1991.10484833","volume":"33","author":"BH Juang","year":"1991","unstructured":"Juang, B. H., & Rabiner, L. R. (1991). Hidden Markov models for speech recognition. Technometrics, 33(3), 251\u2013272.","journal-title":"Technometrics"},{"key":"9573_CR24","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp\u00a01097\u20131105)."},{"key":"9573_CR25","unstructured":"Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv Preprint arXiv:1506.00019."},{"key":"9573_CR26","first-page":"3","volume":"2","author":"T Mikolov","year":"2010","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u00fd, J., & Khudanpur, S. (2010). Recurrent neural network based language model. Interspeech, 2, 3.","journal-title":"Interspeech"},{"key":"9573_CR28","unstructured":"Pascanu, R., Gulcehre, C., Cho, K., & Bengio, Y. (2013). How to construct deep recurrent neural networks. arXiv Preprint arXiv:1312.6026."},{"key":"9573_CR29","unstructured":"Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training recurrent neural networks. In International conference on machine learning (pp\u00a01310\u20131318)."},{"issue":"2","key":"9573_CR30","doi-asserted-by":"publisher","first-page":"257286","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"9573_CR31","doi-asserted-by":"crossref","unstructured":"Rao, K., & Sak, H. (2017). Multi-accent speech recognition with hierarchical grapheme based models. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), (pp.\u00a04815\u20134819). IEEE.","DOI":"10.1109\/ICASSP.2017.7953071"},{"key":"9573_CR32","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., & Beaufays, F. (2014). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In Fifteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2014-80"},{"key":"9573_CR33","unstructured":"Sak, H., Senior, A., Rao, K., & Beaufays, F. (2015). Fast and accurate recurrent neural network acoustic models for speech recognition. arXiv Preprint arXiv:1507.06947."},{"key":"9573_CR34","doi-asserted-by":"crossref","unstructured":"Sarfraz, H., Hussain, S., Bokhari, R., Raza, A. A., Ullah, I., Sarfraz, Z., Pervez, S., Mustafa, A., Javed, I., & Parveen, R. (2010). Large vocabulary continuous speech recognition for Urdu. In Proceedings of the 8th ACM international conference on frontiers of information technology (p\u00a01).","DOI":"10.1145\/1943628.1943629"},{"issue":"11","key":"9573_CR35","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673\u20132681.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"9573_CR36","unstructured":"Sutskever, I., Vinyals, O., & Le, Q. V. (2014), Sequence to sequence learning with neural networks. In Advances in neural information processing systems (pp\u00a03104\u20133112)."},{"issue":"4","key":"9573_CR37","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1162\/neco.1990.2.4.490","volume":"2","author":"RJ Williams","year":"1990","unstructured":"Williams, R. J., & Peng, J. (1990). An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural computation, 2(4), 490\u2013501.","journal-title":"Neural computation"},{"issue":"3","key":"9573_CR38","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1109\/JAS.2017.7510508","volume":"4","author":"D Yu","year":"2017","unstructured":"Yu, D., & Li, J. (2017). Recent progresses in deep learning based acoustic models. IEEE\/CAA Journal of Automatica Sinica, 4(3), 396\u2013409.","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"9573_CR39","unstructured":"Zweig, G., Yu, C., Stolcke, D. J., A. (2017). Advances in all-neural speech recognition. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp.\u00a04805\u20134809). IEEE."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-09573-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-09573-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-09573-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T16:19:19Z","timestamp":1662394759000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-09573-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,8]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["9573"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-09573-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,8]]},"assertion":[{"value":"21 July 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}