{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T10:30:54Z","timestamp":1757586654216,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,2,28]],"date-time":"2019-02-28T00:00:00Z","timestamp":1551312000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100012913","name":"Tata Consultancy Services","doi-asserted-by":"publisher","award":["TCSRSPCycle12"],"award-info":[{"award-number":["TCSRSPCycle12"]}],"id":[{"id":"10.13039\/100012913","id-type":"DOI","asserted-by":"publisher"}]}],"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\/s00034-019-01074-5","type":"journal-article","created":{"date-parts":[[2019,2,28]],"date-time":"2019-02-28T04:54:37Z","timestamp":1551329677000},"page":"3482-3500","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Incorporation of Manner of Articulation Constraint in LSTM for Speech Recognition"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8621-4058","authenticated-orcid":false,"given":"R.","family":"Pradeep","sequence":"first","affiliation":[]},{"given":"K. Sreenivasa","family":"Rao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,28]]},"reference":[{"key":"1074_CR1","doi-asserted-by":"crossref","unstructured":"J. Billa, Dropout approaches for LSTM based speech recognition systems, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5879\u20135883. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462544"},{"key":"1074_CR2","unstructured":"J. Chung, C. Gulcehre, K. Cho, Y. Bengio, Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"issue":"1","key":"1074_CR3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"G.E. Dahl, D. Yu, L. Deng, A. Acero, Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1074_CR4","unstructured":"A. Graves, Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)"},{"issue":"10","key":"1074_CR5","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2017","unstructured":"K. Greff, R.K. Srivastava, J. Koutn\u00edk, B.R. Steunebrink, J. Schmidhuber, LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222\u20132232 (2017)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1074_CR6","doi-asserted-by":"crossref","unstructured":"A.K. Halberstadt, Heterogeneous acoustic measurements and multiple classifiers for speech recognition. Ph.D. thesis, Massachusetts Institute of Technology (1999)","DOI":"10.21437\/ICSLP.1998-522"},{"issue":"8","key":"1074_CR7","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1074_CR8","unstructured":"S. Khandelwal, B. Lecouteux, L. Besacier, Comparing GRU and LSTM for automatic speech recognition. Ph.D. thesis, LIG (2016)"},{"key":"1074_CR9","doi-asserted-by":"crossref","unstructured":"J.F. Kruiger, P.E. Rauber, R.M. Martins, A. Kerren, S. Kobourov, A.C. Telea, Graph layouts by t-SNE, in Computer Graphics Forum, vol.\u00a036 (Wiley Online Library, 2017), pp. 283\u2013294","DOI":"10.1111\/cgf.13187"},{"key":"1074_CR10","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.csl.2016.06.007","volume":"41","author":"AL Maas","year":"2017","unstructured":"A.L. Maas, P. Qi, Z. Xie, A.Y. Hannun, C.T. Lengerich, D. Jurafsky, A.Y. Ng, Building DNN acoustic models for large vocabulary speech recognition. Comput. Speech Lang. 41, 195\u2013213 (2017)","journal-title":"Comput. Speech Lang."},{"key":"1074_CR11","unstructured":"L.v.d. Maaten, G. Hinton, Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579\u20132605 (2008)"},{"issue":"23","key":"1074_CR12","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1049\/el.2009.1977","volume":"45","author":"N Madhu","year":"2009","unstructured":"N. Madhu, Note on measures for spectral flatness. Electron. Lett. 45(23), 1195\u20131196 (2009)","journal-title":"Electron. Lett."},{"key":"1074_CR13","doi-asserted-by":"crossref","unstructured":"R. Miikkulainen, J. Liang, E. Meyerson, A. Rawal, D. Fink, O. Francon, B. Raju, H. Shahrzad, A. Navruzyan, N. Duffy, et\u00a0al.: Evolving deep neural networks, in Artificial Intelligence in the Age of Neural Networks and Brain Computing (Elsevier, Amsterdam, 2019), pp. 293\u2013312","DOI":"10.1016\/B978-0-12-815480-9.00015-3"},{"issue":"1","key":"1074_CR14","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1006\/csla.2001.0184","volume":"16","author":"M Mohri","year":"2002","unstructured":"M. Mohri, F. Pereira, M. Riley, Weighted finite-state transducers in speech recognition. Comput. Speech Lang. 16(1), 69\u201388 (2002)","journal-title":"Comput. Speech Lang."},{"key":"1074_CR15","unstructured":"A. Nayebi, M. Vitelli, GRUV: Algorithmic music generation using recurrent neural networks, in Course CS224D: Deep Learning for Natural Language Processing (Stanford) (2015)"},{"key":"1074_CR16","unstructured":"D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, et\u00a0al., The kaldi speech recognition toolkit, in IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, EPFL-CONF-192584. IEEE Signal Processing Society (2011)"},{"key":"1074_CR17","doi-asserted-by":"crossref","unstructured":"D. Povey, M. Hannemann, G. Boulianne, L. Burget, A. Ghoshal, M. Janda, M. Karafi\u00e1t, S. Kombrink, P. Motl\u00ed\u010dek, Y. Qian, et\u00a0al., Generating exact lattices in the WFST framework., in 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4213\u20134216. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288848"},{"key":"1074_CR18","doi-asserted-by":"publisher","unstructured":"R. Pradeep, K.S. Rao, Split acoustic modeling in decoder for phoneme recognition, in 2017 14th IEEE India Council International Conference (INDICON), pp. 1\u20135 (2017). https:\/\/doi.org\/10.1109\/INDICON.2017.8487556","DOI":"10.1109\/INDICON.2017.8487556"},{"key":"1074_CR19","doi-asserted-by":"publisher","unstructured":"R. Pradeep, K.S. Rao, Manner of articulation based split lattices for phoneme recognition, in 2018 Twenty Fourth National Conference on Communications (NCC), pp. 1\u20136 (2018). https:\/\/doi.org\/10.1109\/NCC.2018.8600190","DOI":"10.1109\/NCC.2018.8600190"},{"key":"1074_CR20","doi-asserted-by":"publisher","unstructured":"R. Pradeep, K.S. Rao, Modifying LSTM posteriors with manner of articulation knowledge to improve speech recognition performance, in 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 769\u2013772 (2018). https:\/\/doi.org\/10.1109\/ICMLA.2018.00122","DOI":"10.1109\/ICMLA.2018.00122"},{"key":"1074_CR21","doi-asserted-by":"crossref","unstructured":"M. Ravanelli, P. Brakel, M. Omologo, Y. Bengio, Batch-normalized joint training for DNN-based distant speech recognition, in Spoken Language Technology Workshop (SLT), 2016 IEEE, pp. 28\u201334. IEEE (2016)","DOI":"10.1109\/SLT.2016.7846241"},{"issue":"2","key":"1074_CR22","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TETCI.2017.2762739","volume":"2","author":"M Ravanelli","year":"2018","unstructured":"M. Ravanelli, P. Brakel, M. Omologo, Y. Bengio, Light gated recurrent units for speech recognition. IEEE Trans. Emerg. Top. Comput. Intell. 2(2), 92\u2013102 (2018)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"1074_CR23","doi-asserted-by":"crossref","unstructured":"H. Sak, A. Senior, K. Rao, F. Beaufays, Fast and accurate recurrent neural network acoustic models for speech recognition. arXiv preprint arXiv:1507.06947 (2015)","DOI":"10.21437\/Interspeech.2015-350"},{"key":"1074_CR24","doi-asserted-by":"crossref","unstructured":"H. Sak, A. Senior, K. Rao, O. Irsoy, A. Graves, F. Beaufays, J. Schalkwyk, Learning acoustic frame labeling for speech recognition with recurrent neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4280\u20134284. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"1074_CR25","doi-asserted-by":"publisher","first-page":"3358","DOI":"10.21437\/Interspeech.2018-2476","volume":"2018","author":"Z T\u00fcske","year":"2018","unstructured":"Z. T\u00fcske, R. Schl\u00fcter, H. Ney, Investigation on LSTM recurrent n-gram language models for speech recognition. Proc. Interspeech 2018, 3358\u20133362 (2018)","journal-title":"Proc. Interspeech"},{"key":"1074_CR26","doi-asserted-by":"crossref","unstructured":"W. Xiong, L. Wu, F. Alleva, J. Droppo, X. Huang, A. Stolcke, The microsoft 2017 conversational speech recognition system, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5934\u20135938. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"1074_CR27","doi-asserted-by":"crossref","unstructured":"Y. Zhang, G. Chen, D. Yu, K. Yaco, S. Khudanpur, J. Glass, Highway long short-term memory RNNs for distant speech recognition, in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5755\u20135759. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472780"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-019-01074-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01074-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01074-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T19:35:51Z","timestamp":1663011351000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-019-01074-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,28]]},"references-count":27,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["1074"],"URL":"https:\/\/doi.org\/10.1007\/s00034-019-01074-5","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2019,2,28]]},"assertion":[{"value":"4 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}