{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T08:10:15Z","timestamp":1761811815809,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032043382","type":"print"},{"value":"9783032043399","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-032-04339-9_1","type":"book-chapter","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T08:06:21Z","timestamp":1761811581000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End ASR Model with Iterative Attention Mechanism Enhanced RNN Model for Phoneme Recognition"],"prefix":"10.1007","author":[{"given":"Ke","family":"Fang","sequence":"first","affiliation":[]},{"given":"Yancong","family":"Deng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"key":"1_CR1","unstructured":"McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Neurocomputing Found. Res. 53, 15\u201327 (1988)"},{"key":"1_CR2","unstructured":"Bayes, T.: An essay towards solving a problem in the doctrine of chances. Reprint of R. Soc. Lond. Philos. Trans.,\u00a0Rev. R. Acad. Sci. Exactas F\u00eds. Nat. 53(1\u20132), 11\u201360 (2001)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Davis, K.H.: Automatic recognition of spoken digits.\u00a0J. Acoust. Soc. Am. 24(6), 669 (1952)","DOI":"10.1121\/1.1906946"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. In: Readings in Speech Recognition, pp. 267\u2013296. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (1990)","DOI":"10.1016\/B978-0-08-051584-7.50027-9"},{"issue":"6","key":"1_CR5","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., Kingsbury, B.: 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":"1_CR6","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"1_CR7","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS 2017), pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"1_CR8","unstructured":"Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE (1999)"},{"key":"1_CR9","doi-asserted-by":"publisher","first-page":"122136","DOI":"10.1109\/ACCESS.2022.3223444","volume":"10","author":"ZK Abdul","year":"2022","unstructured":"Abdul, Z.K., Al-Talabani, A.K.: Mel frequency cepstral coefficient and its applications: a review. IEEE Access 10, 122136\u2013122158 (2022)","journal-title":"IEEE Access"},{"issue":"11","key":"1_CR10","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1_CR11","unstructured":"Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning.\u00a0Comput. Sci. (2015)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning (ICML 2006), pp. 369\u2013376. Association for Computing Machinery, New York (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"1_CR14","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS 2014), vol. 2, pp. 3104\u20133112. MIT Press, Cambridge (2014)"},{"key":"1_CR15","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate.\u00a0Comput. Sci. (2014)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation.\u00a0Comput. Lang. (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"1_CR17","unstructured":"Cordonnier, J.B., Loukas, A., Jaggi, M.: Multi-head attention: collaborate instead of concatenate (2020)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Halberstadt, A.K., Glass, J.R.: Heterogeneous acoustic measurements and multiple classifiers for speech recognition.\u00a0In: International Conference on Spoken Language Processing. DBLP (1999)","DOI":"10.21437\/ICSLP.1998-522"},{"issue":"2","key":"1_CR19","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1109\/TASL.2008.2010286","volume":"17","author":"Y Hifny","year":"2009","unstructured":"Hifny, Y., Renals, S.: Speech recognition using augmented conditional random fields. IEEE Trans. Audio Speech Lang. Process. 17(2), 354\u2013365 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Xie, Y., Zou, C.-R., Liang, R.-Y., Tao, H.-W.: Phoneme recognition based on deep belief network. In: Proceedings of the 2016 International Conference on Information System and Artificial Intelligence (ISAI), Hong Kong, China, pp. 352\u2013355 (2016)","DOI":"10.1109\/ISAI.2016.0081"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Sainath, T.N. , Ramabhadran, B. , Picheny, M. , Nahamoo, D., Kanevsky, D.: Exemplar-based sparse representation features: from TIMIT to LVCSR. IEEE (8) (2011)","DOI":"10.1109\/TASL.2011.2155060"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: IEEE International Conference on Acoustics, vol. 38. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"1_CR23","unstructured":"Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Proceedings of the 28th International Conference on Neural Information Processing Systems - (NIPS 2015), vol. 1, pp. 577\u2013585. MIT Press, Cambridge (2015)"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Toth, L.: Combining time- and frequency-domain convolution in convolutional neural network-based phone recognition.\u00a0IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853584"}],"container-title":["Communications in Computer and Information Science","Deep Learning Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04339-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T08:06:35Z","timestamp":1761811595000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04339-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783032043382","9783032043399"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04339-9_1","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"31 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DeLTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Deep Learning Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"delta2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/delta.scitevents.org\/?y=2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}