{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:24:00Z","timestamp":1742981040050,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030044961"},{"type":"electronic","value":"9783030044978"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-04497-8_19","type":"book-chapter","created":{"date-parts":[[2019,1,2]],"date-time":"2019-01-02T08:23:47Z","timestamp":1546417427000},"page":"227-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Robustness of LSTM Neural Networks for the Enhancement of Spectral Parameters in Noisy Speech Signals"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-9938","authenticated-orcid":false,"given":"Marvin","family":"Coto-Jim\u00e9nez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,3]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Mohamed, A.R., Jiang, H., Penn, G.: Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. In: Acoustics, Speech and Signal Processing, pp. 4277\u20134280. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Bagchi, D., Mandel, M.I., Wang, Z., He, Y., Plummer, A., Fosler-Lussier, E.: Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 496\u2013503. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404836"},{"key":"19_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/978-3-319-43958-7_42","volume-title":"Speech and Computer","author":"M Coto-Jim\u00e9nez","year":"2016","unstructured":"Coto-Jim\u00e9nez, M., Goddard-Close, J., Mart\u00ednez-Licona, F.: Improving automatic speech recognition containing additive noise using deep denoising autoencoders of LSTM networks. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 354\u2013361. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-43958-7_42"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Deng, L., et al.: Recent advances in deep learning for speech research at Microsoft. In: ICASSP, vol. 26, p. 64 (2013)","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Du, J., Wang, Q., Gao, T., Xu, Y., Dai, L.R., Lee, C.H.: Robust speech recognition with speech enhanced deep neural networks. In: Association (2014)","DOI":"10.21437\/Interspeech.2014-148"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Erro, D., Sainz, I., Navas, E., Hern\u00e1ez, I.: Improved HNM-based vocoder for statistical synthesizers. In: Association (2011)","DOI":"10.21437\/Interspeech.2011-35"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Y., Qian, Y., Xie, F.L., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Association (2014)","DOI":"10.21437\/Interspeech.2014-443"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Feng, X., Zhang, Y., Glass, J.: Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1759\u20131763. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853900"},{"issue":"Aug","key":"19_CR9","first-page":"115","volume":"3","author":"FA Gers","year":"2002","unstructured":"Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. J. Mach. Learn. Res. 3(Aug), 115\u2013143 (2002)","journal-title":"J. Mach. Learn. Res."},{"key":"19_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1007\/11550907_126","volume-title":"Artificial Neural Networks: Formal Models and Their Applications \u2013 ICANN 2005","author":"A Graves","year":"2005","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Bidirectional LSTM networks for improved phoneme classification and recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 799\u2013804. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11550907_126"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N., Mohamed, A.R.: Hybrid speech recognition with deep bidirectional LSTM. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 273\u2013278. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707742"},{"issue":"10","key":"19_CR12","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2017","unstructured":"Greff, K., Srivastava, R.K., Koutn\u00edk, J., Steunebrink, B.R., Schmidhuber, J.: 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":"19_CR13","doi-asserted-by":"crossref","unstructured":"Han, K., He, Y., Bagchi, D., Fosler-Lussier, E., Wang, D.: Deep neural network based spectral feature mapping for robust speech recognition. In: Association (2015)","DOI":"10.21437\/Interspeech.2015-536"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Hansen, J.H., Pellom, B.L.: An effective quality evaluation protocol for speech enhancement algorithms. In: Fifth International Conference on Spoken Language Processing (1998)","DOI":"10.21437\/ICSLP.1998-350"},{"issue":"4","key":"19_CR15","doi-asserted-by":"publisher","first-page":"3029","DOI":"10.1121\/1.4820893","volume":"134","author":"EW Healy","year":"2013","unstructured":"Healy, E.W., Yoho, S.E., Wang, Y., Wang, D.: An algorithm to improve speech recognition in noise for hearing-impaired listeners. J. Acoust. Soc. Am. 134(4), 3029\u20133038 (2013)","journal-title":"J. Acoust. Soc. Am."},{"issue":"6","key":"19_CR16","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sign. Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Sign. Process. Mag."},{"issue":"8","key":"19_CR17","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":"19_CR18","doi-asserted-by":"crossref","unstructured":"Huang, J., Kingsbury, B.: Audio-visual deep learning for noise robust speech recognition, pp. 7596\u20137599. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"19_CR19","unstructured":"Ishii, T., Komiyama, H., Shinozaki, T., Horiuchi, Y., Kuroiwa, S. (eds.): In: Interspeech, pp. 3512\u20133516 (2013)"},{"key":"19_CR20","unstructured":"Kominek, J., Black, A.W.: The CMU Arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, A., Florencio, D.: Speech enhancement in multiple-noise conditions using deep neural networks. arXiv preprint arXiv:1605.02427 (2016)","DOI":"10.21437\/Interspeech.2016-88"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Maas, A.L., Le, Q.V., O\u2019Neil, T.M., Vinyals, O., Nguyen, P., Ng, A.Y.: Recurrent neural networks for noise reduction in robust ASR. In: Association (2012)","DOI":"10.21437\/Interspeech.2012-6"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition, pp. 7092\u20137096. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition, pp. 7398\u20137402. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Sertsi, P., Boonkla, S., Chunwijitra, V., Kurpukdee, N., Wutiwiwatchai, C.: Robust voice activity detection based on LSTM recurrent neural networks and modulation spectrum. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 342\u2013346. IEEE (2017)","DOI":"10.1109\/APSIPA.2017.8282048"},{"key":"19_CR26","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.csl.2016.11.005","volume":"46","author":"E Vincent","year":"2017","unstructured":"Vincent, E., Watanabe, S., Nugraha, A.A., Barker, J., Marxer, R.: An analysis of environment, microphone and data simulation mismatches in robust speech recognition. Comput. Speech Lang. 46, 535\u2013557 (2017)","journal-title":"Comput. Speech Lang."},{"issue":"Dec","key":"19_CR27","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(Dec), 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"19_CR28","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1016\/j.csl.2014.01.001","volume":"28","author":"F Weninger","year":"2014","unstructured":"Weninger, F., Geiger, J., W\u00f6llmer, M., Schuller, B., Rigoll, G.: Feature enhancement by deep lstm networks for asr in reverberant multisource environments. Comput. Speech Lang. 28(4), 888\u2013902 (2014)","journal-title":"Comput. Speech Lang."},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Weninger, F., Watanabe, S., Tachioka, Y., Schuller, B.: Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4623\u20134627. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854478"},{"issue":"1","key":"19_CR30","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2014","unstructured":"Xu, Y., Du, J., Dai, L.R., Lee, C.H.: An experimental study on speech enhancement based on deep neural networks. IEEE Sign. Process. Lett. 21(1), 65\u201368 (2014)","journal-title":"IEEE Sign. Process. Lett."},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Zen, H., Sak, H.: Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4470\u20134474. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178816"}],"container-title":["Lecture Notes in Computer Science","Advances in Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04497-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:08:22Z","timestamp":1710241702000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04497-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030044961","9783030044978"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04497-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"3 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexican International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guadalajara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexico","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"micai2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.micai.org\/2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}