{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:45:28Z","timestamp":1742913928552,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030410049"},{"type":"electronic","value":"9783030410056"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-41005-6_20","type":"book-chapter","created":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T21:03:52Z","timestamp":1581541432000},"page":"291-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Performance Evaluation of Several Artificial Neural Networks for Mapping Speech Spectrum Parameters"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4172-1536","authenticated-orcid":false,"given":"V\u00edctor","family":"Yeom-Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7481-0207","authenticated-orcid":false,"given":"Marisol","family":"Zeled\u00f3n-C\u00f3rdoba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-9938","authenticated-orcid":false,"given":"Marvin","family":"Coto-Jim\u00e9nez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,12]]},"reference":[{"key":"20_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: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4277\u20134280. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288864"},{"issue":"1","key":"20_CR2","first-page":"115","volume":"14","author":"AR Barron","year":"1994","unstructured":"Barron, A.R.: Approximation and estimation bounds for artificial neural networks. Mach. Learn. 14(1), 115\u2013133 (1994)","journal-title":"Mach. Learn."},{"key":"20_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-04497-8_19","volume-title":"Advances in Computational Intelligence","author":"M Coto-Jim\u00e9nez","year":"2018","unstructured":"Coto-Jim\u00e9nez, M.: Robustness of LSTM neural networks for the enhancement of spectral parameters in noisy speech signals. In: Batyrshin, I., Mart\u00ednez-Villase\u00f1or, M.L., Ponce Espinosa, H.E. (eds.) MICAI 2018. LNCS (LNAI), vol. 11289, pp. 227\u2013238. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-04497-8_19"},{"issue":"2","key":"20_CR4","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3390\/biomimetics4020039","volume":"4","author":"M Coto-Jim\u00e9nez","year":"2019","unstructured":"Coto-Jim\u00e9nez, M.: Improving post-filtering of artificial speech using pre-trained LSTM neural networks. Biomimetics 4(2), 39 (2019)","journal-title":"Biomimetics"},{"key":"20_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-319-39393-3_28","volume-title":"Pattern Recognition","author":"M Coto-Jim\u00e9nez","year":"2016","unstructured":"Coto-Jim\u00e9nez, M., Goddard-Close, J.: LSTM deep neural networks postfiltering for improving the quality of synthetic voices. In: Mart\u00ednez-Trinidad, J.F., Carrasco-Ochoa, J.A., Ayala-Ram\u00edrez, V., Olvera-L\u00f3pez, J.A., Jiang, X. (eds.) MCPR 2016. LNCS, vol. 9703, pp. 280\u2013289. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-39393-3_28"},{"key":"20_CR6","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":"20_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: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-443"},{"key":"20_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":"3","key":"20_CR9","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0893-6080(89)90003-8","volume":"2","author":"KI Funahashi","year":"1989","unstructured":"Funahashi, K.I.: On the approximate realization of continuous mappings by neural networks. Neural Netw. 2(3), 183\u2013192 (1989)","journal-title":"Neural Netw."},{"issue":"Aug","key":"20_CR10","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":"20_CR11","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":"20_CR12","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":"6","key":"20_CR13","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 Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Huang, J., Kingsbury, B.: Audio-visual deep learning for noise robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7596\u20137599. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Ishii, T., Komiyama, H., Shinozaki, T., Horiuchi, Y., Kuroiwa, S.: Reverberant speech recognition based on denoising autoencoder. In: Interspeech, pp. 3512\u20133516 (2013)","DOI":"10.21437\/Interspeech.2013-267"},{"key":"20_CR16","unstructured":"Kominek, J., Black, A.W.: The CMU arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)"},{"key":"20_CR17","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":"20_CR18","unstructured":"Liang, S., Srikant, R.: Why deep neural networks for function approximation? arXiv preprint arXiv:1610.04161 (2016)"},{"key":"20_CR19","unstructured":"Lu, Z., Pu, H., Wang, F., Hu, Z., Wang, L.: The expressive power of neural networks: a view from the width. In: Advances in Neural Information Processing Systems, pp. 6231\u20136239 (2017)"},{"key":"20_CR20","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/TITS.2018.2867042","volume":"20","author":"X Ma","year":"2018","unstructured":"Ma, X., Zhang, J., Du, B., Ding, C., Sun, L.: Parallel architecture ofconvolutional bi-directional LSTM neural networks for network-wide metroridership prediction. IEEE Trans. Intell. Transp. Syst. 20, 2278\u20132288 (2018)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"20_CR21","unstructured":"Miller, G.F., Todd, P.M., Hegde, S.U.: Designing neural networks using genetic algorithms. In: ICGA, vol. 89, pp. 379\u2013384 (1989)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Ray, A., Rajeswar, S., Chaudhury, S.: Text recognition using deep BLSTM networks. In: 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR), pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/ICAPR.2015.7050699"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7398\u20137402. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"20_CR24","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":"20_CR25","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":"20_CR26","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":"20_CR27","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"},{"key":"20_CR28","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"},{"issue":"1","key":"20_CR29","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/TASLP.2018.2870725","volume":"27","author":"Y Zhao","year":"2019","unstructured":"Zhao, Y., Wang, Z.Q., Wang, D.: Two-stage deep learning for noisy-reverberant speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(1), 53\u201362 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Communications in Computer and Information Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41005-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T11:10:53Z","timestamp":1665832253000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41005-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030410049","9783030410056"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41005-6_20","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CARLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Latin American High Performance Computing Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turrialba","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Costa Rica","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2019","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":"carla2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/carla2019.ccarla.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"52% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}