{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:19:59Z","timestamp":1743139199178,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030490751"},{"type":"electronic","value":"9783030490768"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-49076-8_29","type":"book-chapter","created":{"date-parts":[[2020,6,16]],"date-time":"2020-06-16T23:04:52Z","timestamp":1592348692000},"page":"307-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Experimental Study on Transfer Learning in Denoising Autoencoders for Speech Enhancement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-9938","authenticated-orcid":false,"given":"Marvin","family":"Coto-Jim\u00e9nez","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,17]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Weninger, F., et al.: 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). IEEE (2014)","key":"29_CR1","DOI":"10.1109\/ICASSP.2014.6854478"},{"doi-asserted-by":"crossref","unstructured":"Donahue, C., Bo, L., Prabhavalkar, R.: Exploring speech enhancement with generative adversarial networks for robust speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2018)","key":"29_CR2","DOI":"10.1109\/ICASSP.2018.8462581"},{"key":"29_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"},{"issue":"3","key":"29_CR4","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s10470-019-01446-6","volume":"100","author":"H Abouzid","year":"2019","unstructured":"Abouzid, H., Chakkor, O., Reyes, O.G., Ventura, S.: Signal speech reconstruction and noise removal using convolutional denoising audioencoders with neural deep learning. Analog Integr. Circ. Sig. Process 100(3), 501\u2013512 (2019). https:\/\/doi.org\/10.1007\/s10470-019-01446-6","journal-title":"Analog Integr. Circ. Sig. Process"},{"issue":"7","key":"29_CR5","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1109\/TBME.2016.2613960","volume":"64","author":"Y-H Lai","year":"2016","unstructured":"Lai, Y.-H., et al.: A deep denoising autoencoder approach to improving the intelligibility of vocoded speech in Cochlear implant simulation. IEEE Trans. Biomed. Eng. 64(7), 1568\u20131578 (2016)","journal-title":"IEEE Trans. Biomed. Eng."},{"doi-asserted-by":"crossref","unstructured":"Coto-Jimenez, M., Goddard-Close, J., Di Persia, L., Rufiner, H.L.: Hybrid speech enhancement with wiener filters and deep LSTM denoising autoencoders. In: Proceedings of the 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), San Carlos, CA, USA, 18\u201320 July 2018, pp. 1\u20138 (2018)","key":"29_CR6","DOI":"10.1109\/IWOBI.2018.8464132"},{"issue":"1","key":"29_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/biomimetics5010001","volume":"5","author":"M Guti\u00e9rrez-Mu\u00f1oz","year":"2020","unstructured":"Guti\u00e9rrez-Mu\u00f1oz, M., Gonz\u00e1lez-Salazar, A., Coto-Jim\u00e9nez, M.: Evaluation of mixed deep neural networks for reverberant speech enhancement. Biomimetics 5(1), 1 (2020)","journal-title":"Biomimetics"},{"doi-asserted-by":"crossref","unstructured":"Chakraborty, R., et al.: Front-end feature compensation and denoising for noise robust speech emotion recognition. In: Proceedings of Interspeech 2019, pp. 3257\u20133261 (2019)","key":"29_CR8","DOI":"10.21437\/Interspeech.2019-2243"},{"key":"29_CR9","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"},{"key":"29_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-319-66429-3_69","volume-title":"Speech and Computer","author":"M Tkachenko","year":"2017","unstructured":"Tkachenko, M., Yamshinin, A., Lyubimov, N., Kotov, M., Nastasenko, M.: Speech enhancement for speaker recognition using deep recurrent neural networks. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 690\u2013699. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_69"},{"doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: Speech enhancement method based on LSTM neural network for speech recognition. In: 2018 14th IEEE International Conference on Signal Processing (ICSP). IEEE (2018)","key":"29_CR11","DOI":"10.1109\/ICSP.2018.8652331"},{"unstructured":"Jia, Y., et al.: Transfer learning from speaker verification to multi speaker text-to-speech synthesis. In: Advances in Neural Information Processing Systems (2018)","key":"29_CR12"},{"key":"29_CR13","series-title":"IFIP Advances in Information and Communication Technology","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-319-68121-4_19","volume-title":"Intelligence Science I","author":"G Song","year":"2017","unstructured":"Song, G., Wang, Z., Han, F., Ding, S.: Transfer learning for music genre classification. In: Shi, Z., Goertzel, B., Feng, J. (eds.) ICIS 2017. IAICT, vol. 510, pp. 183\u2013190. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68121-4_19"},{"issue":"1","key":"29_CR14","first-page":"55","volume":"58","author":"YI Jiangyan","year":"2018","unstructured":"Jiangyan, Y.I., et al.: Transfer learning for acoustic modeling of noise robust speech recognition. J. Tsinghua Univ. (Sci. Technol.) 58(1), 55\u201360 (2018)","journal-title":"J. Tsinghua Univ. (Sci. Technol.)"},{"doi-asserted-by":"crossref","unstructured":"Pascual, S., et al.: Language and noise transfer in speech enhancement generative adversarial network. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2018)","key":"29_CR15","DOI":"10.1109\/ICASSP.2018.8462322"},{"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: Proceedings of the Fifteenth Annual Conference of the International Speech Communication Association, Singapore, 14\u201318 September (2014)","key":"29_CR16","DOI":"10.21437\/Interspeech.2014-443"},{"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: Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, Australia, 19\u201324 April 2015, pp. 4470\u20134474 (2015)","key":"29_CR17","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"29_CR18","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N., Mohamed, A.R.: Hybrid speech recognition with deep bidirectional LSTM. In: Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Olomouc, Czech Republic, 8\u201313 December 2013, pp. 273\u2013278 (2013)","key":"29_CR19","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"29_CR20","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":"29_CR21","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, 115\u2013143 (2002)","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"crossref","unstructured":"W\u00f6llmer, M., Eyben, F., Schuler, B., Rigoll, G.: A multi-stream ASR framework for BLSTM modeling of conversational speech. In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, 22\u201327 May 2011, p. 4861 (2011)","key":"29_CR22","DOI":"10.1109\/ICASSP.2011.5947444"},{"issue":"1","key":"29_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"K Weiss","year":"2016","unstructured":"Weiss, K., Khoshgoftaar, T.M., Wang, D.D.: A survey of transfer learning. J. Big Data 3(1), 1\u201340 (2016). https:\/\/doi.org\/10.1186\/s40537-016-0043-6","journal-title":"J. Big Data"},{"issue":"10","key":"29_CR24","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"10","key":"29_CR25","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2016","unstructured":"Greff, K., et al.: LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222\u20132232 (2016)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"unstructured":"Kominek, J., Black, A.W.: The CMU Arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)","key":"29_CR26"},{"issue":"10","key":"29_CR27","first-page":"755","volume":"50","author":"AW Rix","year":"2002","unstructured":"Rix, A.W., et al.: Perceptual evaluation of speech quality (PESQ) the new ITU standard for end-to-end speech quality assessment Part I-time-delay compensation. J. Audio Eng. Soc. 50(10), 755\u2013764 (2002)","journal-title":"J. Audio Eng. Soc."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-49076-8_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T23:06:00Z","timestamp":1718579160000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-49076-8_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030490751","9783030490768"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-49076-8_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"17 June 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexican Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morelia","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mcpr22020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ccc.inaoep.mx\/~mcpr2020\/index.html","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"31","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":"46% - 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":"2.05","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":"2.79","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}