{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:16:02Z","timestamp":1749701762807,"version":"3.41.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319491684"},{"type":"electronic","value":"9783319491691"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-49169-1_12","type":"book-chapter","created":{"date-parts":[[2016,11,3]],"date-time":"2016-11-03T11:31:46Z","timestamp":1478172706000},"page":"117-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Deep Neural Network-Based Noise Estimation for Robust ASR in Dual-Microphone Smartphones"],"prefix":"10.1007","author":[{"given":"Iv\u00e1n","family":"L\u00f3pez-Espejo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio M.","family":"Peinado","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angel M.","family":"Gomez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan M.","family":"Mart\u00edn-Do\u00f1as","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,4]]},"reference":[{"issue":"4","key":"12_CR1","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TASLP.2014.2304637","volume":"22","author":"J Li","year":"2014","unstructured":"Li, J., Deng, L., Gong, Y., Haeb-Umbach, R.: An overview of noise-robust automatic speech recognition. IEEE Trans. Audio Speech Lang. Process. 22(4), 745\u2013777 (2014)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Moreno, P.J., et al.: A vector Taylor series approach for environment-independent speech recognition. In: ICASSP, Atlanta, USA, pp. 733\u2013736 (1996)","DOI":"10.1109\/ICASSP.1996.543225"},{"key":"12_CR3","unstructured":"Wu, J., Droppo, J., Deng, L., Acero, A.: A noise-robust ASR front-end using Wiener filter constructed from MMSE estimation of clean speech and noise. In: ASRU, Virgin Islands, pp. 321\u2013326 (2003)"},{"key":"12_CR4","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.specom.2005.08.005","volume":"48","author":"S Rangachari","year":"2006","unstructured":"Rangachari, S., Loizou, P.C.: A noise-estimation algorithm for highly non-stationary environments. Speech Commun. 48, 220\u2013231 (2006)","journal-title":"Speech Commun."},{"key":"12_CR5","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1109\/TSA.2003.811544","volume":"11","author":"I Cohen","year":"2003","unstructured":"Cohen, I.: Noise spectrum estimation in adverse environments: IMCRA. IEEE Trans. Speech Audio Process. 11, 466\u2013475 (2003)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"12_CR6","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/89.928915","volume":"9","author":"R Martin","year":"2001","unstructured":"Martin, R.: Noise power spectral density estimation based on optimal smoothing and minimum statistics. IEEE Trans. Speech Audio Process. 9, 504\u2013512 (2001)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Hendriks, R.C., Heusdens, R., Jensen, J.: MMSE based noise PSD tracking with low complexity. In: ICASSP, Dallas, USA (2010)","DOI":"10.1109\/ICASSP.2010.5495680"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Jeub, M., et al.: Noise reduction for dual-microphone mobile phones exploiting power level differences. In: ICASSP, Kyoto, Japan, pp. 1693\u20131696 (2012)","DOI":"10.1109\/ICASSP.2012.6288223"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: A fast two-microphone noise reduction algorithm based on power level ratio for mobile phone. In: ISCSLP, Hong-Kong, pp. 206\u2013209 (2012)","DOI":"10.1109\/ISCSLP.2012.6423512"},{"key":"12_CR10","unstructured":"L\u00f3pez-Espejo, I., et al.: Feature enhancement for robust speech recognition on smartphones with dual-microphone. In: EUSIPCO, Lisbon, Portugal (2014)"},{"key":"12_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/978-3-319-13623-3_13","volume-title":"Advances in Speech and Language Technologies for Iberian Languages","author":"I L\u00f3pez-Espejo","year":"2014","unstructured":"L\u00f3pez-Espejo, I., Gonz\u00e1lez, J.A., G\u00f3mez, \u00c1.M., Peinado, A.M.: A deep neural network approach for missing-data mask estimation on dual-microphone smartphones: application to noise-robust speech recognition. In: Navarro Mesa, J.L., Ortega, A., Teixeira, A., Hern\u00e1ndez P\u00e9rez, E., Quintana Morales, P., Ravelo Garc\u00eda, A., Guerra Moreno, I., Toledano, D.T. (eds.) IberSPEECH 2014. LNCS (LNAI), vol. 8854, pp. 119\u2013128. Springer, Heidelberg (2014). doi:10.1007\/978-3-319-13623-3_13"},{"issue":"7","key":"12_CR12","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1109\/TASL.2013.2250961","volume":"21","author":"Y Wang","year":"2013","unstructured":"Wang, Y., Wang, D.L.: Towards scaling up classication-based speech separation. IEEE Trans. Audio Speech Lang. Process. 21(7), 1381\u20131390 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Vincent, E.: Is audio signal processing still useful in the era of machine learning? In: WASPAA, New York, USA (2015)","DOI":"10.1109\/WASPAA.2015.7336882"},{"key":"12_CR14","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"issue":"5786","key":"12_CR15","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Seltzer, M.L., et al.: An investigation of deep neural networks for noise robust speech recognition. In: ICASSP, Vancouver, Canada, pp. 7398\u20137402 (2013)","DOI":"10.1109\/ICASSP.2013.6639100"},{"issue":"1","key":"12_CR17","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2015","unstructured":"Xu, Y., Du, J., Dai, L.R.: A regression approach to speech enhancement based on deep neural networks. IEEE Trans. Audio Speech Lang. Process. 23(1), 7\u201319 (2015)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Segura, J.C., et al.: Model-based compensation of the additive noise for continuous speech recognition. Experiments using the AURORA II database and tasks. In: EUROSPEECH, Aalborg, Denmark (2001)","DOI":"10.21437\/Eurospeech.2001-78"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Pearce, D., Hirsch, H.G.: The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: ICSLP, Beijing, China (2000)","DOI":"10.21437\/ICSLP.2000-743"},{"key":"12_CR20","unstructured":"ETSI ES 201 108 - Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms"},{"key":"12_CR21","unstructured":"Hinton, G.E.: A practical guide to training restricted Boltzmann machines. UTML TR 2010\u2013003 (2010)"},{"key":"12_CR22","unstructured":"Theano Library. http:\/\/deeplearning.net\/software\/theano\/"}],"container-title":["Lecture Notes in Computer Science","Advances in Speech and Language Technologies for Iberian Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49169-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T23:48:00Z","timestamp":1749685680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-49169-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319491684","9783319491691"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49169-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"4 November 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IberSPEECH","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advances in Speech and Language Technologies for Iberian Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iberspeech2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iberspeech2016.inesc-id.pt\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}