{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T06:28:07Z","timestamp":1725863287373},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319439570"},{"type":"electronic","value":"9783319439587"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-43958-7_42","type":"book-chapter","created":{"date-parts":[[2016,8,12]],"date-time":"2016-08-12T02:11:41Z","timestamp":1470967901000},"page":"354-361","source":"Crossref","is-referenced-by-count":14,"title":["Improving Automatic Speech Recognition Containing Additive Noise Using Deep Denoising Autoencoders of LSTM Networks"],"prefix":"10.1007","author":[{"given":"Marvin","family":"Coto-Jim\u00e9nez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Goddard-Close","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabiola","family":"Mart\u00ednez-Licona","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,8,13]]},"reference":[{"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: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4623\u20134627. IEEE (2014)","key":"42_CR1","DOI":"10.1109\/ICASSP.2014.6854478"},{"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: Proceedings of IEEE ASRU (2015)","key":"42_CR2","DOI":"10.1109\/ASRU.2015.7404836"},{"issue":"8","key":"42_CR3","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1109\/TASL.2010.2040522","volume":"18","author":"O Kalinli","year":"2010","unstructured":"Kalinli, O., Seltzer, M.L., Droppo, J., Acero, A.: Noise adaptive training for robust automatic speech recognition. IEEE Trans. Audio Speech Lang. Process. 18(8), 1889\u20131901 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"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)","key":"42_CR4","DOI":"10.21437\/Interspeech.2013-267"},{"issue":"1","key":"42_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13636-014-0045-2","volume":"2015","author":"Z Zhang","year":"2015","unstructured":"Zhang, Z., Wang, L., Kai, A., Yamada, T., Li, W., Iwahashi, M.: Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification. EURASIP J. Audio Speech Music Process. 2015(1), 1\u201313 (2015)","journal-title":"EURASIP J. Audio Speech Music Process."},{"unstructured":"Delcroix, M., Yoshioka, T., Ogawa, A., Kubo, Y., Fujimoto, M., Ito, N., Nakamura, A.: Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the REVERB challenge. In: Proceedings of REVERB Workshop (2014)","key":"42_CR6"},{"unstructured":"Kawase, T., Niwa, K., Hioka, Y., Kobayashi, K.: Selection of optimal array noise reduction parameter set for accurate speech recognition in various noisy environments. In: Western Pacific Acoustics Conference (2015)","key":"42_CR7"},{"doi-asserted-by":"crossref","unstructured":"Zhao, M., Wang, D., Zhang, Z., Zhang, X.: Music removal by denoising autoencoder in speech recognition. In: APSIPA 2015 (2015)","key":"42_CR8","DOI":"10.1109\/APSIPA.2015.7415289"},{"doi-asserted-by":"crossref","unstructured":"Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7398\u20137402 (2013)","key":"42_CR9","DOI":"10.1109\/ICASSP.2013.6639100"},{"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: INTERSPEECH, pp. 616\u2013620 (2014)","key":"42_CR10","DOI":"10.21437\/Interspeech.2014-148"},{"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: INTERSPEECH, pp. 2484\u20132488 (2015)","key":"42_CR11","DOI":"10.21437\/Interspeech.2015-536"},{"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: INTERSPEECH, pp. 22\u201325 (2012)","key":"42_CR12","DOI":"10.21437\/Interspeech.2012-6"},{"doi-asserted-by":"crossref","unstructured":"Deng, L., Li, J., Huang, J.T., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., Williams, J., Gong, Y.: Recent advances in deep learning for speech research at Microsoft. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8604\u20138608 (2013)","key":"42_CR13","DOI":"10.1109\/ICASSP.2013.6639345"},{"issue":"6","key":"42_CR14","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1109\/TASLP.2014.2318514","volume":"22","author":"JT Geiger","year":"2014","unstructured":"Geiger, J.T., Weninger, F., Gemmeke, J.F., Wollmer, M., Schuller, B., Rigoll, G.: Memory-enhanced neural networks and NMF for robust ASR. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(6), 1037\u20131046 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"crossref","unstructured":"Zen, H., Sak, H.: Unidirectional long short-term memory recurrent neural network with recurrent output layer for lowlatency speech synthesis. In: Submitted to ICASSP (2015)","key":"42_CR15","DOI":"10.1109\/ICASSP.2015.7178816"},{"issue":"8","key":"42_CR16","doi-asserted-by":"crossref","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."},{"doi-asserted-by":"crossref","unstructured":"Graves, A., Navdeep, J., Abdel-Rahman, M.: Hybrid speech recognition with deep bidirectional LSTM. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (2013)","key":"42_CR17","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"42_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","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)"},{"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: Interspeech, pp. 1964\u20131968 (2014)","key":"42_CR19","DOI":"10.21437\/Interspeech.2014-443"},{"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: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1759\u20131763 (2014)","key":"42_CR20","DOI":"10.1109\/ICASSP.2014.6853900"},{"unstructured":"Kominek, J., Black, A.W.: The CMU Arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)","key":"42_CR21"},{"unstructured":"Speechmatics. https:\/\/www.speechmatics.com","key":"42_CR22"},{"doi-asserted-by":"crossref","unstructured":"Erro, D., Sainz, I., Navas, E., Hernaez, I.: Improved HNM-based vocoder for statistical synthesizers. In: INTERSPEECH, pp. 1809\u20131812 (2011)","key":"42_CR23","DOI":"10.21437\/Interspeech.2011-35"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-43958-7_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T21:08:56Z","timestamp":1657055336000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-43958-7_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319439570","9783319439587"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-43958-7_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}