{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:04:43Z","timestamp":1742911483866,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030279462"},{"type":"electronic","value":"9783030279479"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-27947-9_28","type":"book-chapter","created":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T23:02:43Z","timestamp":1567378963000},"page":"329-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Comparing Front-End Enhancement Techniques and Multiconditioned Training for Robust Automatic Speech Recognition"],"prefix":"10.1007","author":[{"given":"Meet H.","family":"Soni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonal","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashish","family":"Panda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,6]]},"reference":[{"key":"28_CR1","unstructured":"Berouti, M., Schwartz, R., Makhoul, J.: Enhancement of speech corrupted by acoustic noise. In: Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP 1979, vol. 4, pp. 208\u2013211. IEEE (1979)"},{"issue":"2","key":"28_CR2","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S Boll","year":"1979","unstructured":"Boll, S.: Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust. Speech Signal Process. 27(2), 113\u2013120 (1979)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"28_CR3","unstructured":"Brookes, M., et al.: Voicebox: Speech processing toolbox for matlab. Software [March 2011] www.ee.ic.ac.uk\/hp\/staff\/dmb\/voicebox\/voicebox.html, vol. 47 (1997)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Das, B., Panda, A.: Robust front-end processing for speech recognition in noisy conditions. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5235\u20135239. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953155"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Dean, D.B., Sridharan, S., Vogt, R.J., Mason, M.W.: The QUT-NOISE-TIMIT corpus for the evaluation of voice activity detection algorithms. In: Proceedings of Interspeech 2010 (2010)","DOI":"10.21437\/Interspeech.2010-774"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Do, C.T., Stylianou, Y.: Improved automatic speech recognition using subband temporal envelope features and time-delay neural network denoising autoencoder. In: Proceedings of Interspeech 2017, pp. 3832\u20133836 (2017)","DOI":"10.21437\/Interspeech.2017-1096"},{"key":"28_CR7","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: Proceedings of Interspeech (2014)","DOI":"10.21437\/Interspeech.2014-148"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Hirsch, H.G., Finster, H.: The simulation of realistic acoustic input scenarios for speech recognition systems. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-263"},{"issue":"9","key":"28_CR9","doi-asserted-by":"publisher","first-page":"1809","DOI":"10.1109\/TASLP.2017.2718843","volume":"25","author":"K Janod","year":"2017","unstructured":"Janod, K., Morchid, M., Dufour, R., Linares, G., De Mori, R.: Denoised bottleneck features from deep autoencoders for telephone conversation analysis. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(9), 1809\u20131820 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Joshi, S., Panda, A., DAs, B.: Enhanced denoising auto-encoder for robust speech recognition in unseen noise conditions. In: International Symposium on Chinese Spoken Languages Processing (2018)","DOI":"10.1109\/ISCSLP.2018.8706697"},{"key":"28_CR11","unstructured":"Li, J., Deng, L., Yu, D., Gong, Y., Acero, A.: High-performance HMM adaptation with joint compensation of additive and convolutive distortions via vector taylor series. In: IEEE Workshop on Automatic Speech Recognition & Understanding, 2007. ASRU, pp. 65\u201370. IEEE (2007)"},{"key":"28_CR12","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: Proceedings of Interspeech (2012)","DOI":"10.21437\/Interspeech.2012-6"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Marchi, E., Vesperini, F., Eyben, F., Squartini, S., Schuller, B.: A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1996\u20132000. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178320"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Mitra, V., Franco, H.: Leveraging deep neural network activation entropy to cope with unseen data in speech recognition. arXiv preprint arXiv:1708.09516 (2017)","DOI":"10.1109\/ICASSP.2018.8461369"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Mitra, V., Franco, H., Bartels, C., van Hout, J., Graciarena, M., Vergyri, D.: Speech recognition in unseen and noisy channel conditions. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5215\u20135219. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953151"},{"key":"28_CR16","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-3-319-64680-0_8","volume-title":"New Era for Robust Speech Recognition","author":"V Mitra","year":"2017","unstructured":"Mitra, V., et al.: Robust features in deep-learning-based speech recognition. In: Watanabe, S., Delcroix, M., Metze, F., Hershey, J.R. (eds.) New Era for Robust Speech Recognition, pp. 187\u2013217. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64680-0_8"},{"key":"28_CR17","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.specom.2017.03.003","volume":"89","author":"V Mitra","year":"2017","unstructured":"Mitra, V., Sivaraman, G., Nam, H., Espy-Wilson, C., Saltzman, E., Tiede, M.: Hybrid convolutional neural networks for articulatory and acoustic information based speech recognition. Speech Commun. 89, 103\u2013112 (2017)","journal-title":"Speech Commun."},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.: Joint noise adaptive training for robust automatic speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2504\u20132508. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Proceedings of Interspeech (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"key":"28_CR21","unstructured":"Povey, D., et al.: The kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. No. EPFL-CONF-192584, IEEE Signal Processing Society (2011)"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., Visweswariah, K.: Boosted MMI for model and feature-space discriminative training. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008, pp. 4057\u20134060. IEEE (2008)","DOI":"10.1109\/ICASSP.2008.4518545"},{"issue":"12","key":"28_CR23","doi-asserted-by":"publisher","first-page":"2263","DOI":"10.1109\/TASLP.2016.2602884","volume":"24","author":"Y Qian","year":"2016","unstructured":"Qian, Y., Bi, M., Tan, T., Yu, K.: Very deep convolutional neural networks for noise robust speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(12), 2263\u20132276 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yin, M., You, Y., Yu, K.: Multi-task joint-learning of deep neural networks for robust speech recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 310\u2013316. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404810"},{"key":"28_CR25","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"},{"issue":"4","key":"28_CR26","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1109\/TASLP.2017.2661712","volume":"25","author":"C Spille","year":"2017","unstructured":"Spille, C., Kollmeier, B., Meyer, B.T., Spille, C., Kollmeier, B., Meyer, B.T.: Combining binaural and cortical features for robust speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 25(4), 756\u2013767 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"issue":"3","key":"28_CR27","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., Steeneken, H.J.: Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. In: Readings in Speech Recognition, pp. 393\u2013404. Elsevier (1990)","DOI":"10.1016\/B978-0-08-051584-7.50037-1"},{"issue":"4","key":"28_CR29","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/TASLP.2016.2528171","volume":"24","author":"ZQ Wang","year":"2016","unstructured":"Wang, Z.Q., Wang, D.: A joint training framework for robust automatic speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(4), 796\u2013806 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR30","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.csl.2017.11.003","volume":"49","author":"Z Wang","year":"2018","unstructured":"Wang, Z., Vincent, E., Serizel, R., Yan, Y.: Rank-1 constrained multichannel wiener filter for speech recognition in noisy environments. Comput. Speech Lang. 49, 37\u201351 (2018)","journal-title":"Comput. Speech Lang."}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27947-9_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:43:25Z","timestamp":1710348205000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-27947-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030279462","9783030279479"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27947-9_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"6 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","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":"10 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.kiv.zcu.cz\/tsd2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"inhouse TSD Web App 3.1","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"73","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":"33","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":"45% - 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":"2-4","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":"2,42","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":"1 full invited talk","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)"}}]}}