{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:59:08Z","timestamp":1740099548892,"version":"3.37.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030313715"},{"type":"electronic","value":"9783030313722"}],"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\/978-3-030-31372-2_18","type":"book-chapter","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T00:02:49Z","timestamp":1569542569000},"page":"210-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving Speech Recognition with Drop-in Replacements for f-Bank Features"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9680-3753","authenticated-orcid":false,"given":"Sean","family":"Robertson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3553-8305","authenticated-orcid":false,"given":"Gerald","family":"Penn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7613-5700","authenticated-orcid":false,"given":"Yingxue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,27]]},"reference":[{"issue":"3","key":"18_CR1","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/BF00342772","volume":"39","author":"AMHJ Aertsen","year":"1981","unstructured":"Aertsen, A.M.H.J., Olders, J.H.J., Johannesma, P.I.M.: Spectro-temporal receptive fields of auditory neurons in the grassfrog. Biol. Cybern. 39(3), 195\u2013209 (1981)","journal-title":"Biol. Cybern."},{"issue":"16","key":"18_CR2","doi-asserted-by":"publisher","first-page":"4114","DOI":"10.1109\/TSP.2014.2326991","volume":"62","author":"J And\u00e9n","year":"2014","unstructured":"And\u00e9n, J., Mallat, S.: Deep scattering spectrum. IEEE Trans. Signal Process. 62(16), 4114\u20134128 (2014)","journal-title":"IEEE Trans. Signal Process."},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Chang, S.-Y., Meyer, B.T., Morgan, N.: Spectro-temporal features for noise-robust speech recognition using power-law nonlinearity and power-bias subtraction. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 7063\u20137067 (2013)","DOI":"10.1109\/ICASSP.2013.6639032"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Chang, S.Y., Morgan, N.: Robust CNN-based speech recognition with Gabor filter kernels. In: Proceedings Interspeech (2014)","DOI":"10.21437\/Interspeech.2014-226"},{"key":"18_CR5","unstructured":"Chollet, F., et al.: Keras. https:\/\/keras.io (2015)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Degottex, G., Kane, J., Drugman, T., Raitio, T., Scherer, S.: COVAREP \u2014 A collaborative voice analysis repository for speech technologies. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 960\u2013964 (2014)","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"18_CR7","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2172153","volume":"20","author":"L Deng","year":"2012","unstructured":"Deng, L., Acero, A., Dahl, G., Yu, D.: Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio, Speech, Lang. Process. 20, 30\u201342 (2012)","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"issue":"6","key":"18_CR8","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1109\/TASL.2010.2092766","volume":"19","author":"D Dimitriadis","year":"2011","unstructured":"Dimitriadis, D., Maragos, P., Potamianos, A.: On the effects of filterbank design and energy computation on robust speech recognition. IEEE Trans. Audio, Speech, Lang. Process. 19(6), 1504\u20131516 (2011)","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"issue":"5","key":"18_CR9","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1002\/j.1538-7305.1960.tb03955.x","volume":"39","author":"JL Flanagan","year":"1960","unstructured":"Flanagan, J.L.: Models for approximating basilar membrane displacement. Bell Syst. Tech. J. 39(5), 1163\u20131191 (1960)","journal-title":"Bell Syst. Tech. J."},{"issue":"200","key":"18_CR10","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","volume":"32","author":"M Friedman","year":"1937","unstructured":"Friedman, M.: The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J. Am. Stat. Assoc. 32(200), 675\u2013701 (1937)","journal-title":"J. Am. Stat. Assoc."},{"issue":"2","key":"18_CR11","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJF Gales","year":"1998","unstructured":"Gales, M.J.F.: Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Lang. 12(2), 75\u201398 (1998)","journal-title":"Comput. Speech Lang."},{"issue":"3","key":"18_CR12","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/89.759034","volume":"7","author":"MJF Gales","year":"1999","unstructured":"Gales, M.J.F.: Semi-tied covariance matrices for hidden Markov models. IEEE Trans. Speech Audio Process. 7(3), 272\u2013281 (1999)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"18_CR13","unstructured":"Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. In: Proceedings of the 30th International Conference on International Conference on Machine Learning. ICML 2013, vol. 28, pp. III-1319-III-1327 (2013)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning. pp. 369\u2013376. ICML 2006, ACM, New York, NY, USA (2006)","DOI":"10.1145\/1143844.1143891"},{"issue":"8","key":"18_CR15","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(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"2","key":"18_CR16","first-page":"65","volume":"6","author":"S Holm","year":"1979","unstructured":"Holm, S.: A simple sequentially rejective multiple test procedure. Scand. J. Stat. 6(2), 65\u201370 (1979)","journal-title":"Scand. J. Stat."},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Hoshen, Weiss, R.J., Wilson, K.W.: Speech acoustic modeling from raw multichannel waveforms. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 4624\u20134628 (2015)","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Kov\u00e1cs, G., T\u00f3th, L., Gosztolya, G.: Multi-band processing with gabor filters and time delay neural nets for noise robust speech recognition. In: IEEE Spoken Language Technology Workshop. pp. 242\u2013249 (2018)","DOI":"10.1109\/SLT.2018.8639631"},{"key":"18_CR19","volume-title":"A Wavelet Tour of Signal Processing: The Sparse Way","author":"S Mallat","year":"2008","unstructured":"Mallat, S.: A Wavelet Tour of Signal Processing: The Sparse Way. Elsevier Science, Amsterdam (2008)"},{"issue":"10","key":"18_CR20","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1002\/cpa.21413","volume":"65","author":"S Mallat","year":"2012","unstructured":"Mallat, S.: Group invariant scattering. Commun. Pure Appl. Math. 65(10), 1331\u20131398 (2012)","journal-title":"Commun. Pure Appl. Math."},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Sainath, T., Maymon, S., Ramabhadran, B., Nahamoo, D., Goel, V.: Deep scattering spectrum with deep neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 210\u2013214 (May 2014)","DOI":"10.1109\/ICASSP.2014.6853588"},{"key":"18_CR22","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society, Hilton Waikoloa Village, Big Island, Hawaii, US (Dec 2011)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Ravanelli, M., Bengio, Y.: Speech and Speaker Recognition from Raw Waveform with SincNet. CoRR abs\/1812.05920 (2018)","DOI":"10.1109\/SLT.2018.8639585"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Ravanelli, M., Brakel, P., Omologo, M., Bengio, Y.: Improving speech recognition by revising gated recurrent units. In: Proceedings Interspeech. pp. 1308\u20131312 (2017)","DOI":"10.21437\/Interspeech.2017-775"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Weiss, R.J., Senior, A., Wilson, K.W., Vinyals, O.: Learning the speech front-end with raw waveform CLDNNs. In: Proceedings Interspeech (2015)","DOI":"10.21437\/Interspeech.2015-1"},{"issue":"4","key":"18_CR26","doi-asserted-by":"publisher","first-page":"2047","DOI":"10.1121\/1.4916618","volume":"137","author":"MR Sch\u00e4dler","year":"2015","unstructured":"Sch\u00e4dler, M.R., Kollmeier, B.: Separable spectro-temporal Gabor filter bank features: reducing the complexity of robust features for automatic speech recognition. J. Acoust. Soc. Am. 137(4), 2047\u20132059 (2015)","journal-title":"J. Acoust. Soc. Am."},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Schluter, R., Bezrukov, I., Wagner, H., Ney, H.: Gammatone features and feature combination for large vocabulary speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. vol. 4, pp. IV-649 (Apr 2007)","DOI":"10.1109\/ICASSP.2007.366996"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: Wav2vec: Unsupervised Pre-training for Speech Recognition. CoRR abs\/1904.05862 (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Shao, Y., Jin, Z., Wang, D., Srinivasan, S.: An auditory-based feature for robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 4625\u20134628 (Apr 2009)","DOI":"10.1109\/ICASSP.2009.4960661"},{"issue":"3","key":"18_CR30","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1121\/1.1915893","volume":"8","author":"SS Stevens","year":"1937","unstructured":"Stevens, S.S., Volkmann, J., Newman, E.B.: A scale for the measurement of the psychological magnitude pitch. J. Acoust. Soc. Am. 8(3), 185\u2013190 (1937)","journal-title":"J. Acoust. Soc. Am."},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"T\u00f3th, L.: Combining time- and frequency-domain convolution in convolutional neural network-based phone recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 190\u2013194 (May 2014)","DOI":"10.1109\/ICASSP.2014.6853584"},{"issue":"6","key":"18_CR32","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bullet. 1(6), 80\u201383 (1945)","journal-title":"Biometrics Bullet."},{"key":"18_CR33","unstructured":"Young, S., et al.: The HTK book (for HTK version 3.4). Cambridge University Engineering Department 2(2), 2\u20133 (2006)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Zeghidour, N., Usunier, N., Kokkinos, I., Schaiz, T., Synnaeve, G., Dupoux, E.: Learning filterbanks from raw speech for phone recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 5509\u20135513 (Apr 2018)","DOI":"10.1109\/ICASSP.2018.8462015"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Zeghidour, N., Usunier, N., Synnaeve, G., Collobert, R., Dupoux, E.: End-to-end speech recognition from the raw waveform. In: Proceedings Interspeech. pp. 781\u2013785 (2018)","DOI":"10.21437\/Interspeech.2018-2414"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Towards end-to-end speech recognition with deep convolutional neural networks. In: Proceedings Interspeech. pp. 410\u2013414 (2016)","DOI":"10.21437\/Interspeech.2016-1446"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31372-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T01:27:40Z","timestamp":1664501260000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-31372-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030313715","9783030313722"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31372-2_18","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":"27 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SLSP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Statistical Language and Speech Processing","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":"14 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/slsp2019.irdta.eu\/","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":"48","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":"25","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":"1","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":"4","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)"}}]}}