{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:40:41Z","timestamp":1764020441280,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030708658"},{"type":"electronic","value":"9783030708665"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","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":[[2021]]},"DOI":"10.1007\/978-3-030-70866-5_16","type":"book-chapter","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T16:03:57Z","timestamp":1614701037000},"page":"245-254","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Spectral Analysis for Automatic Speech Recognition and Enhancement"],"prefix":"10.1007","author":[{"given":"Jane","family":"Oruh","sequence":"first","affiliation":[]},{"given":"Serestina","family":"Viriri","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,3]]},"reference":[{"key":"16_CR1","unstructured":"Nasreen, P.N., Kumar, A.C., Nabeel, P.A.: Speech analysis for automatic speech recognition. In: Proceedings of International Conference on Computing, Communication and Science (2016)"},{"key":"16_CR2","unstructured":"Delcroix, M., et al.: Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the REVERB challenge. In: Reverb workshop (2014)"},{"key":"16_CR3","volume-title":"Speech Processing in Modern Communication: Challenges and Perspectives","author":"I Cohen","year":"2009","unstructured":"Cohen, I., Benesty, J., Gannot, S.: Speech Processing in Modern Communication: Challenges and Perspectives, vol. 3. Springer Science & Business Media, Berlin (2009)"},{"issue":"3","key":"16_CR4","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/MCAS.2016.2583681","volume":"16","author":"M Parchami","year":"2016","unstructured":"Parchami, M., Zhu, W.-P., Champagne, B., Plourde, E.: Recent developments in speech enhancement in the short-time Fourier transform domain. IEEE Circ. Syst. Mag. 16(3), 45\u201377 (2016)","journal-title":"IEEE Circ. Syst. Mag."},{"issue":"10","key":"16_CR5","doi-asserted-by":"publisher","first-page":"2964","DOI":"10.1109\/78.869059","volume":"48","author":"HK Kwok","year":"2000","unstructured":"Kwok, H.K., Jones, D.L.: Improved instantaneous frequency estimation using an adaptive short-time Fourier transform. IEEE Trans. Sig. Process. 48(10), 2964\u20132972 (2000)","journal-title":"IEEE Trans. Sig. Process."},{"key":"16_CR6","doi-asserted-by":"publisher","first-page":"5118","DOI":"10.1109\/TSP.2010.2053028","volume":"58","author":"J Zhong","year":"2010","unstructured":"Zhong, J., Huang, Y.: Time-frequency representation based on an adaptive short-time Fourier transform. IEEE Trans. Sig. Process. 58, 5118\u20135128 (2010)","journal-title":"IEEE Trans. Sig. Process."},{"issue":"10","key":"16_CR7","doi-asserted-by":"publisher","first-page":"e0205355","DOI":"10.1371\/journal.pone.0205355","volume":"13","author":"DT Toledano","year":"2018","unstructured":"Toledano, D.T., Fern\u00e1ndez-Gallego, M.P., Lozano-Diez, A.: Multi-resolution speech analysis for automatic speech recognition using deep neural networks: experiments on TIMIT. PloS one 13(10), e0205355 (2018)","journal-title":"PloS one"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"T\u00fcske, Z., Golik, P., Schl\u00fcter, R., Drepper, F.R.: Non-stationary feature extraction for automatic speech recognition. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5204\u20135207. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5947530"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Parchami, M.: New Approaches for Speech Enhancement in the Short-Time Fourier Transform Domain. PhD thesis, Concordia University (2016)","DOI":"10.1109\/MCAS.2016.2583681"},{"key":"16_CR10","unstructured":"Ahmadizadeh, M.: An Introduction to Short-Time Fourier Transform (STFT). Advanced Structural Dynamics, April 2014"},{"key":"16_CR11","unstructured":"Jurafsky, D., Martin, J.H.: Speech and Language Processing, vol. 3 (2014)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Solovyev, R.A., et al.: Deep learning approaches for understanding simple speech commands. In: 2020 IEEE 40th International Conference on Electronics and Nanotechnology (ELNANO), pp. 688\u2013693. IEEE (2020)","DOI":"10.1109\/ELNANO50318.2020.9088863"},{"issue":"2","key":"16_CR13","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.specom.2004.08.001","volume":"45","author":"KK Paliwal","year":"2005","unstructured":"Paliwal, K.K., Alsteris, L.D.: On the usefulness of STFT phase spectrum in human listening tests. Speech Communi. 45(2), 153\u2013170 (2005)","journal-title":"Speech Communi."},{"issue":"2","key":"16_CR14","first-page":"126","volume":"7","author":"A Dutta","year":"2016","unstructured":"Dutta, A., Valiveti, G.R.S.: Enhancing the performance of audio visual speech recognition using deep learning techniques. Int. J. Comput. Sci. Commun. 7(2), 126\u2013135 (2016)","journal-title":"Int. J. Comput. Sci. Commun."},{"key":"16_CR15","unstructured":"Creative Commons. Creative Commons Attribution 4.0 International (CC BY 4.0) License. https:\/\/creativecommons.org\/licenses\/by\/4.0\/. Accessed 07 Nov 2017"},{"key":"16_CR16","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"},{"issue":"12","key":"16_CR17","first-page":"1400","volume":"8","author":"P Sarma","year":"2019","unstructured":"Sarma, P., Sarmah, S., Bhuyan, M.P., Hore, K., Das, P.P.: Automatic spoken digit recognition using artificial neural network. Int. J. Sci. Technol. Res. 8(12), 1400\u20131404 (2019)","journal-title":"Int. J. Sci. Technol. Res."},{"key":"16_CR18","unstructured":"Gutierrez-Osuna, R.: Introduction to speech processing. CSE@ TAMU (2016)"},{"key":"16_CR19","doi-asserted-by":"publisher","first-page":"4065","DOI":"10.1109\/TSP.2012.2197204","volume":"60","author":"S-C Pei","year":"2012","unstructured":"Pei, S.-C., Huang, S.-G.: STFT with adaptive window width based on the chirp rate. IEEE Trans. Sig. Process. 60, 4065\u20134080 (2012)","journal-title":"IEEE Trans. Sig. Process."},{"issue":"2","key":"16_CR20","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/97.554468","volume":"4","author":"RN Czerwinski","year":"1997","unstructured":"Czerwinski, R.N., Jones, D.L.: Adaptive short-time Fourier analysis. IEEE Sig. Process. Lett. 4(2), 42\u201345 (1997)","journal-title":"IEEE Sig. Process. Lett."},{"key":"16_CR21","unstructured":"McFee, B., et al.: Librosa: v0.4.0.Zenodo. In: Proceedings of the 14th Python in Science Conference (SCIPY 2015) (2015)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Singh, J., Kaur, K.: Speech enhancement for Punjabi language using deep neural network. In: 2019 International Conference on Signal Processing and Communication (ICSC), pp. 202\u2013204. IEEE (2019)","DOI":"10.1109\/ICSC45622.2019.8938309"},{"key":"16_CR23","unstructured":"F. A. Q. International Computer Science Institute (ICSI) Speech. https:\/\/www1.icsi.berkeley.edu\/Speech\/faq\/speechSNR.html. Accessed 17 Sep 2019"},{"issue":"6","key":"16_CR24","first-page":"289","volume":"1","author":"PDA Athaley","year":"2017","unstructured":"Athaley, P.D.A.: Audio signal denoising algorithm by adaptive block thresholding using STFT. Int. J. Trend Sci. Res. Dev. 1(6), 289\u2013300 (2017)","journal-title":"Int. J. Trend Sci. Res. Dev."}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Networking"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-70866-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T16:14:37Z","timestamp":1614701677000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-70866-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030708658","9783030708665"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-70866-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"3 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MLN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning for Networking","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2020","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":"mln2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.adda-association.org\/mln-2020\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"50","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":"22","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":"44% - 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":"3","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic this event was held virtually.","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)"}}]}}