{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:28:32Z","timestamp":1742912912405,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602758"},{"type":"electronic","value":"9783030602765"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-60276-5_58","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"603-612","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Noisy Speech Parameterization Using Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Ryhor","family":"Vashkevich","sequence":"first","affiliation":[]},{"given":"Elias","family":"Azarov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"58_CR1","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. http:\/\/arxiv.org\/abs\/1609.03499 . Accessed 26 Nov 2019"},{"key":"58_CR2","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. http:\/\/arxiv.org\/abs\/1512.02595 . Accessed 13 Jan 2020"},{"key":"58_CR3","unstructured":"Collobert, R., Puhrsch, C., Synnaeve, G.: Wav2Letter: an end-to-end convnet-based speech recognition system. http:\/\/arxiv.org\/abs\/1609.03193 . Accessed 15 Jan 2020"},{"key":"58_CR4","doi-asserted-by":"publisher","unstructured":"Prenger, R., Valle, R., Catanzaro, B.: Waveglow: a flow-based generative network for speech synthesis. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, pp. 3617\u20133621 (2019). https:\/\/doi.org\/10.1109\/icassp.2019.8683143","DOI":"10.1109\/icassp.2019.8683143"},{"key":"58_CR5","doi-asserted-by":"publisher","DOI":"10.1002\/0470041978","volume-title":"Audio Signal Processing and Coding","author":"A Spanias","year":"2007","unstructured":"Spanias, A., Painter, T., Atti, V.: Audio Signal Processing and Coding. Wiley, Hoboken (2007)"},{"issue":"12","key":"58_CR6","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.1109\/TASLP.2015.2476762","volume":"23","author":"I-C Yoo","year":"2015","unstructured":"Yoo, I.-C., Lim, H., Yook, D.: Formant-based robust voice activity detection. Trans. Audio Speech Lang. Process. 23(12), 2238\u20132245 (2015). https:\/\/doi.org\/10.1109\/TASLP.2015.2476762","journal-title":"Trans. Audio Speech Lang. Process."},{"key":"58_CR7","doi-asserted-by":"publisher","unstructured":"Pang, J.: Spectrum energy based voice activity detection. In: The 7th IEEE Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, USA, pp. 1\u20135 (2017). https:\/\/doi.org\/10.1109\/CCWC.2017.7868454","DOI":"10.1109\/CCWC.2017.7868454"},{"key":"58_CR8","unstructured":"Kinnunen, T., et al.: Voice activity detection using MFCC features and support vector machine. In: The 12th International Conference on Speech and Computer (SPECOM07), Moscow, Russia, vol. 2, pp. 556\u2013561 (2007)"},{"key":"58_CR9","doi-asserted-by":"publisher","unstructured":"Zazo, R., Sainath, T.N., Simko, G., Parada, C.: Feature learning with raw-waveform CLDNNs for voice activity detection. In: 17th Annual Conference of the International Speech Communication Association, San Francisco, USA, pp. 3668\u20133672 (2016). https:\/\/doi.org\/10.21437\/interspeech.2016-268","DOI":"10.21437\/interspeech.2016-268"},{"key":"58_CR10","doi-asserted-by":"publisher","unstructured":"Zhang, X., Wu, J.: Denoising deep neural networks based voice activity detection. In: International Conference on Acoustics Speech and Signal Processing, Vancouver, Canada, pp. 853\u2013857 (2013). https:\/\/doi.org\/10.1109\/ICASSP.2013.6637769","DOI":"10.1109\/ICASSP.2013.6637769"},{"key":"58_CR11","doi-asserted-by":"crossref","unstructured":"Ryant, N., Liberman, M., Yuan, J.: Speech activity detection on youtube using deep neural networks. In: 14th Annual Conference of the International Speech Communication Association Lyon, France, pp. 728\u2013731 (2013)","DOI":"10.21437\/Interspeech.2013-203"},{"key":"58_CR12","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: A universal VAD based on jointly trained deep neural networks. In: 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, pp. 2282\u20132286 (2015)","DOI":"10.21437\/Interspeech.2015-442"},{"key":"58_CR13","doi-asserted-by":"publisher","unstructured":"Hughes, T., Mierle, K.: Recurrent neural networks for voice activity detection. In: International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada, pp. 7378\u20137382 (2013). https:\/\/doi.org\/10.1109\/ICASSP.2013.6639096","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"58_CR14","doi-asserted-by":"publisher","unstructured":"Eyben, F., Weninger, F., Squartini, S., Schuller, B.: Real-life voice activity detection with LSTM recurrent neural networks and an application to Hollywood movies. In: International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada, pp. 483\u2013487 (2013). https:\/\/doi.org\/10.1109\/ICASSP.2013.6637694","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"58_CR15","unstructured":"Python interface to the WebRTC Voice Activity Detector. https:\/\/github.com\/wiseman\/py-webrtcvad"},{"key":"58_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"58_CR17","doi-asserted-by":"publisher","unstructured":"Valentini-Botinhao, C.: Noisy speech database for training speech enhancement algorithms and TTS models [sound]. University of Edinburgh. School of Informatics. Centre for Speech Technology Research (CSTR) (2017). https:\/\/doi.org\/10.7488\/ds\/2117","DOI":"10.7488\/ds\/2117"},{"key":"58_CR18","unstructured":"Snyder, D., Chen, G., Povey, D.: Musan: a music, speech, and noise corpus. arXiv preprint arXiv:1510.08484 (2015)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T02:43:30Z","timestamp":1669085010000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_58","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St. Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","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":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","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":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","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":"160","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":"65","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":"41% - 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":"5","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":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","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)"}}]}}