{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:55:07Z","timestamp":1764784507794,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"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_3","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"22-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["MP3 Compression to Diminish Adversarial Noise in End-to-End Speech Recognition"],"prefix":"10.1007","author":[{"given":"Iustina","family":"Andronic","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5312-3870","authenticated-orcid":false,"given":"Ludwig","family":"K\u00fcrzinger","sequence":"additional","affiliation":[]},{"given":"Edgar Ricardo","family":"Chavez Rosas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1096-1596","authenticated-orcid":false,"given":"Gerhard","family":"Rigoll","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3621-3409","authenticated-orcid":false,"given":"Bernhard U.","family":"Seeber","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"3_CR1","unstructured":"Alzantot, M., Balaji, B., Srivastava, M.: Did you hear that? adversarial examples against automatic speech recognition. arXiv preprint arXiv:1801.00554 (2018)"},{"key":"3_CR2","unstructured":"Andronic, I.: MP3 Compression as a Means to Improve Robustness against Adversarial Noise Targeting Attention-based End-to-End Speech Recognition. Master\u2019s thesis, Technical University of Munich, Germany (2020)"},{"key":"3_CR3","unstructured":"Brandenburg, K.: MP3 and AAC Explained. In: Audio Engineering Society, 17th International Conference 2004 October 26\u201329, pp. 99\u2013110 (1999)"},{"key":"3_CR4","unstructured":"Carlini, N., et al.: Hidden voice commands. In: 25th USENIX Security Symposium (USENIX Security 16), pp. 513\u2013530. USENIX Association, August 2016"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Audio adversarial examples: targeted attacks on speech-to-text. In: Proceedings - 2018 IEEE Symposium on Security and Privacy Workshops, SPW 2018, pp. 1\u20137 (2018)","DOI":"10.1109\/SPW.2018.00009"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4960\u20134964. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"3_CR7","unstructured":"Chavez Rosas, E.R.: Improving Robustness of Sequence-to-sequence Automatic Speech Recognition by Means of Adversarial Training. Master\u2019s thesis, Technical University of Munich, Germany (2020)"},{"key":"3_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-030-10997-4_50","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"N Das","year":"2019","unstructured":"Das, N., Shanbhogue, M., Chen, S.-T., Chen, L., Kounavis, M.E., Chau, D.H.: ADAGIO: interactive experimentation with adversarial attack and defense for audio. In: Brefeld, U., et al. (eds.) ECML PKDD 2018. LNCS (LNAI), vol. 11053, pp. 677\u2013681. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-10997-4_50"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Dong, Y., et al.: Boosting adversarial attacks with momentum. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9185\u20139193 (2018)","DOI":"10.1109\/CVPR.2018.00957"},{"key":"3_CR10","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, pp. 1\u201311 (2015)"},{"key":"3_CR11","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. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"3_CR12","unstructured":"Hannun, A., et al.: Deep speech: scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"issue":"10","key":"3_CR13","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1109\/MCOM.2019.1900006","volume":"57","author":"S Hu","year":"2019","unstructured":"Hu, S., Shang, X., Qin, Z., Li, M., Wang, Q., Wang, C.: Adversarial examples for automatic speech recognition: attacks and countermeasures. IEEE Commun. Mag. 57(10), 120\u2013126 (2019)","journal-title":"IEEE Commun. Mag."},{"key":"3_CR14","unstructured":"Iter, D., Huang, J., Jermann, M.: Generating adversarial examples for speech recognition. Stanford Technical report (2017)"},{"key":"3_CR15","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"K\u00fcrzinger, L., Rosas, E.R.C., Li, L., Watzel, T., Rigoll, G.: Audio adversarial examples for robust hybrid ctc\/attention speech recognition. arXiv preprint arXiv:2007.10723 , To be published at SPECOM 2020 (2020)","DOI":"10.1007\/978-3-030-60276-5_26"},{"key":"3_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-030-26061-3_27","volume-title":"Speech and Computer","author":"L K\u00fcrzinger","year":"2019","unstructured":"K\u00fcrzinger, L., Watzel, T., Li, L., Baumgartner, R., Rigoll, G.: Exploring Hybrid CTC\/Attention end-to-end speech recognition with gaussian processes. In: Salah, A.A., Karpov, A., Potapova, R. (eds.) SPECOM 2019. LNCS (LNAI), vol. 11658, pp. 258\u2013269. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-26061-3_27"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in python. In: Proceedings of the 14th Python in Science Conference, vol. 8 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE Symposium on Security and Privacy (SP), pp. 582\u2013597. IEEE (2016)","DOI":"10.1109\/SP.2016.41"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Rajaratnam, K., Alshemali, B., Kalita, J.: Speech coding and audio preprocessing for mitigating and detecting audio adversarial examples on automatic speech recognition, August 2018","DOI":"10.1109\/ISSPIT.2018.8642623"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nherr, L., Kohls, K., Zeiler, S., Holz, T., Kolossa, D.: Adversarial attacks against automatic speech recognition systems via psychoacoustic hiding. arXiv preprint arXiv:1808.05665 (2018)","DOI":"10.14722\/ndss.2019.23288"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nherr, L., Zeiler, S., Holz, T., Kolossa, D.: Imperio: Robust over-the-air adversarial examples against automatic speech recognition systems. arXiv preprint arXiv:1908.01551 (2019)","DOI":"10.14722\/ndss.2019.23288"},{"issue":"11","key":"3_CR23","doi-asserted-by":"publisher","first-page":"1826","DOI":"10.1109\/TASLP.2019.2933146","volume":"27","author":"S Sun","year":"2019","unstructured":"Sun, S., Guo, P., Xie, L., Hwang, M.Y.: Adversarial regularization for attention based end-to-end robust speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(11), 1826\u20131838 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Watanabe, S., et al.: ESPNet: end-to-end speech processing toolkit. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2018-Sep, pp. 2207\u20132211 (2018)","DOI":"10.21437\/Interspeech.2018-1456"},{"issue":"8","key":"3_CR25","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","volume":"11","author":"S Watanabe","year":"2017","unstructured":"Watanabe, S., Hori, T., Kim, S., Hershey, J.R., Hayashi, T.: Hybrid CTC\/attention architecture for end-to-end speech recognition. IEEE J. Sel. Top. Sign. Proces. 11(8), 1240\u20131253 (2017)","journal-title":"IEEE J. Sel. Top. Sign. Proces."},{"key":"3_CR26","unstructured":"Yang, Z., Li, B., Chen, P.Y., Song, D.: Towards mitigating audio adversarial perturbations (2018). https:\/\/openreview.net\/forum?id=SyZ2nKJDz"}],"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_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T02:06:49Z","timestamp":1617674809000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_3","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)"}}]}}