{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:12:36Z","timestamp":1743109956048,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916443"},{"type":"electronic","value":"9789819916450"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-1645-0_40","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:03:13Z","timestamp":1681405393000},"page":"482-492","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GhostVec: Directly Extracting Speaker Embedding from\u00a0End-to-End Speech Recognition Model Using Adversarial Examples"],"prefix":"10.1007","author":[{"given":"Xiaojiao","family":"Chen","sequence":"first","affiliation":[]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"40_CR1","unstructured":"Campbell, W., et al.: SVM based speaker verification using a GMM supervector Kernel and NAP variability compensation. In: Proceedings IEEE-ICASSP (2006)"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Audio adversarial examples: targeted attacks on speech-to-text. in Proceedings IEEE Security and Privacy Workshops (SPW), pp. 1\u20137 (2018)","DOI":"10.1109\/SPW.2018.00009"},{"key":"40_CR3","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":"40_CR4","unstructured":"Chen, G., et al.: Who is real bob? adversarial attacks on speaker recognition systems. arXiv preprint arXiv:1911.01840 (2019)"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Cooper, E., Lai, C.I., Yasuda, Y., Fang, F., Wang, X., Chen, N., Yamagishi, J.: Zero-shot multi-speaker text-to-speech with state-of-the-art neural speaker embeddings. In: Proc. IEEE-ICASSP, pp. 6184\u20136188 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Dalmia, S., Liu, Y., Ronanki, S., Kirchhoff, K.: Transformer-transducers for code-switched speech recognition. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5859\u20135863. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413562"},{"key":"40_CR7","first-page":"788","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., et al.: Front-end factor analysis for speaker verification. IEEE Trans. ASLP 19, 788\u2013798 (2011)","journal-title":"IEEE Trans. ASLP"},{"key":"40_CR8","doi-asserted-by":"publisher","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135888 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8462506","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"40_CR9","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"40_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101199","volume":"68","author":"A Jati","year":"2021","unstructured":"Jati, A., Hsu, C.C., Pal, M., Peri, R., AbdAlmageed, W., Narayanan, S.: Adversarial attack and defense strategies for deep speaker recognition systems. Comput. Speech Lang. 68, 101199 (2021)","journal-title":"Comput. Speech Lang."},{"key":"40_CR11","unstructured":"Jia, Y., et al.: Transfer learning from speaker verification to multispeaker text-to-speech synthesis. In: Advances in Neural Information Processing Systems, pp. 4480\u20134490 (2018)"},{"issue":"5","key":"40_CR12","first-page":"980","volume":"16","author":"P Kenny","year":"2008","unstructured":"Kenny, P., et al.: A study of inter-speaker variability in speaker verification. IEEE Trans. ASLP 16(5), 980\u2013988 (2008)","journal-title":"IEEE Trans. ASLP"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Kreuk, F., Adi, Y., Cisse, M., Keshet, J.: Fooling end-to-end speaker verification with adversarial examples. In: Proceedings IEEE-ICASSP, pp. 1962\u20131966 (2018)","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Li, C.Y., Yuan, P.C., Lee, H.Y.: What does a network layer hear? Analyzing hidden representations of end-to-end ASR through speech synthesis. In: Proceedings IEEE-ICASSP, pp. 6434\u20136438 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054675"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Li, S., Dabre, R., Lu, X., Shen, P., Kawahara, T., Kawai, H.: Improving transformer-based speech recognition systems with compressed structure and speech attributes augmentation. In: Proceedings INTERSPEECH (2019)","DOI":"10.21437\/Interspeech.2019-2112"},{"key":"40_CR16","doi-asserted-by":"publisher","unstructured":"Li, S., lu, X., Dabre, R., Shen, P., Kawai, H.: Joint training end-to-end speech recognition systems with speaker attributes, pp. 385\u2013390 (2020). https:\/\/doi.org\/10.21437\/Odyssey","DOI":"10.21437\/Odyssey"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, J., Wu, X., Yu, J., Liu, X., Meng, H.: Adversarial attacks on GMM i-vector based speaker verification systems. In: Proceedings IEEE-ICASSP, pp. 6579\u20136583 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"40_CR18","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J.: UMAP: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)","DOI":"10.21105\/joss.00861"},{"key":"40_CR20","unstructured":"Miyato, T., Maeda, S., Koyama, M., Nakae, K., Ishii, S.: Distributional smoothing with virtual adversarial training. arXiv preprint arXiv:1507.00677 (2015)"},{"issue":"1","key":"40_CR21","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/375360.375365","volume":"33","author":"G Navarro","year":"2001","unstructured":"Navarro, G.: A guided tour to approximate string matching. ACM Comput. Surv. (CSUR) 33(1), 31\u201388 (2001)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"40_CR22","doi-asserted-by":"publisher","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 (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Sar\u0131, L., Moritz, N., Hori, T., Le Roux, J.: Unsupervised speaker adaptation using attention-based speaker memory for end-to-end ASR. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7384\u20137388. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054249"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Snyder, D., et al.: X-vectors: Robust DNN embeddings for speaker recognition. In: Proceedings IEEE-ICASSP, pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"40_CR25","unstructured":"Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Variani, E., et al.: Deep neural networks for small footprint text-dependent speaker verification, pp. 4052\u20134056 (2014)","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"40_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. CoRR abs\/1706.03762 (2017)"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Q., Guo, P., Sun, S., Xie, L., Hansen, J.: Adversarial regularization for end-to-end robust speaker verification. In: Proceedings INTERSPEECH, pp. 4010\u20134014 (2019)","DOI":"10.21437\/Interspeech.2019-2983"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Q., Guo, P., Xie, L.: Inaudible adversarial perturbations for targeted attack in speaker recognition. arXiv preprint arXiv:2005.10637 (2020)","DOI":"10.21437\/Interspeech.2020-1955"},{"key":"40_CR30","unstructured":"Yuan, X., et al.: CommanderSong: a systematic approach for practical adversarial voice recognition. In: Proceedings 27th $$\\{$$USENIX$$\\}$$ Security Symposium ($$\\{$$USENIX$$\\}$$ Security 18), pp. 49\u201364 (2018)"},{"key":"40_CR31","doi-asserted-by":"crossref","unstructured":"Zeyer, A., Bahar, P., Irie, K., Schl\u00fcter, R., Ney, H.: A comparison of transformer and LSTM encoder decoder models for ASR. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 8\u201315. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: Transformer transducer: a streamable speech recognition model with transformer encoders and RNN-T loss. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7829\u20137833. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"40_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Ni, C., Leung, C.C., Joty, S.R., Chng, E.S., Ma, B.: Speech transformer with speaker aware persistent memory. In: INTERSPEECH. pp. 1261\u20131265 (2020)","DOI":"10.21437\/Interspeech.2020-1281"},{"key":"40_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1007\/978-3-030-91356-4_19","volume-title":"Information Security","author":"W Zong","year":"2021","unstructured":"Zong, W., Chow, Y.-W., Susilo, W., Rana, S., Venkatesh, S.: Targeted universal adversarial perturbations for\u00a0automatic speech recognition. In: Liu, J.K., Katsikas, S., Meng, W., Susilo, W., Intan, R. (eds.) ISC 2021. LNCS, vol. 13118, pp. 358\u2013373. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-91356-4_19"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1645-0_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:18:43Z","timestamp":1681406323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1645-0_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916443","9789819916450"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1645-0_40","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"2.65","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}