{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:49:59Z","timestamp":1760240999567,"version":"build-2065373602"},"publisher-location":"Basel Switzerland","reference-count":26,"publisher":"MDPI","license":[{"start":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T00:00:00Z","timestamp":1574208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.3390\/proceedings2019031037","type":"proceedings-article","created":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T11:06:03Z","timestamp":1574247963000},"page":"37","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["On the Use of Fisher Vector Encoding for Voice Spoofing Detection"],"prefix":"10.3390","author":[{"given":"Jahangir","family":"Alam","sequence":"first","affiliation":[{"name":"Computer Research Institute of Montreal (CRIM), Montr\u00e9al, QC H3N 1M3, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2019,11,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Marcel, S., Li, S., and Nixon, M. (2014). Speaker recognition anti-spoofing. Handbook of Biometric Anti-Spoofing, Springer-Verlag.","DOI":"10.1007\/978-1-4471-6524-8"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kinnunen, T., Wu, Z., Lee, K.A., Sedlak, F., Chng, E.S., and Li, H. (2012, January 25\u201330). Vulnerability of speaker verification systems against voice conversion spoofing attacks: The case of telephone speech. Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan.","DOI":"10.1109\/ICASSP.2012.6288895"},{"key":"ref_3","unstructured":"de Leon, P.L., Pucher, M., and Yamagishi, J. (July, January 28). Evaluation of the vulnerability of speaker verification to synthetic speech. Proceedings of the IEEE Speaker and Language Recognition Workshop (Odyssey), Brno, Czech Republic."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wu, Z., Kinnunen, T., Evans, N., Yamagishi, J., Hanilc\u0327i, C., Sahidullah, M., and Sizov, A. (2015, January 6\u201310). ASVspoof 2015: The First ASV Spoofing and Countermeasures Challenge. Proceedings of the INTERSPEECH 2015, Dresden, Germany. Available online: http:\/\/www.spoofingchallenge.org\/is2015_asvspoof.pdf.","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, N., Qian, Y., Dinkel, H., Chen, B., and Yu, K. (2015, January 6\u201310). Robust Deep Feature for Spoofing Detection\u2014The SJTU System for ASVspoof 2015 Challenge. Proceedings of the Interspeech 2015, Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-474"},{"key":"ref_6","unstructured":"van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). Wavenet: A generative model for raw audio. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, Y., Skerry-Ryan, R., Stanton, D., Wu, Y., Weiss, R.J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., and Bengio, S. (2017, January 20\u201324). Tacotron: Towards end-to-end speech synthesis. Proceedings of the Interspeech 2017, Stockholm, Sweden.","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Tamamori, A., Hayashi, T., Kobayashi, K., Takeda, K., and Toda, T. (2017, January 20\u201324). Speaker-dependent WaveNet vocoder. Proceedings of the Interspeech 2017, Stockholm, Sweden.","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Hojo, N., Ijima, Y., Hiramatsu, K., and Kashino, K. (2017, January 5\u20139). Generative adversarial network-based postfilter for statistical parametric speech synthesis. Proceedings of the 2017 ICASSP, New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7953090"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1016\/j.csl.2017.01.001","article-title":"Constant Q Cepstral Coefficients: A Spoofing Countermeasure for Automatic Speaker Verification","volume":"45","author":"Todisco","year":"2017","journal-title":"Comput. Speech Lang."},{"key":"ref_11","unstructured":"Alam, J., and Kenny, P. (September, January 28). Spoofing Detection Employing Infinite Impulse Response\u2014Constant Q Transform-based Feature Representations. Proceedings of the EUSIPCO, Kos Island, Greece."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Alam, J., Kenny, P., Gupta, V., and Stafylakis, T. (2016, January 21\u201324). Spoofing Detection on the ASVSpoof2015 Challenge Corpus Employing Deep Neural Networks. Proceedings of the Odyssey Speaker and Language Recognition Workshop, Bilbao, Spain.","DOI":"10.21437\/Odyssey.2016-39"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Alam, J., Kenny, P., Bhattacharya, G., and Stafylakis, T. (2015, January 6\u201310). Development of CRIM System for the Automatic Speaker Verification Spoofing and Countermeasures Challenge 2015. Proceedings of the Interspeech 2015, Dresden, Germany. Available online: https:\/\/www.asvspoof.org\/asvspoof2015\/CRIM.pdf.","DOI":"10.21437\/Interspeech.2015-469"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Patel, T.B., and Patil, H.A. (2015, January 6\u201310). Combining Evidences from Mel Cepstral, Cochlear Filter Cepstral and Instantaneous Frequency Features for Detection of Natural vs. Spoofed Speech. Proceedings of the Interspeech 2015, Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-467"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xiao, X., Tian, X., Du, S., Xu, H., Chng, E.S., and Li, H. (2015, January 6\u201310). Spoofing Speech Detection Using High Dimensional Magnitude and Phase Features: The NTU Approach for ASVspoof 2015 Challenge. Proceedings of the Interspeech 2015, Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-465"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tian, X., Wu, Z., Xiao, X., Chng, E.S., and Li, H. (2016, January 20\u201325). Spoofing detection from a feature representation perspective. Proceedings of the ICASSP, Shanghai, China.","DOI":"10.1109\/ICASSP.2016.7472051"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Patel, T., and Patil, H. (2016, January 20\u201325). Effectiveness of fundamental frequency (F0) and strength of excitation (SOE) for spoofed speech detection. Proceedings of the ICASSP, Shanghai, China.","DOI":"10.1109\/ICASSP.2016.7472650"},{"key":"ref_18","unstructured":"Jaakkola, T., and Haussler, D. (December, January 30). Exploiting generative models in discriminative classifiers. Proceedings of the Advances in Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Perronnin, F., and Dance, C. (2007, January 17\u201322). Fisher kernels on visual vocabularies for image categorization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., Sanchez, J., and Poirier, H. (2010, January 13\u201318). Large-scale Image Retrieval with Compressed Fisher Vectors. Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kaya, H., Karpov, A., and Salah, A.A. (2015, January 6\u201310). Fisher Vectors with Cascaded Normalization for Paralinguistic Analysis. Proceedings of the Interspeech 2015, Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-193"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Sahidullah, M., Kinnunen, T., and Hanil\u00e7i, C. (2015, January 6\u201310). A Comparison of Features for Synthetic Speech Detection. Proceedings of the Interspeech 2015, Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"Dehak","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"ref_24","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., and Schwarz, P. (2011, January 11\u201315). The kaldi speech recognition toolkit. Proceedings of the IEEE 2011 workshop on automatic speech recognition and understanding, IEEE Signal Processing Society, Big Island, HI, USA."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Saito, D., Yamamoto, K., Minematsu, N., and Hirose, K. (2011, January 27\u201331). One-to-many voice conversion based on tensor representation of speaker space. Proceedings of the Interspeech 2011, Florence, Italy.","DOI":"10.21437\/Interspeech.2011-268"},{"key":"ref_26","unstructured":"The MARY TTS\u2014An Open-Source, Multilingual Text-To-Speech Synthesis System. (the first version was released on 14 February 2006)."}],"event":{"name":"The International Conference on Ubiquitous Computing and Ambient \u202aIntelligence","acronym":"UCAmI 2019"},"container-title":["13th International Conference on Ubiquitous Computing and Ambient \u202aIntelligence UCAmI 2019\u202c"],"original-title":[],"link":[{"URL":"https:\/\/www.mdpi.com\/2504-3900\/31\/1\/37\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:35:53Z","timestamp":1760189753000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-3900\/31\/1\/37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,20]]},"references-count":26,"alternative-id":["proceedings2019031037"],"URL":"https:\/\/doi.org\/10.3390\/proceedings2019031037","relation":{},"subject":[],"published":{"date-parts":[[2019,11,20]]}}}