Filters








41 Hits in 4.6 sec

Generalized Spoofing Detection Inspired from Audio Generation Artifacts [article]

Yang Gao, Tyler Vuong, Mahsa Elyasi, Gaurav Bharaj, Rita Singh
<span title="2021-06-26">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Thus, we propose a novel use of long-range spectro-temporal modulation feature -- 2D DCT over log-Mel spectrogram for the audio deepfake detection.  ...  Finally, by combining our baseline with our proposed 2D DCT spectro-temporal feature, we decrease the t-DCF score down by 14% to 0.0737, making it a state-of-the-art system for spoofing detection.  ...  We propose a novel long-range spectro-temporal featureglobal modulation feature, for audio deepfake detection. 2.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.04111v2">arXiv:2104.04111v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bfq2n4mtv5f7lbejprck4kl2qu">fatcat:bfq2n4mtv5f7lbejprck4kl2qu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210701033547/https://arxiv.org/pdf/2104.04111v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e9/94/e99483365075a34816d9d344015189a1f5af04e4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.04111v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Explaining deep learning models for spoofing and deepfake detection with SHapley Additive exPlanations [article]

Wanying Ge, Jose Patino, Massimiliano Todisco, Nicholas Evans
<span title="2021-10-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Nonetheless, the community has yet to make notable inroads in providing an explanation for how a classifier produces its output.  ...  Substantial progress in spoofing and deepfake detection has been made in recent years.  ...  A study of replay detection [17] shows the impact of different replay attack configurations upon detection performance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.03309v1">arXiv:2110.03309v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dorw5hmapjhvpp4jpz4e7ltssy">fatcat:dorw5hmapjhvpp4jpz4e7ltssy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211010025423/https://arxiv.org/pdf/2110.03309v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1d/d7/1dd7b41e41587b871ee51c6f0fb94379730b7e3e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.03309v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Towards Vulnerability Analysis of Voice-Driven Interfaces and Countermeasures for Replay [article]

Khalid Mahmood Malik, Hafiz Malik, Roland Baumann
<span title="2019-04-13">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a novel framework to model replay attack distortion, and then use a non-learning-based method for replay attack detection on smart speakers.  ...  The reply attack distortion is modeled as a higher-order nonlinearity in the replay attack audio.  ...  REPLAY ATTACK DETECTION FRAMEWORK FOR SMART SPEAKERS We propose to use higher-order spectral analysis (HOSA)-based features to capture traces of replay attack distortion and thus detect them.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.06591v1">arXiv:1904.06591v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bddutuc74nfnlnisyvdeuuqgl4">fatcat:bddutuc74nfnlnisyvdeuuqgl4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929223137/https://arxiv.org/ftp/arxiv/papers/1904/1904.06591.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4c/8c/4c8cd13c6f61c1753b82306b80eff4026d8b5d7c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.06591v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learnable Spectro-temporal Receptive Fields for Robust Voice Type Discrimination [article]

Tyler Vuong, Yangyang Xia, Richard Stern
<span title="2020-10-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose a deep-learning-based VTD system that features an initial layer of learnable spectro-temporal receptive fields (STRFs).  ...  that were played back such as traffic noise and television broadcasts ("Distractor Audio").  ...  Related methods for each type of attack is therefore highly specialized. For example, Replay Attack (RA) countermeasures typically rely on detecting distortions in the higher-frequency bands (e.g.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.09151v1">arXiv:2010.09151v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4ma36xx6qbg2pmnkrrfzk6vwj4">fatcat:4ma36xx6qbg2pmnkrrfzk6vwj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201024005849/https://arxiv.org/pdf/2010.09151v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/69/7c/697c737f598f2c1ae42ca655dada4f389fed24cc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.09151v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learnable Spectro-Temporal Receptive Fields for Robust Voice Type Discrimination

Tyler Vuong, Yangyang Xia, Richard M. Stern
<span title="2020-10-25">2020</span> <i title="ISCA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/trpytsxgozamtbp7emuvz2ypra" style="color: black;">Interspeech 2020</a> </i> &nbsp;
In this work, we propose a deep-learning-based VTD system that features an initial layer of learnable spectro-temporal receptive fields (STRFs).  ...  that were played back such as traffic noise and television broadcasts ("Distractor Audio").  ...  Related methods for each type of attack is therefore highly specialized. For example, Replay Attack (RA) countermeasures typically rely on detecting distortions in the higher-frequency bands (e.g.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2020-1878">doi:10.21437/interspeech.2020-1878</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/interspeech/VuongXS20.html">dblp:conf/interspeech/VuongXS20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/udjjmzz7zbbgpixwlqxvdbklie">fatcat:udjjmzz7zbbgpixwlqxvdbklie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201212105046/https://www.isca-speech.org/archive/Interspeech_2020/pdfs/1878.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/80/4a/804a763087950da375c89d47d50c20ed2eee2279.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2020-1878"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

End-To-End Audio Replay Attack Detection Using Deep Convolutional Networks with Attention

Francis Tom, Mohit Jain, Prasenjit Dey
<span title="2018-09-02">2018</span> <i title="ISCA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/trpytsxgozamtbp7emuvz2ypra" style="color: black;">Interspeech 2018</a> </i> &nbsp;
In this paper, we propose an end-to-end deep learning framework for audio replay attack detection.  ...  This highlights the efficacy of our feature representation and attention-based architecture in tackling the challenging task of audio replay attack detection.  ...  of deep convolutional neural networks for audio replay attack detection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2018-2279">doi:10.21437/interspeech.2018-2279</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/interspeech/TomJD18.html">dblp:conf/interspeech/TomJD18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/buaxa2l2a5g7pg3qfmtogdolia">fatcat:buaxa2l2a5g7pg3qfmtogdolia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190309172130/http://pdfs.semanticscholar.org/fcf7/c71e98a833ed1af4da28c24ad63d7df6841f.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fc/f7/fcf7c71e98a833ed1af4da28c24ad63d7df6841f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2018-2279"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Impact of Bandwidth and Channel Variation on Presentation Attack Detection for Speaker Verification

Hector Delgado, Massimiliano Todisco, Nicholas Evans, Md Sahidullah, Wei Ming Liu, Federico Alegre, Tomi Kinnunen, Benoit Fauve
<span title="">2017</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ntxvoxgbebhonjb3rtav25bsee" style="color: black;">2017 International Conference of the Biometrics Special Interest Group (BIOSIG)</a> </i> &nbsp;
This performance gain is achieved by optimising the spectro-temporal decomposition in the feature extraction process to compensate for narrowband speech.  ...  While efforts to develop countermeasures, known as presentation attack detection (PAD) systems, are now under way, the majority of past work has been performed with high-quality speech data.  ...  This would suggest that the detection of voice conversion and speech synthesis attacks requires a spectro-temporal analysis with higher time resolution.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.23919/biosig.2017.8053510">doi:10.23919/biosig.2017.8053510</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/biosig/DelgadoTESLAKF17.html">dblp:conf/biosig/DelgadoTESLAKF17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2zlaq6fxt5cvfpzmf7k6a66hq4">fatcat:2zlaq6fxt5cvfpzmf7k6a66hq4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180720002514/https://erepo.uef.fi/bitstream/handle/123456789/5109/BIOSIG2017_impact.pdf;jsessionid=380CD6112B0EA8450DBFD91B11A2DA49?sequence=2" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/17/2f/172fb111f8cb9cded85a278f0e46beaf550a146b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.23919/biosig.2017.8053510"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Audio Spoofing Verification using Deep Convolutional Neural Networks by Transfer Learning [article]

Rahul T P, P R Aravind, Ranjith C, Usamath Nechiyil, Nandakumar Paramparambath
<span title="2020-08-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Some spoofing attacks like Replay attacks are easier to implement but are very hard to detect thus creating the need for suitable countermeasures.  ...  In this paper, we propose a speech classifier based on deep-convolutional neural network to detect spoofing attacks.  ...  Acknowledgements The authors would like to thank ASVspoof 2019 organizers for providing the dataset and detailed analysis of our system.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.03464v1">arXiv:2008.03464v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/panm4vgdvbatlfsqj266rannze">fatcat:panm4vgdvbatlfsqj266rannze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200812060528/https://arxiv.org/pdf/2008.03464v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.03464v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Modulation Dynamic Features for the Detection of Replay Attacks

Gajan Suthokumar, Vidhyasaharan Sethu, Chamith Wijenayake, Eliathamby Ambikairajah
<span title="2018-09-02">2018</span> <i title="ISCA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/trpytsxgozamtbp7emuvz2ypra" style="color: black;">Interspeech 2018</a> </i> &nbsp;
in replay detection.  ...  The development of automatic systems that can detect replayed speech has emerged as a significant research challenge for securing voice biometric systems and is the focus of this paper.  ...  However, the long-term spectro temporal dynamics is affected by noise and reverberation [17, 18, 19, 20] and has not been fully explored in the context of replay attack detection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2018-1846">doi:10.21437/interspeech.2018-1846</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/interspeech/SuthokumarSWA18.html">dblp:conf/interspeech/SuthokumarSWA18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ljvler4urbf6dijnprelf4b7om">fatcat:ljvler4urbf6dijnprelf4b7om</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190227141022/http://pdfs.semanticscholar.org/90da/0f6fbd8c601aeef37e2ee252323d3e7b86de.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/90/da/90da0f6fbd8c601aeef37e2ee252323d3e7b86de.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2018-1846"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Explainable deepfake and spoofing detection: an attack analysis using SHapley Additive exPlanations [article]

Wanying Ge and Massimiliano Todisco and Nicholas Evans
<span title="2022-05-04">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Despite several years of research in deepfake and spoofing detection for automatic speaker verification, little is known about the artefacts that classifiers use to distinguish between bona fide and spoofed  ...  and consistencies between synthetic speech and converted voice spoofing attacks.  ...  By operating directly upon raw audio waveforms, such systems have greater potential to capture the tell-tale signs of spoofing attacks, e.g. speech synthesis, converted voice and replay, the artefacts  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.13693v2">arXiv:2202.13693v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vyjup4bdlbczhmaumukd7tfh4y">fatcat:vyjup4bdlbczhmaumukd7tfh4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220507073357/https://arxiv.org/pdf/2202.13693v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/27/13/27137adb841cd225fe931cab79c189ef7c32f8ad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.13693v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Constant Q cepstral coefficients: A spoofing countermeasure for automatic speaker verification

Massimiliano Todisco, Héctor Delgado, Nicholas Evans
<span title="">2017</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fut52bg77zaztmwr37xhgokdce" style="color: black;">Computer Speech and Language</a> </i> &nbsp;
The benefit of CQCC features stems from a variable spectro-temporal resolution which, while being fundamentally different to that used by most automatic speaker verification system front-ends, also captures  ...  This finding suggests that the past single-system pursuit of generalised spoofing detection may need rethinking.  ...  1.80 Variable (unknown attack) 3.01 1.92 Table 15 : 15 Spoofing detection performance for the RedDots Replayed database.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.csl.2017.01.001">doi:10.1016/j.csl.2017.01.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bur3wk3fmrgqlahgicmqjoeg4y">fatcat:bur3wk3fmrgqlahgicmqjoeg4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170519180440/http://www.spoofingchallenge.org:80/papers/CSL_CQCC.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4d/be/4dbe43d67677f1371a7ac6f9072c9fd4fe9c9f87.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.csl.2017.01.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

A Light Convolutional GRU-RNN Deep Feature Extractor for ASV Spoofing Detection

Alejandro Gomez-Alanis, Antonio M. Peinado, Jose A. Gonzalez, Angel M. Gomez
<span title="2019-09-15">2019</span> <i title="ISCA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/trpytsxgozamtbp7emuvz2ypra" style="color: black;">Interspeech 2019</a> </i> &nbsp;
voice conversion and replay based attacks.  ...  The aim of this work is to develop a single anti-spoofing system which can be applied to effectively detect all the types of spoofing attacks considered in the ASVspoof 2019 Challenge: text-to-speech,  ...  Conclusions This paper has proposed a novel technique for the extraction of utterance-level identity vectors for an efficient detection of TTS/VC and replay attacks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2019-2212">doi:10.21437/interspeech.2019-2212</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/interspeech/AlanisP0G19.html">dblp:conf/interspeech/AlanisP0G19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d2m6oy6mcjaljgocug6dbojeve">fatcat:d2m6oy6mcjaljgocug6dbojeve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211210081037/https://www.isca-speech.org/archive/pdfs/interspeech_2019/gomezalanis19_interspeech.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/24/22/24225bbbab084fe0c9ee991b5b44e86742713485.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2019-2212"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A non-speech audio CAPTCHA based on acoustic event detection and classification

Hendrik Meutzner, Dorothea Kolossa
<span title="">2016</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wiu3vyiu4fcgnd4znybulgkh6m" style="color: black;">2016 24th European Signal Processing Conference (EUSIPCO)</a> </i> &nbsp;
These audio CAPTCHAs are generally based on distorted speech, rendering the task difficult for untrained or non-native listeners, while still being vulnerable against attacks that make use of automatic  ...  Most websites provide an audio CAPTCHA-in addition to a conventional visual scheme-to facilitate access for a wider range of users.  ...  The advantage of using non-speech sounds is that it enables us to create a vast number of different acoustic scenarios that exhibit highly diverse spectro-temporal characteristics, rendering machinedriven  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/eusipco.2016.7760649">doi:10.1109/eusipco.2016.7760649</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/eusipco/MeutznerK16.html">dblp:conf/eusipco/MeutznerK16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7dilgrhxyfdbhni5zirmumzgja">fatcat:7dilgrhxyfdbhni5zirmumzgja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170921120028/http://www.eurasip.org/Proceedings/Eusipco/Eusipco2016/papers/1570251627.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/11/0a/110a2b5ee1c9c14a8b58cfa09295137c2503fed0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/eusipco.2016.7760649"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

2020 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 28

<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rut5unc4enborm7fhpkwgeza7m" style="color: black;">IEEE/ACM Transactions on Audio Speech and Language Processing</a> </i> &nbsp;
Mathad, V.C., +, TASLP 2020 450-460 Channel bank filters Audio Replay Spoof Attack Detection by Joint Segment-Based Linear Filter Bank Feature Extraction and Attention-Enhanced DenseNet-BiLSTM Net-  ...  Bai, Z., +, TASLP 2020 1533-1548 Spectro-Temporal Sparsity Characterization for Dysarthric Speech Detection.  ...  T Target tracking Multi-Hypothesis Square-Root Cubature Kalman Particle Filter for Speaker Tracking in Noisy and Reverberant Environments. Zhang, Q., +, TASLP 2020 1183 -1197  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2021.3055391">doi:10.1109/taslp.2021.3055391</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7vmstynfqvaprgz6qy3ekinkt4">fatcat:7vmstynfqvaprgz6qy3ekinkt4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210218100609/https://ieeexplore.ieee.org/ielx7/6570655/8938144/09352987.pdf?tp=&amp;arnumber=9352987&amp;isnumber=8938144&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/48/5a/485a74dc9066974fdf8cc3ec000abfaa0f4ffd37.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/taslp.2021.3055391"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Review of Modern Audio Deepfake Detection Methods: Challenges and Future Directions

Zaynab Almutairi, Hebah Elgibreen
<span title="2022-05-04">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/63zsvf7vxzfznojpqgfvpyk2lu" style="color: black;">Algorithms</a> </i> &nbsp;
The article introduces types of AD attacks and then outlines and analyzes the detection methods and datasets for imitation- and synthetic-based Deepfakes.  ...  This article can be a starting point for researchers to understand the current state of the AD literature and investigate more robust detection models that can detect fakeness even if the target audio  ...  This review will thus cover the detection methods used to identify synthetic and imitation Deepfakes, and replay-based attacks will be considered out of scope.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/a15050155">doi:10.3390/a15050155</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g4bw7lnu7nhdbizg2c62ppwf74">fatcat:g4bw7lnu7nhdbizg2c62ppwf74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220506205614/https://mdpi-res.com/d_attachment/algorithms/algorithms-15-00155/article_deploy/algorithms-15-00155.pdf?version=1651653068" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f0/f1/f0f158682061bb8066b5b262c48d1b8b0e6f8af0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/a15050155"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 41 results