Channel pattern noise based playback attack detection algorithm for speaker recognition
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
This paper proposes a channel pattern noise based approach to guard speaker recognition system against playback attacks. For each recording under investigation, the channel pattern noise severs as a unique channel identification fingerprint. Denoising filter and statistical frames are applied to extract channel pattern noise, and 6 Legendre coefficients and 6 statistical features are extracted. SVM is used to train channel noise model to judge whether the input speech is an authentic or a playback recording. The experimental results indicate that, with the designed playback detector, the equal error rate of speaker recognition system is reduced by 30%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Hermansky, H., & Morgan, N. (1994) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.326616 · Cited by 1,808 · cited 1×
“The low frequency component is mainly the effect of convolution noise intro duced by channel noise [9].”
BackgroundTheory and Applications of Digital Speech Processing
Rabiner, L. R., & Schafer, R. W. (2010) · Medical Entomology and Zoology · Cited by 579
Kersta, L. G. (1962) · Nature · doi:10.1038/1961253a0 · Cited by 204 · cited 3×
“T he concept of voiceprint was firstly presented by Kersta for speaker recognition in 1962 in Nature [1].”
BackgroundInfluentialPohlmann, K. C. (1985) · Cited by 148
Vulnerability of speaker verification to voice mimicking
Lau, Y. W., Wagner, M., & Tran, D. (2005) · Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004. · doi:10.1109/isimp.2004.1434021 · Cited by 128 · cited 2×
“Two common security problems for speaker recognition systems are voice mimicking [3] and playback attack [4].”
BackgroundMornington-West, A. (1998) · Elsevier eBooks · doi:10.1016/b978-0-08-054564-6.50008-2 · Cited by 68
Score normalization in playback attack detection
Shang, W., & Stevenson, M. (2010) · 2010 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2010.5495503 · Cited by 58
Language Identification Using Pitch Contour Information
Lin, C.-Y., & Wang, H.-C. (2006) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2005.1415185 · Cited by 57 · cited 1×
“Legendre polynomials are a set of orthogonal basis, and this technique of approximation by Legendre polynomials has been successfully applied in language identification and other engineering applications [10].”
MethodSubband or cepstral domain filtering for recognition of Lombard and channel-distorted speech
Hanson, B. A., & Applebaum, T. H. (1993) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1993.319235 · Cited by 30 · cited 1×
“Channel noise is all along with speech signals and varies slowly [7].”
BackgroundPrevention of impostors entering speaker recognition systems
Zheng, F. (2008) · Journal of Tsinghua University(Science and Technology) · Cited by 6
Research works printed but not linked: 1
- lipeng, 2008, Pre-vention of impostors entering speaker recognition sys-tems, Journal of Tsinghua University, 48, 699
Cited by
Spoofing and countermeasures for speaker verification: A survey
Wu, Z., Evans, N., Kinnunen, T., Yamagishi, J., Alegre, F., & Li, H. (2015) · Speech Communication · doi:10.1016/j.specom.2014.10.005 · Cited by 601
“…adoption of ASV techniques (Lee et al., 2013; Nuance, 2013) and the awareness and simplicity of replay attacks, both industry (Nuance, 2013) and academia (Shang and Stevenson, 2010; Villalba and Lleida, 2011a,b; Wang et al., 2011) have shown an interest in developing replay attack countermeasures.”
BackgroundMethodInfluentialZhang, L., Tan, S., & Yang, J. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133962 · Cited by 191
“Numerous work has pointed out existing verification systems can not efficiently defend against replay attacks [18, 20, 46].”
BackgroundVoiceLive: A Phoneme Localization based Liveness Detection for Voice Authentication on Smartphones
Zhang, L., Tan, S., Yang, J., & Chen, Y. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978296 · Cited by 174
“As an alternative, Villalba et al. utilize the increased noise and reverberation of replaying far-field recordings for attack detection [32], whereas Wang et al. use the additional channel noise of the recording and loudspeaker for attack detection [33].”
BackgroundMethodInfluentialA study on replay attack and anti-spoofing for text-dependent speaker verification
Wu, Z., Gao, S., Cling, E. S., & Li, H. (2014) · Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific · doi:10.1109/apsipa.2014.7041636 · Cited by 147
“In [20], an anti-spoofing approach based on examining the channel noised”
BackgroundMethodResultAudio Replay Attack Detection Using High-Frequency Features
Witkowski, M., Kacprzak, S., Żelasko, P., Kowalczyk, K., & Gałka, J. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-776 · Cited by 140
“Detection of far-field recording and loudspeaker playback has been reported in [11] and the algorithm that identifies an acoustic channel artefacts has been presented in [12].”
BackgroundYou Can Hear But You Cannot Steal: Defending Against Voice Impersonation Attacks on Smartphones
Chen, S., Ren, K., Piao, S., Wang, C., Wang, Q., Weng, J., Su, L., & Mohaisen, A. (2017) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2017.133 · Cited by 130
“Although a few system research papers on developing replay attack countermeasures have been published [30], [38], [46], [47], [50], all these systems suffer from high false acceptance rate (FAR) compared to the respective baselines.”
Font, R., Espín, J. M., & Cano, M. J. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-450 · Cited by 109
“Previous work [4, 5, 6] used small sized in-house databases collected with a small set of recording and playback devices, which makes it difficult to compare their results with those of other studies.”
ResultDeepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113
“An example of an artifact-based approach is presented in [111], where channel pattern noise analysis is used to secure Automatic Speaker Verification (ASV) systems against physical attacks.”
VoicePop: A Pop Noise based Anti-spoofing System for Voice Authentication on Smartphones
Wang, Q., Lin, X., Zhou, M., Chen, Y., Wang, C., Li, Q. L., & Luo, X. (2019) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2019.8737422 · Cited by 120
“However, since the sound transmits through an open and public channel, the voice authentication system is highly vulnerable to spoofing attacks [3]–[5].”
BackgroundMethodA Robust Approach to Multimodal Deepfake Detection
Salvi, D., Liu, H., Mandelli, S., Bestagini, P., Zhou, W., Zhang, W., & Tubaro, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9060122 · Cited by 96
“An example of an artifacts-based approach is presented in [25], where channel pattern noise analysis is used to secure Automatic Speaker Verification (ASV) systems against physical attacks.”
Spoof Detection Using Source, Instantaneous Frequency and Cepstral Features
Jelil, S., Das, R. K., Prasanna, S. R. M., & Sinha, R. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-930 · Cited by 79
“In [7], channel noise pattern is determined from denoising filter and statistical frames that are trained by support vector machine based classifier to identify whether the input speech is authentic or replayed.”
BackgroundIntroduction to Voice Presentation Attack Detection and Recent Advances
Sahidullah, M., Delgado, H., Todisco, M., Kinnunen, T., Evans, N., Yamagishi, J., & Lee, K. A. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-92627-8_15 · Cited by 84
Deep features for automatic spoofing detection
Qian, Y., Chen, N., & Yu, K. (2016) · Speech Communication · doi:10.1016/j.specom.2016.10.007 · Cited by 78
“For instance, similarities within stored access attempts (Shang and Stevenson, 2010), spectral ratio and modulation indexes (Villalba and Lleida, 2011b,a), channel noise (Wang et al., 2011) has been demonstrated to be efficient at detecting replay attacks.”
BackgroundRobust deep feature for spoofing detection — the SJTU system for ASVspoof 2015 challenge
Chen, N., Qian, Y., Dinkel, H., Chen, B., & Yu, K. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-474 · Cited by 69
“Replay uses the recorded speech to spoof the system, and better features [7, 8], channel noise detection [9] are suggested to be effective.”
MethodPlayback attack detection for text-dependent speaker verification over telephone channels
Gałka, J., Grzywacz, M., & Samborski, R. (2014) · Speech Communication · doi:10.1016/j.specom.2014.12.003 · Cited by 67
Yan, C., Long, Y., Ji, X., & Xu, W. (2019) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3319535.3354248 · Cited by 83
“…between human and Acoustic artifacts of spoofing attacks can exist on the physical, hardware, and software levels, including the channel noise [64], far-field recordings [61], frequency response of loudspeakers [13], similarity to stored recordings [53], audio editing [62], etc. Subtle attack…”
BackgroundTIMIT-TTS: A Text-to-Speech Dataset for Multimodal Synthetic Media Detection
Salvi, D., Hosler, B., Bestagini, P., Stamm, M. C., & Tubaro, S. (2023) · IEEE Access · doi:10.1109/access.2023.3276480 · Cited by 65
“As an example of artifacts-based approaches, [35] aims to secure Automatic Speaker Verification (ASV) systems against physical attacks through channel pattern noise analysis.”
A Survey on Voice Assistant Security: Attacks and Countermeasures
Yan, C., Ji, X., Wang, K., Jiang, Q., Jin, Z., & Xu, W. (2022) · ACM Computing Surveys · doi:10.1145/3527153 · Cited by 92
“distortion G# G# ? ? ? # SW é é Any Ë [5, 17, 51, 123, 176, 181] Magnetic ield G# G# # # SW é Ë Medium é [25]”
BackgroundAdversarial Attack and Defense Strategies of Speaker Recognition Systems: A Survey
Tan, H., Wang, L., Zhang, H., Zhang, J., Shafiq, M., & Gu, Z. (2022) · Electronics · doi:10.3390/electronics11142183 · Cited by 74
Speaker Recognition Anti-spoofing
Evans, N., Kinnunen, T., Yamagishi, J., Wu, Z., Alegre, F., & Leon, P. L. D. (2014) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-6524-8_7 · Cited by 51
“Two different replay attack countermeasures are compared i n [92].”
BackgroundLiu, Y., Tian, Y., He, L. J., Liu, J., & Johnson, M. T. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-471 · Cited by 49
Deep Feature Engineering for Noise Robust Spoofing Detection
Qian, Y., Chen, N., Dinkel, H., & Wu, Z. (2017) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2017.2732162 · Cited by 46
“For instance, spectral ratio and modulation indexes [7], [8] and channel noise features [9] were have been demonstrated to be effective to detect replay attacks.”
BackgroundVoice In Ear: Spoofing-Resistant and Passphrase-Independent Body Sound Authentication
Gao, Y., Jin, Y., Chauhan, J., Choi, S., Li, J., & Jin, Z. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3448113 · Cited by 68
“It was reported that [56], playback attacks could achieve a 40% attack rate to the voiceprint-based speaker verification, which indicates the voiceprint authentication has poor resiliency to replay attacks.”
BackgroundAn assessment of automatic speaker verification vulnerabilities to replay spoofing attacks
Janicki, A., Alegre, F., & Evans, N. (2016) · Security and Communication Networks · doi:10.1002/sec.1499 · Cited by 42
“Two such algorithms are reported in [41] for which the EER for a baseline GMM system with a universal background model (UBM) was shown to decrease from 40% to 10% with active countermeasures.”
MethodWang, S., Cao, J., He, X., Sun, K., & Li, Q. (2020) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3372297.3417254 · Cited by 46
“Second, the attacker can launch a simple replay attack by playing back a pre-recorded speech of the victim to the ASR systems [60, 62].”
BackgroundLow frequency frame-wise normalization over constant-Q transform for playback speech detection
Yang, J., & Das, R. K. (2019) · Digital Signal Processing · doi:10.1016/j.dsp.2019.02.018 · Cited by 39
Lü, L., Yu, J., Chen, Y. J., & Wang, Y. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3397320 · Cited by 49
“Existing studies [42, 49, 51] validated that replay attacks to the voiceprint-based user authentication can achieve over 50% successful attack rate, which reveals the severe vulnerability of voiceprint-based user authentication.”
BackgroundProtecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues
Gong, Y., & Poellabauer, C. (2018) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn.2018.8487334 · Cited by 36
“In [26], the authors use channel noise patterns to distinguish between a pre-recorded voice and the voice of a live speaker.”
BackgroundCountermeasures to Replay Attacks: A Review
Singh, M., & Pati, D. (2019) · IETE Technical Review · doi:10.1080/02564602.2019.1684851 · Cited by 36
Defending Against Voice Spoofing: A Robust Software-Based Liveness Detection System
Shang, J., Chen, S., & Wu, J. (2018) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass.2018.00016 · Cited by 36
Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection
Attorresi, L., Salvi, D., Borrelli, C., Bestagini, P., & Tubaro, S. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-37742-6_21 · Cited by 30
Spoofing countermeasure based on analysis of linear prediction error
Janicki, A. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-470 · Cited by 33
“Such algorithms were reported in [13], for which the EER for a baseline GMM-UBM system was shown to decrease from 40% to 10% with active countermeasures.”
MethodBreathLive: Liveness Detection for Heart Sound Authentication with Deep Breathing
Huang, C., Chen, H., Yang, L., & Zhang, Q. (2018) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3191744 · Cited by 31
“To defend against such attacks, many methods utilizing the sound features of the voice itself have been proposed[48, 49, 52].”
BackgroundMethodInstantaneous Phase and Excitation Source Features for Detection of Replay Attacks
Das, R. K., & Li, H. (2018) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipa.2018.8659789 · Cited by 30
“Similarly, channel noise has been used a characteristics for discriminating replay attacks as mentioned in [22].”
MethodVibLive: A Continuous Liveness Detection for Secure Voice User Interface in IoT Environment
Zhang, L., Tan, S., Wang, Z., Ren, Y., Wang, Z., & Yang, J. (2020) · Annual Computer Security Applications Conference · doi:10.1145/3427228.3427281 · Cited by 43
“Conventional voice authentication has been proved to be vulnerable to spoofing attacks including replay attacks, synthesize attacks, conversion attacks, and impersonation attacks [5, 30, 35, 38, 42, 49, 58].”
BackgroundSelf-citationSecuring Liveness Detection for Voice Authentication via Pop Noises
Jiang, P., Wang, Q., Lin, X., Zhou, M., Ding, W., Wang, C., Shen, C. Q., & Li, Q. L. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3163024 · Cited by 28
“However, since the sound transmits through an open and public channel, the voice authentication system is highly vulnerable to spoofing attacks [19], [20], [21].”
BackgroundMethodReplay attack detection with auditory filter-based relative phase features
Oo, Z., Wang, L., Phapatanaburi, K., Liu, M., Nakagawa, S., Iwahashi, M., & Dang, J. (2019) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-019-0151-2 · Cited by 32
Usefulness of linear prediction residual for replay attack detection
Singh, M., & Pati, D. (2019) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2019.152837 · Cited by 23
Novel Empirical Mode Decomposition Cepstral Features for Replay Spoof Detection
Tapkir, P. A., & Patil, H. A. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-1661 · Cited by 21
“The channel noise from recording device was used to detect the replay speech [8].”
MethodReplay attack detection based on distortion by loudspeaker for voice authentication
Ren, Y., Fang, Z., Liu, D., & Chen, C. W. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6834-3 · Cited by 23
“All the studies [7, 14, 17] are found to be consistent in their findings: regardless the ASV system tested, replay attacks provoke significant increases in FAR (False Alarm Rate) [20].”
Speech Based Human Authentication on Smartphones
Dai, H., Wang, W., Liu, A. X., Ling, K., & Sun, J. (2019) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/sahcn.2019.8824958 · Cited by 22
“For replay attacks, some countermeasures use physical characteristics of the recording and replay devices, and some use the increased background noise [17, 18] or channel noise [19] resulted from replaying recordings and the loud-speaker, and some countermeasures use additional means such as video [20] to enhance the…”
BackgroundMuckenhirn, H., Magimai.-Doss, M., & Marcel, S. (2016) · International Conference of the Biometrics Special Interest Group (BIOSIG) · doi:10.1109/biosig.2016.7736933 · Cited by 19
“mainly focuses on characteristics related to channel noise and reverberation [6], [7].”
BackgroundExploring the Synthetic Speech Attribution Problem Through Data-Driven Detectors
Salvi, D., Bestagini, P., & Tubaro, S. (2022) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs55849.2022.9975440 · Cited by 26
“Some aim to determine the authenticity of a multimedia signal by exploiting traces left by the generators [9]– [11].”
BackgroundInvestigating the use of scattering coefficients for replay attack detection
Sriskandaraja, K., Suthokumar, G., Sethu, V., & Ambikairajah, E. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282211 · Cited by 20
“The second approach involves distinguishing between the transmission channels of genuine and replayed speech, such as the detection of pop-noise [12], of far-field recordings based on reverberation levels [13], channel differences [14] or local binary patterns [10].”
BackgroundVoicePM: A Robust Privacy Measurement on Voice Anonymity
Zhang, S., Li, Z., & Das, A. (2023) · ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec) · doi:10.1145/3558482.3590175 · Cited by 24
“Studies have shown that voice-based authentication systems are vulnerable to impersonation [23, 24] and replay attacks [34, 69].”
BackgroundIntroduction to Voice Presentation Attack Detection and Recent Advances
Sahidullah, M., Delgado, H., Todisco, M., Nautsch, A., Wang, X., Kinnunen, T., Evans, N., Yamagishi, J., & Lee, K. A. (2023) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-19-5288-3_13 · Cited by 22
Combining evidences from Hilbert envelope and residual phase for detecting replay attacks
Singh, M., & Pati, D. (2019) · International Journal of Speech Technology · doi:10.1007/s10772-019-09604-x · Cited by 14
“In Wang et al. (2011), the differences between the channel pattern noise computed from original and replay recordings was used for detecting replay signals.”
MethodProcessing linear prediction residual signal to counter replay attacks
Mishra, J., Singh, M., & Pati, D. (2018) · International Conference on Signal Processing and Communications (SPCOM) · doi:10.1109/spcom.2018.8724390 · Cited by 15
“As such, the state-of-the-art short-term spectral features based SV systems are vulnerable to replay attacks [6].”
BackgroundHandLock: Enabling 2-FA for Smart Home Voice Assistants using Inaudible Acoustic Signal
Zhang, S., & Das, A. (2021) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1145/3471621.3471866 · Cited by 13
Audio recapture detection using deep learning
Luo, D., Wu, H., & Huang, J. (2015) · IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP) · doi:10.1109/chinasip.2015.7230448 · Cited by 14
“Index Terms— Audio recapture detection, Deep learning, Dropout, SAE”
BackgroundReplay attack: Its effect on GMM-UBM based text-independent speaker verification system
Singh, M., Mishra, J., & Pati, D. (2016) · IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) · doi:10.1109/upcon.2016.7894726 · Cited by 13
“It is mainly due to the strong attenuation of loud speaker (smart phone) frequency response at low frequency regions [7], [9].”
BackgroundDeep learning countermeasures for detecting replay speech attacks: a review
Veesa, S., & Singh, M. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10163-z · Cited by 16
SRVoice: A Robust Sparse Representation-Based Liveness Detection System
Shang, J., Chen, S., & Wu, J. (2018) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/padsw.2018.8644547 · Cited by 11
“To fight against simple but effective voice replay attacks, a few research papers have been published [16, 17].”
Discriminative features based on modified log magnitude spectrum for playback speech detection
Yang, J., Xu, L., Ren, B., & Ji, Y. (2020) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-020-00173-5 · Cited by 12
Detection of speech playback attacks using robust harmonic trajectories
Shang, W., & Stevenson, M. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101133 · Cited by 9
Liu, L., & Yang, J. (2020) · IEEE Access · doi:10.1109/access.2020.3013066 · Cited by 10
“In [9], [21] six long-term statistical parameters were introduced, which were obtained from DFT frequency bin and they are the minimal value, maximal value, average value, median, difference between the maximal and minimal values and standard deviation, respectively.”
BackgroundSpoofing and countermeasures for speaker verification: A review
Anjum, Z. K., & Swamy, R. K. (2017) · 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) · doi:10.1109/wispnet.2017.8299800 · Cited by 9
“17% when subjected to replay attacks [9].”
BackgroundCombating Voice Spoofing Attacks on Wearables via Speech Movement Sequences
Chang, S., Luo, Z., Liu, W., Zhu, H., Hu, X., & Yang, L. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3418908 · Cited by 8
Replay attack detection using excitation source and system features
Singh, M., & Pati, D. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-816801-1.00002-5 · Cited by 8
Increasing anti-spoofing protection in speaker verification using linear prediction
Janicki, A. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3508-x · Cited by 10
“Such algorithms were reported in [37], for which the EER of a baseline GMM-UBM system was shown to decrease from 40 % to 10 % with active countermeasures.”
MethodFusion of RMFCC and RCQCC Features for Replay Attack Detection Task
Veesa, S., Badugu, V. K., & Singh, M. (2023) · IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS) · doi:10.1109/iotais60147.2023.10346062 · Cited by 7
“Studies on replay attacks and countermeasures was started since beginning of the 21st century [4], [11], [5], [12], [13], [14], [15].”
BackgroundA Robust Method for Speech Replay Attack Detection
Lin, L., Wang, R., Yan, D., & Dong, L. (2020) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2020.01.010 · Cited by 7
Detection of Replay Attack Based on Normalized Constant Q Cepstral Feature
Ye, Y., Lao, L., Yan, D., & Lin, L. (2019) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda.2019.8725688 · Cited by 7
Detection of replay signals using excitation source and shifted CQCC features
Dutta, K., Singh, M., & Pati, D. (2021) · International Journal of Speech Technology · doi:10.1007/s10772-021-09810-6 · Cited by 8
“Due to the dia-phragms inertia, the loudspeaker creates typically significant attenuation in low frequency regions (Villaba and Lieida 2011; Wang et al. 2011).”
BackgroundSafavi, S., Gan, H., & Mporas, I. (2017) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa.2017.8064954 · Cited by 6
“In audio replay attacks, countermeasures based on uncharacteristic similarity between recorded inputs [16] and dissimilarity due to the specific environmental characteristics of replay attacks [17] have been proposed.”
BackgroundmmSafe: A Voice Security Verification System Based on Millimeter-Wave Radar
Hao, Z., Peng, J., Dang, X., Yan, H., & Wang, R. (2022) · Sensors · doi:10.3390/s22239309 · Cited by 7
“[10] have carried out a significant amount of work on acoustic feature extraction, and their study found that mute segment cancellation reduces detection accuracy when preprocessing audio for playback attack detection; Cepstral Mean Normalization (CMN) of acoustic features [11] helps improve system performance.”
BackgroundAn Efficient Learning Based Smartphone Playback Attack Detection Using GMM Supervector
Wang, C., Zou, Y., Liu, S., Shi, W., & Zheng, W. (2016) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2016.14 · Cited by 6
“According to the research results in [10], SOM algorithm and grid searching algorithm are used to find the best error penalty parameter C (C > 0) and and then the best parameters can be used to train the optimal channel model.”
BackgroundMethodA Phoneme Localization Based Liveness Detection for Text-Independent Speaker Verification
Zhang, L., Tan, S., Chen, Y. J., & Yang, J. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3187432 · Cited by 5
“suggest that the additional channel noises introduced by the recording and loudspeaker can be used for attack detection [32], [34].”
BackgroundMethodInfluentialListening to Sounds of Silence for Audio replay attack detection
Hajipour, M., Akhaee, M. A., & Toosi, R. (2021) · International Conference on Signal Processing and Intelligent Systems (ICSPIS) · doi:10.1109/icspis54653.2021.9729353 · Cited by 6
“…their production process, considering that in the process of producing spoof samples, there is a recorder and an audio player, so the noise created by these two devices in the recorded utterance is affected and this noise can be used as a criterion for distinguishing spoofed and real samples [14].”
BackgroundBiologically Inspired Adaptive-Q Filterbanks for Replay Spoofing Attack Detection
Wickramasinghe, B., Eliathamby Ambikairajah, A., & Epps, J. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1535 · Cited by 5
“Other countermeasures include discriminating replayed speech from genuine speech using the channel characteristics of replayed speech and added reverberation [6, 7].”
BackgroundPlayback Attack Detection: The Search for the Ultimate Set of Antispoof Features
Smiatacz, M. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-59162-9_13 · Cited by 4
Xu, X., Fu, C., Du, X., & Ratazzi, E. P. (2023) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn58367.2023.00060 · Cited by 6
“…Speech Recognition (ASR) systems used by smart voice assistants to differentiate playback from the live human voice [17], [39], [66], [74], [79], they are vulnerable to adversarial example attacks that generate synthetic audio mimicking the owner and successfully fool the voice assistants…”
BackgroundContreras, R. C., Viana, M. S., & Guido, R. C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42508-0_27 · Cited by 3
BIM-Based Adversarial Attacks Against Speech Deepfake Detectors
Wang, W. E., Salvi, D., Negroni, V., Leonzio, D. U., Bestagini, P., & Tubaro, S. (2025) · Electronics · doi:10.3390/electronics14152967 · Cited by 9
Development of playback attacks detection system
Singh, M., Mishra, J., & Pati, D. (2017) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2017.8228080 · Cited by 3
“In [8], channel pattern noise was used as an alternative to”
BackgroundMethodUsefulness of linear prediction residual signal for development of replay attacks detection system
Singh, M., Mishra, J., & Pati, D. (2017) · National Conference on Communications · doi:10.1109/ncc.2017.8077117 · Cited by 3
“It is mainly due to the strong attenuation of loud speaker (smart phone) frequency response at low frequency regions [4], [12].”
BackgroundTowards Development of Smart and Reliable Voice Based Personal Assistants
Mankad, S. H., Shah, V., & Garg, S. (2018) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2018.8650091 · Cited by 3
“Illustration of playback attack on voice based authentication system (adapted from [19]) Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference (Jeju, Korea, 28-31 October 2018)”
MethodSecurity, Privacy, and Usability Challenges in Selfie Biometrics
Gofman, M. I., Mitra, S., Bai, Y., & Choi, Y. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-26972-2_16 · Cited by 5
An Investigation about the Scalability of the Spoofing Detection System
Suthokumar, G., Sriskandaraja, K., Sethu, V., Wijenayake, C. A., & Ambikairajah, E. (2018) · International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2018.8913369 · Cited by 6
“In literature, proposed approaches involve distinguishing between the transmission channels of genuine and replayed speech such as the detection of pop-noise [4], acoustic channel artefacts [5]; detection of far-field recording [6].”
BackgroundPiezoBud: A Piezo-Aided Secure Earbud with Practical Speaker Authentication
Li, G., Zeng, H., Guo, H., Ren, Y., Dixon, A., Cao, Z., & Li, T. (2024) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3666025.3699358 · Cited by 2
“However, existing audio-based user authentication solutions [13, 14] fail to defend against prevalent threats such as re-play attacks [15], side-channel attacks [14], and mimic attacks [16].”
Exploring linear prediction residual signal for developing countermeasures to playback attacks
Mishra, J., Singh, M., & Pati, D. (2018) · IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS) · doi:10.1109/sceecs.2018.8546964 · Cited by 2
“As mentioned earlier, it is mainly due to the influence of the playback device characteristics [6].”
BackgroundInfluentialSpeaker Orientation-Aware Privacy Control to Thwart Misactivation of Voice Assistants
Zhang, S., Sabir, A., & Das, A. (2023) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn58367.2023.00061 · Cited by 6
“For example, VAs can misactivate either accidentally due to suboptimal wake-word recognition engine [26], [57] or maliciously through replay attacks [39], [70].”
BackgroundContreras, R. C., Heck, G. L., Viana, M. S., Bongarti, M. A. D. S., Zamani, H., & Guido, R. C. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7181-3_20 · Cited by 3
Replay spoofing countermeasures using high spectro-temporal resolution features
Alluri, K. N. R. K. R., & Vuppala, A. K. (2019) · International Journal of Speech Technology · doi:10.1007/s10772-019-09602-z · Cited by 2
“Initial studies of replay attacks on ASV technology are reported in (Villalba and Lleida 2011a; Wang et al. 2011; Villalba and Lleida 2011b; Shang and Stevenson 2010) these works are carried out on their own onsite data-sets.”
BackgroundAn Approach to Detect Replay Attack in Automatic Speaker Verification System
Saranya, S., Bharathi, B., & Kavitha, S. N. (2018) · International Conference on Computer, Communication and Signal Processing (ICCCSP) · doi:10.1109/icccsp.2018.8452827 · Cited by 2
“According to the paper [2], an approach to speaker guard recognition system based on channel pattern noise is proposed.”
BackgroundReplay Spoofing Countermeasure Using Autoencoder and Siamese Network on ASVspoof 2019 ChallengePreprint
Adiban, M., Sameti, H., & Shehnepoor, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.13345 · Cited by 2
“[24] claims that licit recordings have just a specific type of channel noise which is mixed with additional noise of environment when a replay attack is presented in far-field.”
BackgroundWang, Z., Zheng, X., & Zeng, C. (2025) · arXiv · doi:10.48550/arxiv.2510.22559 · Cited by 2
Self-citationRecording Source Identification Using Device Universal Background Model
Wang, Z., Liu, Q., Chen, J., & Yao, H. (2015) · International Conference of Educational Innovation through Technology (EITT) · doi:10.1109/eitt.2015.11 · Cited by 1
“amplifier, power amplifier, input filter, A/D, sample and hold circuit will cause channel noise [12]).”
BackgroundSelf-citationPlayback detection using machine learning with spectrogram features approach
Dembski, J., & Rumiński, J. (2017) · Conference on Human System Interactions · doi:10.1109/hsi.2017.8004991 · Cited by 1
“It was confirmed by results reported in [4], [5], [6] although with different interpretations.”
ResultAudio Replay Spoof Attack Detection Using A GMM-RFPNN Model as Back-end Classifier
Qi, K., Huang, W., Wang, D., & Zhang, H. (2021) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice54393.2021.00089 · Cited by 2
Compensating Removed Frequency Components: Thwarting Voice Spectrum Reduction Attacks
Wang, S., Sun, K., & Li, Q. (2024) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2024.23150 · Cited by 3
“Attackers can launch impersonation attacks by physically changing their voices [46] or launch replay attacks with pre-recorded audio [45], [72], [35].”
BackgroundA Simple Neural Network Based Countermeasure for Replay Attack
Pang, W., & He, Q. (2017) · International Conference on Communication and Information Systems (ICCIS) · doi:10.1145/3158233.3159308 · Cited by 1
“Wang Zhi-feng et al [4] proposed a method based on channel pattern noise, in which different devices were regarded to possess different noise pattern.”
BackgroundMethodInfluentialSelf-citationRobust speaker verification system with anti-spoofing detection and DNN feature enhancement modules
Du, S. (2015) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/65396 · Cited by 1
“Similar results were also obtained in recent text-independent JFA [156, 170] and GMM-UBM based SV systems [171].”
ResultThe Dual Role of Smartphones in IoT Security
Ren, K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-75160-3_3
Bezpieczeństwo systemów biometrii głosowej
Janicki, A. (2017) · Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne · doi:10.15199/59.2017.8-5.3
Security and Privacy Issues of Mobile Cyber-physical Systems
Shang, J. (2020) · TUScholarShare (Temple University) · Cited by 1
A Continuous Liveness Detection System for Text-independent Speaker VerificationPreprint
Zhang, L., & Yang, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.01840
“use the additional channel noise of the recording and loudspeaker for attack detection [39].”
BackgroundMethodInfluentialSun, K., & Wang, S. (2023) · SpringerBriefs in computer science · doi:10.1007/978-3-031-44748-8_1
Secure Voice Processing Systems for Driverless Vehicles
Sun, K., & Wang, S. (2023) · SpringerBriefs in computer science · doi:10.1007/978-3-031-44748-8_3 · Cited by 1
Sorokin, V. N. (2023) · Акустический журнал · doi:10.31857/s0320791923600282
Metadata
- Authors
- Wang, Z.-F., Wei, G., & He, Q.-H.
- Affiliations
- South China University of Technology (CN)
- ORCID
- Wei, Gang
- Venue
- 2011 International Conference on Machine Learning and Cybernetics
- Publisher
- IEEE
- Published
- 2011-07
- Pages
- 1708-1713
- OpenAlex
- W2114376863
- Cited by
- 101
- References
- 11
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 5 · 2023: 12 · 2022: 6 · 2021: 6 · 2020: 9 · 2019: 14 · 2018: 13 · 2017: 15 · 2016: 7 · 2015: 6 · 2014: 4
- FWCI
- 1.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Machine Learning and Cybernetics (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- speaker recognition, replay attacks, Legendre coefficients, statistical features, support vector machine, anti-spoofing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.