Long Range Acoustic Features for Spoofed Speech Detection
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Speaker verification systems in practice are vulnerable to spoofing attacks. The high quality recording and playback devices make replay attack a real threat to speaker verification. Additionally, the furtherance in voice conversion and speech synthesis has produced perceptually natural sounding speech. The ASVspoof 2019 challenge is organized to study the robustness of countermeasures against such attacks, which cover two common modes of attacks, logical and physical access. The former deals with synthetic attacks arising from voice conversion and text-to-speech techniques, whereas the latter deals with replay attacks. In this work, we explore several novel countermeasures based on long range acoustic features that are found to be effective for spoofing attack detection. The long range features capture different aspects of long range information as they are computed from subbands and octave power spectrum in contrast to the conventional way from linear power spectrum. These novel features are combined with the other known features for improved detection of spoofing attacks. We obtain a tandem detection cost function of 0.1264 and 0.1381 (equal error rate 4.13% and 5.95%) for logical and physical access on the best combined system submitted to the challenge.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“a significant body of research [64,96,97,98,99] has demonstrated that the performance of detection models largely depends on the choice of input features.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [97]
Citations
Cites
The ASVspoof 2017 challenge: assessing the limits of replay spoofing attack detection
Kinnunen, T., Sahidullah, M., Delgado, H., Todisco, M., Evans, N., Yamagishi, J., & Lee, K. A. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1111 · Cited by 535 · cited 1×
“The previous edition of challenges focused on synthetic and replay attacks in the year 2015 and 2017, respectively [9, 10].”
BackgroundCNTK: Microsoft's Open-Source Deep-Learning Toolkit
Seide, F., & Agarwal, A. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2945397 · Cited by 382 · cited 1×
“We used the Microsoft Cognitive Toolkit for DNN training [36].”
MethodEvaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech
De Leon, P. L., Pucher, M., Yamagishi, J., Hernaez, I., & Saratxaga, I. (2012) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2012.2201472 · Cited by 231
Kinnunen, T., Lee, K. A., Delgado, H., Evans, N., Todisco, M., Sahidullah, M., Yamagishi, J., & Reynolds, D. A. (2018) · The Speaker and Language Recognition Workshop (Odyssey 2018) · doi:10.21437/odyssey.2018-44 · Cited by 198
Patel, T. B., & Patil, H. A. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-467 · Cited by 164 · cited 1×
“The importance of long range features is also supported by effectiveness of cochlear filter cepstral coefficients and instantaneous frequency feature that produced the best performance in the first edition of anti-spoofing challenge on synthetic speech attacks [21].”
BackgroundThe BOSARIS Toolkit: Theory, Algorithms and Code for Surviving the New DCF
Brümmer, N., & de Villiers, E. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.2865 · Cited by 141 · cited 1×
“We have used Bosaris(3) toolkit for fusion and calibration of multiple systems [37].”
MethodAudio 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
Patil, H. A., Kamble, M. R., Patel, T. B., & Soni, M. H. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-1362 · Cited by 77
Development of Multi-Level Speech based Person Authentication System
Das, R. K., Jelil, S., & Prasanna, S. R. M. (2016) · Journal of Signal Processing Systems · doi:10.1007/s11265-016-1148-z · Cited by 51
Self-citationLong-term high frequency features for synthetic speech detection
Yang, J., & Das, R. K. (2020) · Digital Signal Processing · doi:10.1016/j.dsp.2019.102622 · Cited by 45 · cited 1×
“Another long range feature, inverted constant-Q cepstral coefficient (ICQCC) is considered [33].”
BackgroundSelf-citation
Cited by
Towards End-to-End Synthetic Speech Detection
Hua, G., Teoh, A. B. J., & Zhang, H. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3089437 · Cited by 176
“We make the following remarks from the main results. i) The of [19] and [21] represent the best results sophisticated hand-crafted feature engineering plus an MLP as the back-end classifier. ii) The majority of recent works belong to the type of pre-transform (or light feature engineering) plus DNNs…”
BackgroundMethodWu, Z., Das, R. K., Yang, J., & Li, H. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-1810 · Cited by 111
“The long-term CQT based features are found to capture useful artifacts for spoofing attack detection [33].”
BackgroundSelf-citationMel spectrogram-based audio forgery detection using CNN
Üstübıoğlu, A., Üstübioğlu, B., & Ulutaş, G. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02436-4 · Cited by 100
Shaaban, O. A., Yıldırım, R., & Alguttar, A. A. (2023) · IEEE Access · doi:10.1109/access.2023.3333866 · Cited by 107
“Das et al. and Li et al. [67], [68]. have suggested the utilization of Inverted Constant-Q Coefficient (ICQC), Inverted Constant-Q Cepstral Coefficient (ICQCC), and Long-term Variable Q transform (L-VQT) techniques to identify synthetic music.”
MethodAudio Deepfake Detection: What Has Been Achieved and What Lies Ahead
Zhang, B., Cui, H., Nguyen, V., & Whitty, M. (2025) · Sensors · doi:10.3390/s25071989 · Cited by 72
Significance of Subband Features for Synthetic Speech Detection
Yang, J., Das, R. K., & Li, H. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2956589 · Cited by 70
“The proposed subband features are validated as part of our participation in the ASVspoof 2019 challenge [70], [71].”
BackgroundSelf-citationLong Range Acoustic and Deep Features Perspective on ASVspoof 2019
Das, R. K., Yang, J., & Li, H. (2019) · 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru46091.2019.9003845 · Cited by 65
“The score level fusion of the systems was submitted during the challenge period [30].”
BackgroundSelf-citationA Robust Audio Deepfake Detection System via Multi-View Feature
Yang, Y., Qin, H., Zhou, H., Wang, C., Guo, T., Han, K., & Wang, Y. (2024) · ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp48485.2024.10446560 · Cited by 61
“For instance, the constant-Q transform (CQT) is good at capturing both long-range features and fine details in audio signals with its different filter window lengths across frequency bands[4].”
BackgroundFake Audio Detection Based On Unsupervised Pretraining Models
Lv, Z., Zhang, S., Tang, K., & Hu, P. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9747605 · Cited by 56
Modified Magnitude-Phase Spectrum Information for Spoofing Detection
Yang, J., Wang, H., Das, R. K., & Qian, Y. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3060810 · Cited by 53
Self-citationDefense Against Adversarial Attacks on Spoofing Countermeasures of ASV
Wu, H., Liu, S., Meng, H. M. L., & Lee, H.-Y. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053643 · Cited by 70
“A variety of state-of-the-art coun-termeasure methods that aim at anti-spoofing for ASV models are proposed, and these have achieved considerable performance level for anti-spoofing [10–14].”
BackgroundVoice Spoofing Countermeasure for Logical Access Attacks Detection
Arif, T., Javed, A., Alhameed, M., Jeribi, F., & Tahir, A. (2021) · IEEE Access · doi:10.1109/access.2021.3133134 · Cited by 48
“Spectral features such as MFCC, GTCC, CQCC, etc., have been employed to develop features representation schemes for anti-spoofing methods [36],[37].”
MethodExtraction of Octave Spectra Information for Spoofing Attack Detection
Yang, J., Das, R. K., & Zhou, N. (2019) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2019.2946897 · Cited by 48
“Recently, we have investigated the proposed CMC features on ASVspoof 2019 challenge that showed a promising result with our feature [61], [62].”
BackgroundSelf-citationAssessing the Scope of Generalized Countermeasures for Anti-Spoofing
Das, R. K., Yang, J., & Li, H. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053086 · Cited by 45
“These two features are found to be effective for both logical and physical access attacks on the recent ASVspoof 2019 challenge [25].”
BackgroundSelf-citationXLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection
Xiao, Y., & Das, R. K. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3547861 · Cited by 103
“Previous works in anti-spoofing advocated long-term features to capture the relevant artifacts for spoofing attack detection [7], [8], [9], [10].”
Self-citationLong-term high frequency features for synthetic speech detection
Yang, J., & Das, R. K. (2020) · Digital Signal Processing · doi:10.1016/j.dsp.2019.102622 · Cited by 45
Self-citationTan, C. B., Hijazi, M. H. A., Khamis, N., Nohuddin, P. N. E. B., Zainol, Z., Coenen, F., & Gani, A. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11235-x · Cited by 40
“Since feature fusion can produce good detection results [20, 77, 130], it is conjectured that feature fusion could still be employed in the future.”
BackgroundData Augmentation with Signal Companding for Detection of Logical Access Attacks
Das, R. K., Yang, J., & Li, H. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413501 · Cited by 50
Self-citationDeepfake audio detection with vision transformer based method
Ulutas, G., Tahaoglu, G., & Ustubioglu, B. (2023) · 2023 46th International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp59544.2023.10197715 · Cited by 34
“These methods were submitted to the ASVSpoof 2019 competition and those reported in works afterward [16-20].”
MethodDas, R. K. (2021) · 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge · doi:10.21437/asvspoof.2021-5 · Cited by 30
Self-citationA robust voice spoofing detection system using novel CLS-LBP features and LSTM
Dawood, H., Saleem, S., Hassan, F., & Javed, A. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.02.024 · Cited by 37
“Long-range acoustic features derived from long term constant-Q transform (CQT) were used in Das et al. (2019) for PA and LA attacks detection.”
Replay spoofing countermeasure using autoencoder and siamese networks on ASVspoof 2019 challenge
Adiban, M., Sameti, H., & Shehnepoor, S. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101105 · Cited by 29
Transformer-based Arabic Dialect Identification
Lin, W., Madhavi, M. C., Das, R. K., & Li, H. (2020) · International Conference on Asian Language Processing · doi:10.1109/ialp51396.2020.9310504 · Cited by 29
“Similarly, long range information based features are found to be useful for detection tasks [7]–[9].”
BackgroundSelf-citationAn Overview of Recent Work in Multimedia Forensics
Bhagtani, K., Yadav, A. K. S., Bartusiak, E. R., Xiang, Z., Shao, R., Baireddy, S., & Delp, E. J. (2022) · 2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr54900.2022.00064 · Cited by 25
“Das et al. and Li et al. proposed features such as Inverted Constant-Q Coefficient (ICQC), Inverted Constant-Q Cepstral Coefficient (ICQCC), and Long-term Variable Q Transform (L-VQT) [64, 65] for synthetic audio detection.”
Spatial reconstructed local attention Res2Net with F0 subband for fake speech detection
Fan, C., Xue, J., Tao, J., Yi, J., Wang, C., Zheng, C., & Lv, Z. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106320 · Cited by 28
Ambili, A. R., & Roy, R. C. (2023) · IEEE Access · doi:10.1109/access.2023.3316142 · Cited by 20
Improving anti-spoofing with octave spectrum and short-term spectral statistics information
Yang, J., & Das, R. K. (2019) · Applied Acoustics · doi:10.1016/j.apacoust.2019.107017 · Cited by 18
Self-citationZhang, X., Zhang, X., Liu, W., Zou, X., Sun, M., & Zhao, J. C. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105469 · Cited by 20
Deep 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
“• None of the countermeasure studies used the GMM classifier for system development in the ASVspoof 2019 PA challenge, except for one Das et al. (2019).”
Wu, Y., Hua, H., Li, Z., & Zhang, S. (2025) · Electronics · doi:10.3390/electronics14122456 · Cited by 12
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
Self-citationDiagnosis of COVID-19 Using Auditory Acoustic Cues
Das, R. K., Madhavi, M. C., & Li, H. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-497 · Cited by 10
Self-citationImplicit processing of linear prediction residual for replay attack detection
Veesa, S., & Singh, M. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10125-5 · Cited by 9
“Precisely, Compared to short-term (10-20 ms window length) Fourier processing in RMFCC computation, RCQCC is computed using long-term window-based CQT processing (Das et al., 2019).”
Multi Pattern Features-Based Spoofing Detection Mechanism Using One Class Learning
Üstübioğlu, B., Tahaoğlu, G., Üstübıoğlu, A., Ulutaş, G., Amerini, I., & Kılıç, M. (2024) · IEEE Access · doi:10.1109/access.2024.3447572 · Cited by 7
“While the lowest performing studies were [6] and [10], with the proposed fused approach, superior and satisfactory results have been obtained in many studies.”
BackgroundResultRawTFNet: A Lightweight CNN Architecture for Speech Anti-Spoofing
Yang, X. X., Dang, T., & Das, R. K. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249383 · Cited by 12
“Feature-based methods use pre-designed representations such as linear-frequency cepstral coefficients (LFCC) [7], cochlear filter cepstral coefficient and instantaneous frequency [8] and constant-Q transform (CQT) based representations [9], [10].”
Self-citationFusion 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
“Compared to short-term (10-20 ms window length) Fourier processing in RMFCC computation, RCQCC is computed using long-term window based CQT processing [35].”
MethodNasersharif, B., & Yazdani, M. (2021) · Expert Systems · doi:10.1111/exsy.12670 · Cited by 7
Multi-band Spectral Entropy Information for Detection of Replay Attacks
Liu, Y., Das, R. K., & Li, H. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023062 · Cited by 6
“Again, the importance of various long range acoustic features and deep features are shown recently in [35], [36].”
BackgroundSelf-citationPlaying a Part: Speaker Verification at the movies
Brown, A., Huh, J., Nagrani, A., Chung, J. S., & Zisserman, A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413815 · Cited by 34
“Being able to detect human identity under such conditions of spoofing is valuable for security and authentication [11, 12, 13], and as shown by psychology studies [14, 15], is a challenging task even for humans.”
Capsule Network based End-to-end System for Detection of Replay Attacks
Ouyang, M., Das, R. K., Yang, J., & Li, H. (2021) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp49672.2021.9362111 · Cited by 8
Self-citationClassification of Speech with and without Face Mask using Acoustic FeaturesPreprint
Das, R. K., & Li, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03907 · Cited by 6
Self-citationSynthetic Speech Spoofing Detection Based on Online Hard Example Mining
Hu, C., Zhou, R., & Yuan, Q. (2023) · IEEE Access · doi:10.1109/access.2023.3311849 · Cited by 4
Feature Extraction Method for Hidden Information in Audio Streams Based on HM-EMD
Lou, J., Xu, Z., Zuo, D., & Liu, H. (2021) · Security and Communication Networks · doi:10.1155/2021/5566347 · Cited by 5
“One is to generate spoofed utterances using text-to-speech (TTS) and voice conversion (VC) algorithms, which is also called logic access (LA) [3] and the other is the use of professional replay devices to get spoof attack, which is also known as physical access (PA) [4].”
BackgroundKumar, S. R., & Bharathi, B. (2022) · Circuits Systems and Signal Processing · doi:10.1007/s00034-022-01957-0 · Cited by 5
Ji, J., Xie, Y., & Yang, Y. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10393996
“In the past years, the performance of CMs has been improved greatly through active research in various of approaches [4]–[7].”
BackgroundDetection of Speech Spoofing Based on Dense Convolutional Network
Wang, Y., Chen, X., Chen, Y., & Zhang, S. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-73699-5_18
Yang, J., Wu, J., Wen, H., & Gao, Z. (2024) · Innovative Applications of AI · doi:10.70695/skknxc45
Self-citation$\beta$-Order Energy-Weighting Modulation on Spectral Bins for Replay Speech Detection
Yang, J., You, C. H., & Das, R. K. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3587454
“Similarly, DNN has been successfully utilized for RSD in [36], [37], [48], [49].”
Self-citationEnd-to-End Modeling for Speech Spoofing and Deepfake Detection
Tak, H. (2023) · theses.fr (ABES) · doi:10.70675/aa9fb6cbz3f6az45bcz933fzf95d89893e59 · Cited by 4
Mahum, R., Shehab, M., Nasr, E. A., El-Meligy, M. A., Sarwar, A., & Shaikh, S. (2026) · Array · doi:10.1016/j.array.2026.101184 · Cited by 1
Metadata
- Authors
- Das, R. K., Yang, J., & Li, H.
- Venue
- Interspeech 2019
- Publisher
- ISCA
- Published
- 2019-09-15
- Pages
- 1058-1062
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2972703466
- Cited by
- 53
- References
- 11
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 7 · 2023: 7 · 2022: 6 · 2021: 12 · 2020: 8 · 2019: 7
- FWCI
- 3.16
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (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
- voice spoofing, anti-spoofing, audio feature extraction
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.