Constant-Q Deep Coefficients for Playback Attack Detection

Yang, Jichen; Xu, Longting; Ren, Bo

doi:10.1587/transinf.2019edl8115

Cited by 4 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spoofing attacks are mainly categorized into two types: physical access (PA) and logical access (LA). The PA considers the replay attack [2][3][4] while the LA includes the spoofing attacks based on text-to-speech synthesis [5][6][7][8] and voice conversion [9][10][11] technologies.…”

Section: Introductionmentioning

confidence: 99%

Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network

Kim¹,

Ban²

2022

Preprint

View full text Add to dashboard Cite

The spoof speech detection (SSD) is the essential countermeasure for automatic speaker verification systems. Although SSD with magnitude features in the frequency domain has shown promising results, the phase information also can be important to capture the artefacts of certain types of spoofing attacks. Thus, both magnitude and phase features must be considered to ensure the generalization ability to diverse types of spoofing attacks. In this paper, we investigate the failure reason of feature-level fusion of the previous works through the entropy analysis from which we found that the randomness difference between magnitude and phase features is large, which can interrupt the feature-level fusion via backend neural network; thus, we propose a phase network to reduce that difference. Our SSD system: phase network equipped Res2Net achieved significant performance improvement, specifically in the spoofing attack for which the phase information is considered to be important. Also, we demonstrate our SSD system in both knownand unknown-kind SSD scenarios for practical applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network

Kim¹,

Ban²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Apart from the handcrafted features, some deep features based on power spectrum were also explored in recent years. For example, constant-Q deep coefficients [20], that is obtained from a DNN by using log LPS as the input plus discrete cosine transform to extract the principal information at the last step. The use of light convolutional neural network with LPS as the input to extract deep feature for replay speech detection has been studied in [5], [7].…”

Section: Introductionmentioning

confidence: 99%

“…• Different to the previous works, LFNS is used to feed neural networks such as DNN and ResNet to form frame-and utterance-based end-to-end systems for replay speech answer-sheet detection. The reason why we select DNN as the frame-based neural network and ResNet as the utterance-based neural network here is that they are widely used in the field of spoofing attack detection such DNN in [12], [19], [20] and ResNet in [22]. In addition, we also construct classifiers for CNOC and CNOC-LSE using DNN and ResNet, respectively.…”

Section: Introductionmentioning

confidence: 99%

Replay Speech Answer-Sheet Detection on Intelligent Language Learning System Based on Power Spectrum Decomposition

Xiong

Zhu

2021

IEEE Access

View full text Add to dashboard Cite

Replay speech answer-sheet detection is an urgent problem to be solved for intelligent language learning system. Traditional features used in replay speech detection are often extracted from power spectrum. However, power spectrum may not be the optimal spectrum to extract feature for replay speech answer-sheet detection because it doesn't consider the characteristic of replay speech. In order to solve this limitation, this paper proposes a method of power spectrum decomposition for replay speech answer-sheet detection on intelligent language learning system. Log frame-wise normalization spectrum (LFNS) and log spectral energy (LSE) which consider the characteristic of replay speech, are obtained by decomposing log power spectrum based on constant-Q transform. Next, the other two features are obtained at the base of LFNS and LSE. The first is constant-Q normalization octave coefficients (CNOC) which is obtained by combining LFNS and octave subband transform. The second is CNOC-LSE that is obtained by combining CNOC and LSE. Then LFNS, CNOC and CNOC-LSE are fed into frame-and utterance-based neural networks. Experimental results show that the proposed LFNS can outperform the conventional log power spectrum, CNOC and CNOC-LSE can perform better than most of commonly used features. We found that utterance-based neural network outperforms frame-based neural network with the same inputs. In addition, handcrafted features give worse performance than corresponding spectrum for the utterance-based neural network while the opposite conclusion can be obtained for the frame-based neural network.

show abstract

Phase-Aware Spoof Speech Detection Based On Res2net with Phase Network

Kim¹,

Ban²

2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Constant-Q Deep Coefficients for Playback Attack Detection

Cited by 4 publications

References 13 publications

Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network

Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network

Replay Speech Answer-Sheet Detection on Intelligent Language Learning System Based on Power Spectrum Decomposition

Phase-Aware Spoof Speech Detection Based On Res2net with Phase Network

Contact Info

Product

Resources

About