Audio Replay Attack Detection with Deep Learning Frameworks

@inproceedings{Lavrentyeva2017AudioRA,
  title={Audio Replay Attack Detection with Deep Learning Frameworks},
  author={Galina Lavrentyeva and Sergey Novoselov and Egor Malykh and Alexander Kozlov and Oleg Kudashev and Vadim Shchemelinin},
  booktitle={INTERSPEECH},
  year={2017}
}
Nowadays spoofing detection is one of the priority research areas in the field of automatic speaker verification. [...] Key Result Experimental results obtained on the Challenge corpora demonstrate that the selected approach outperforms current state-of-the-art baseline systems in terms of spoofing detection quality. Our primary system produced an EER of 6.73% on the evaluation part of the corpora which is 72% relative improvement over the ASVspoof 2017 baseline system.Expand
An Experimental Study on Audio Replay Attack Detection Using Deep Neural Networks
TLDR
Experimental results reveal that DNN considerably outperforms the well-known and successful GMM classifier and long term average spectrum (LTAS) based features are superior to CQCC and MFCC in terms of equal error rate (EER). Expand
Replay Spoof Attack Detection using Deep Neural Networks for Classification
In this paper, we explore the use of the deep learning approach for replay spoof detection in speaker verification systems. Automatic speaker verifications (ASVs) can be easily spoofed by previouslyExpand
End-To-End Audio Replay Attack Detection Using Deep Convolutional Networks with Attention
TLDR
An end-to-end deep learning framework for audio replay attack detection using a novel visual attention mechanism on time-frequency representations of utterances based on group delay features, via deep residual learning (an adaptation of ResNet-18 architecture). Expand
An Investigation about the Scalability of the Spoofing Detection System
TLDR
This work investigates about the effectiveness of building a unified spoofing detection system which could handle the synthesized speech and replayed speech. Expand
Voice Presentation Attack Detection Using Convolutional Neural Networks
TLDR
This work compared the use of three different CNNs architectures: AlexNet, CNNs with max-feature-map activation, and an ensemble of standard CNNs for developing spoofing countermeasures, and discussed their potential to avoid overfitting due to small amounts of training data that is usually available in this task. Expand
A Survey on Replay Attack Detection for Automatic Speaker Verification (ASV) System
  • H. Patil, Madhu R. Kamble
  • Computer Science
  • 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
  • 2018
TLDR
An overview of the replay attack focusing on 2nd ASVspoof 2017 challenge is provided to provide critical analysis of state-of-the-art techniques, various countermeasures, databases, and also aims to present current limitations along with road map ahead in this technological challenging problem. Expand
Multi-task Learning Based Spoofing-Robust Automatic Speaker Verification System
TLDR
A spoofing-robust automatic speaker verification (SR-ASV) system for diverse attacks based on a multi-task learning architecture that is jointly trained with time-frequency representations from utterances to provide recognition decisions for both tasks simultaneously. Expand
Audio-Replay Attack Detection Countermeasures
TLDR
This paper presents the Speech Technology Center (STC) replay attack detection systems proposed for Automatic Speaker Verification Spoofing and Countermeasures Challenge 2017 and demonstrates stable efficiency of deep learning approaches in case of changing acoustic conditions. Expand
Audio Spoofing Verification using Deep Convolutional Neural Networks by Transfer Learning
TLDR
A speech classifier based on deep-convolutional neural network to detect spoofing attacks and uses acoustic time-frequency representation of power spectral densities on Mel frequency scale (Mel-spectrogram), via deep residual learning (an adaptation of ResNet-34 architecture). Expand
Light CNN Architecture Enhancement for Different Types Spoofing Attack Detection
TLDR
Deep learning approach based on Light CNN architecture and its modification for replay attack detection on the base of ASVspoof2017 V2 is considered and the possibility of unified LCNN-based approach to detect not only replay spoofing attacks but also attacks of logical level, specifically speech synthesis and voice conversion is investigated. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 24 REFERENCES
The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection
TLDR
ASVspoof 2017, the second in the series, focused on the development of replay attack countermeasures and indicates that the quest for countermeasures which are resilient in the face of variable replay attacks remains very much alive. Expand
An Investigation of Deep-Learning Frameworks for Speaker Verification Antispoofing
TLDR
This paper aims to investigate the genuine-spoofing discriminative ability from the back-end stage, utilizing recent advancements in deep-learning research, and proposes a novel spoofing detection system, which simultaneously employs convolutional neural networks (CNNs) and recurrent neural network (RNNs) is proposed. Expand
A New Feature for Automatic Speaker Verification Anti-Spoofing: Constant Q Cepstral Coefficients
TLDR
It is argued that there is more to be gained from the study of features rather than classifiers and a new feature for spoofing detection based on the constant Q transform, a perceptually-inspired time-frequency analysis tool popular in theStudy of music. Expand
STC anti-spoofing systems for the ASVspoof 2015 challenge
TLDR
This paper presents the Speech Technology Center (STC) systems submitted to Automatic Speaker Verification Spoofing and Countermeasures (ASVspoof) Challenge 2015 and uses the standard TV approach for probability modelling in spoofing detection systems. Expand
Spoofing and countermeasures for speaker verification: A survey
TLDR
A survey of past work and priority research directions for the future is provided, showing that future research should address the lack of standard datasets and the over-fitting of existing countermeasures to specific, known spoofing attacks. Expand
Spoofing speech detection using temporal convolutional neural network
TLDR
Experimental results on ASVspoof 2015 corpus show that the temporal CNN based classifier is effective for synthetic speech detection, and the proposed method brings a significant performance boost for the unit selection based spoofing speech detection. Expand
ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge
TLDR
The ASVspoof initiative aims to overcome the lack of standards through the provision of standard corpora, protocols and metrics to support a common evaluation of automatic speaker verification technology. Expand
I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry
TLDR
This work studies the vulnerability of two well-known speaker recognition systems, traditional Gaussian mixture model – universal background model (GMM-UBM) and a state-of-the-art i-vector classifier with cosine scoring, which consists of one professional Finnish imitator impersonating five wellknown Finnish public figures. Expand
Large-Scale Video Classification with Convolutional Neural Networks
TLDR
This work studies multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggests a multiresolution, foveated architecture as a promising way of speeding up the training. Expand
Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification
TLDR
A new speaker verification system architecture based on Joint Factor Analysis (JFA) as feature extractor is presented, using the use of the cosine kernel in the new total factor space to design two different systems: the first system is Support Vector Machines based, and the second one uses directly this kernel as a decision score. Expand
...
1
2
3
...