ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements

Delgado, Héctor; Todisco, Massimiliano; Sahidullah, Md; Evans, Nicholas; Kinnunen, Tomi; Lee, Kong Aik; Yamagishi, Junichi

doi:10.21437/odyssey.2018-42

Cited by 123 publications

(113 citation statements)

References 19 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…On the ASVspoof 2017 dataset, the GMM displays EERs of 19.07% and 22.6% on the development and evaluation sets, respectively. Note that our baseline is completely different from the CQCC-GMM results of [84] for two reasons. First, we use a unified time representation of the first 100 frames obtained either by truncating or copying time frames, for reasons explained earlier.…”

Section: Impact Of Latent Space Dimensionalitymentioning

confidence: 95%

“…We apply a pre-processing step on the raw-audio waveforms to trim silence/noise before and after the utterance in the training, development and test sets, following recommendations in [45] and [76]. Following [84], we extract log energy plus 19dimensional static coefficients augmented with deltas and double-deltas, yielding 60-dimensional feature vectors. This is followed by cepstral mean and variance normalisation.…”

Section: Features and Input Representationmentioning

confidence: 99%

See 1 more Smart Citation

Deep generative variational autoencoding for replay spoof detection in automatic speaker verification

Chettri

Kinnunen

Benetos

2020

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

Automatic speaker verification (ASV) systems are highly vulnerable to presentation attacks, also called spoofing attacks. Replay is among the simplest attacks to mount -yet difficult to detect reliably. The generalization failure of spoofing countermeasures (CMs) has driven the community to study various alternative deep learning CMs. The majority of them are supervised approaches that learn a human-spoof discriminator. In this paper, we advocate a different, deep generative approach that leverages from powerful unsupervised manifold learning in classification. The potential benefits include the possibility to sample new data, and to obtain insights to the latent features of genuine and spoofed speech. To this end, we propose to use variational autoencoders (VAEs) as an alternative backend for replay attack detection, via three alternative models that differ in their class-conditioning. The first one, similar to the use of Gaussian mixture models (GMMs) in spoof detection, is to train independently two VAEs -one for each class. The second one is to train a single conditional model (C-VAE) by injecting a one-hot class label vector to the encoder and decoder networks. Our final proposal integrates an auxiliary classifier to guide the learning of the latent space. Our experimental results using constant-Q cepstral coefficient (CQCC) features on the ASVspoof 2017 and 2019 physical access subtask datasets indicate that the C-VAE offers substantial improvement in comparison to training two separate VAEs for each class. On the 2019 dataset, the C-VAE outperforms the VAE and the baseline GMM by an absolute 9 -10% in both equal error rate (EER) and tandem detection cost function (t-DCF) metrics. Finally, we propose VAE residuals -the absolute difference of the original input and the reconstruction as features for spoofing detection. The proposed frontend approach augmented with a convolutional neural network classifier demonstrated substantial improvement over the VAE backend use case.

show abstract

Section: Impact Of Latent Space Dimensionalitymentioning

confidence: 95%

Section: Features and Input Representationmentioning

confidence: 99%

Deep generative variational autoencoding for replay spoof detection in automatic speaker verification

Chettri

Kinnunen

Benetos

2020

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use two publicly available spoofing datasets, ASVspoof 2017 v2.0 [28] and ASVspoof 2019 physical access (PA), [7] for model training and testing. In addition, we also include results on the recently released ASVspoof2019 real PA dataset 1 for the challenging case of cross-database performance evaluation.…”

Section: Datasetmentioning

confidence: 99%

Ensemble Models for Spoofing Detection in Automatic Speaker Verification

et al. 2019

View full text Add to dashboard Cite

Spectrograms -time-frequency representations of audio signals -have found widespread use in neural network-based spoofing detection. While deep models are trained on the fullband spectrum of the signal, we argue that not all frequency bands are useful for these tasks. In this paper, we systematically investigate the impact of different subbands and their importance on replay spoofing detection on two benchmark datasets: ASVspoof 2017 v2.0 and ASVspoof 2019 PA. We propose a joint subband modelling framework that employs n different sub-networks to learn subband specific features. These are later combined and passed to a classifier and the whole network weights are updated during training. Our findings on the ASVspoof 2017 dataset suggest that the most discriminative information appears to be in the first and the last 1 kHz frequency bands, and the joint model trained on these two subbands shows the best performance outperforming the baselines by a large margin. However, these findings do not generalise on the ASVspoof 2019 PA dataset. This suggests that the datasets available for training these models do not reflect real world replay conditions suggesting a need for careful design of datasets for training replay spoofing countermeasures.

show abstract

“…The evaluation subset contains data collected from 161 replay sessions in 62 unique replay configurations 7 . More details regarding replay configurations can be found in [126,135].…”

Section: Asvspoof 2017mentioning

confidence: 99%

Introduction to Voice Presentation Attack Detection and Recent Advances

Sahidullah

Delgado

Todisco

et al. 2019

Handbook of Biometric Anti-Spoofing

Self Cite

View full text Add to dashboard Cite

Over the past few years significant progress has been made in the field of presentation attack detection (PAD) for automatic speaker recognition (ASV). This includes the development of new speech corpora, standard evaluation protocols and advancements in front-end feature extraction and back-end classifiers. The use of standard databases and evaluation protocols has enabled for the first time the meaningful benchmarking of different PAD solutions. This chapter summarises the progress, with a focus on studies completed in the last three years. The article presents a summary of findings and lessons learned from two ASVspoof challenges, the first community-led benchmarking efforts. These show that ASV PAD remains an unsolved problem and that further attention is required to develop generalised

show abstract

ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements

Cited by 123 publications

References 19 publications

Deep generative variational autoencoding for replay spoof detection in automatic speaker verification

Deep generative variational autoencoding for replay spoof detection in automatic speaker verification

Ensemble Models for Spoofing Detection in Automatic Speaker Verification

Introduction to Voice Presentation Attack Detection and Recent Advances

Contact Info

Product

Resources

About