ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection

Todisco, Massimiliano; Wang, Xin; Vestman, Ville; Sahidullah, Md; Delgado, Héctor; Nautsch, Andreas; Yamagishi, Junichi; Evans, Nicholas; Kinnunen, Tomi; Lee, Kong Aik

doi:10.48550/arxiv.1904.05441

Cited by 50 publications

(87 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of fake audio detection, there are fewer existing datasets. One of the most famous datasets are ASVspoof datasets [4,5,6]. Among them, ASVspoof 2015 particularly focused on the detection of synthetic and converted speech.…”

Section: Deepfake Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

AI Singapore Trusted Media Challenge Dataset

Chen,

Chua,

Winkler

et al. 2022

Preprint

View full text Add to dashboard Cite

The development of powerful deep learning technologies has brought about some negative effects to both society and individuals. One such issue is the emergence of fake media. To tackle the issue, we have organized the Trusted Media Challenge (TMC) to explore how Artificial Intelligence (AI) technologies could be leveraged to combat fake media. Together with the challenge, we have released a challenge dataset which consists of 4,380 fake and 2,563 real videos. All these videos are accompanied with audios and different video and/or audio manipulation methods are adopted to produce different types of fake media. The videos in the dataset have various durations, background, illumination, a minimum resolution of 360p and may contain perturbations that mimic transmission errors and bad compression. We have also carried out a user study to demonstrate the quality of our composed dataset. The results show that our dataset has a promising quality and can fool human participants in many cases.

show abstract

Section: Deepfake Datasetsmentioning

confidence: 99%

“…There are some existing deepfake datasets focusing on video manipulation [1,2,3] or audio manipulation [4,5,6]. The only dataset which has both video and audio manipulations is [7].…”

mentioning

confidence: 99%

AI Singapore Trusted Media Challenge Dataset

Chen,

Chua,

Winkler

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…WaveNet vocoder is used generate high quality raw speech samples conditioned on acoustic features [24]. WavNetbased vocoder is popularly used in ASVSpoof 2019 challenge to create logical access presentation attacks [41]. In our work, we have used MFCC features as the acoustic features in synthesizing 16-bit raw audio.…”

Section: ) Synthesized Attacksmentioning

confidence: 99%

“…The PAD methods used to evaluate the attacks created using speech are chosen from the baseline methods in the ASVSpoof 2019 challenge [41]. The two baseline methods are available in ASVSpoof 2019 evaluation protocols.…”

Section: Presentation Attack Detection (Pad) 1) Voice Padmentioning

confidence: 99%

Multilingual Audio-Visual Smartphone Dataset And Evaluation

Mandalapu¹,

N²,

Ramachandra³

et al. 2021

Preprint

View full text Add to dashboard Cite

Smartphones have been employed with biometric-based verification systems to provide security in highly sensitive applications. Audio-visual biometrics are getting popular due to the usability and also it will be challenging to spoof because of multi-modal nature. In this work, we present an audiovisual smartphone dataset captured in five different recent smartphones. This new dataset contains 103 subjects captured in three different sessions considering the different real-world scenarios. Three different languages are acquired in this dataset to include the problem of language dependency of the speaker recognition systems. These unique characteristics of this dataset will pave the way to implement novel state-of-the-art unimodal or audio-visual speaker recognition systems. We also report the performance of the bench-marked biometric verification systems on our dataset. The robustness of biometric algorithms is evaluated towards multiple dependencies like signal noise, device, language and presentation attacks like replay and synthesized signals with extensive experiments. The obtained results raised many concerns about the generalization properties of state-of-the-art biometrics methods in smartphones.

show abstract

“…Research has shown that both Technology and the human ear * equal contribution are susceptible to voice spoofing. In the past few years, Anti-Spoofing for ASV has become a field of interest in the research community, as four challenges [4,5,6,7] have been held in which the goal has been to improve the ability to discriminate bona fide speech from spoofed speech.…”

Section: Introductionmentioning

confidence: 99%

A Study On Data Augmentation In Voice Anti-Spoofing

Cohen¹,

Rimon²,

Permuter³

2021

Preprint

View full text Add to dashboard Cite

In this paper we perform an in depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different bandwidths and unseen spoofing attacks, which have all been shown to significantly degrade the performance of audio based systems and Anti-Spoofing systems. Our results are based on the ASVspoof 2021 challenge, in the Logical Access (LA) and Deep Fake (DF) categories. Our study is Data-Centric, meaning that the models are fixed and we significantly improve the results by making changes in the data. We introduce two forms of data augmentation -compression augmentation for the DF part, compression & channel augmentation for the LA part. In addition, a new type of online data augmentation, SpecAverage, is introduced in which the audio features are masked with their average value in order to improve generalization. Furthermore, we introduce a Log spectrogram feature design that improved the results. Our best single system and fusion scheme both achieve state of the art performance in the DF category, with an EER of 15.46% and 14.46% respectively. Our best system for the LA task reduced the best baseline EER by 50% and the min t-DCF by 16%. Our techniques to deal with spoofed data from a wide variety of distributions can be replicated and can help anti-spoofing and speech based systems enhance their results.

show abstract

ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection

Cited by 50 publications

References 0 publications

AI Singapore Trusted Media Challenge Dataset

AI Singapore Trusted Media Challenge Dataset

Multilingual Audio-Visual Smartphone Dataset And Evaluation

A Study On Data Augmentation In Voice Anti-Spoofing

Contact Info

Product

Resources

About