ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge

Wu, Zhizheng; Kinnunen, Tomi; Evans, Nicholas; Yamagishi, Junichi; Hanilçi, Cemal; Sahidullah, Md; Сизов, А. С.

doi:10.21437/interspeech.2015-462

Cited by 286 publications

(152 citation statements)

References 28 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…Then the spectrogram is used to generate audio with a vocoder. We use a high-performance neural vocoder LPCNet [24] with 22-dimensional acoustic features to generate the audio 4 . The components of the whole TTS system are all open source.…”

Section: Fully Fake Audio Generationmentioning

confidence: 99%

“…The models of utterance-level binary classification are evaluated in terms of equal error rate (EER). More details of metrics can be found in [4].…”

Section: Evaluation Metricmentioning

confidence: 99%

“…However, this technology also poses a great threat to the global political economy and social stability if some attackers and criminals misuse it with the intent to cause harm. Therefore, an increasing number of efforts [4,5,6,7,8,9] have been made to detect the fake audio recently. A diverse set of databases also have been designed to hold back the development of this research.…”

Section: Introductionmentioning

confidence: 99%

“…ing database SAS including a wide variety of spoofing methods of speech synthesis and voice conversion. Based on the SAS database, the first ASVspoof challenge [4] have been organized involving only the detection of spoofed speech in 2015. Replay attack is also a key concern among other possible attacks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Half-Truth: A Partially Fake Audio Detection Dataset

Yi¹,

Bai²,

Tao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Diverse promising datasets have been designed to hold back the development of fake audio detection, such as ASVspoof databases. However, previous datasets ignore an attacking situation, in which the hacker hides some small fake clips in real speech audio. This poses a serious threat since that it is difficult to distinguish the small fake clip from the whole speech utterance. Therefore, this paper develops such a dataset for half-truth audio detection (HAD). Partially fake audio in the HAD dataset involves only changing a few words in an utterance. The audio of the words is generated with the very latest state-of-the-art speech synthesis technology. We can not only detect fake uttrances but also localize manipulated regions in a speech using this dataset. Some benchmark results are presented on this dataset. The results show that partially fake audio presents much more challenging than fully fake audio for fake audio detection.

show abstract

Section: Fully Fake Audio Generationmentioning

confidence: 99%

“…The models of utterance-level binary classification are evaluated in terms of equal error rate (EER). More details of metrics can be found in [4].…”

Section: Evaluation Metricmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Half-Truth: A Partially Fake Audio Detection Dataset

Yi¹,

Bai²,

Tao³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Fake audio detection has attracted increasing attention since the organization of a series of automatic speaker verification spoofing and countermeasures challenge (ASVspoof) [1,2,3]. Plenty of approaches are proposed to alleviate the threat of voice spoofing attacks.…”

Section: Introductionmentioning

confidence: 99%

Continual Learning for Fake Audio Detection

Ma,

Yi,

Tao

et al. 2021

Preprint

View full text Add to dashboard Cite

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data. Fine-tuning and retraining from scratch have been applied to incorporate new data. However, fine-tuning leads to performance degradation on previous data. Retraining takes a lot of time and computation resources. Besides, previous data are unavailable due to privacy in some situations. To solve the above problems, this paper proposes detecting fake without forgetting, a continual-learningbased method, to make the model learn new spoofing attacks incrementally. A knowledge distillation loss is introduced to loss function to preserve the memory of original model. Supposing the distribution of genuine voice is consistent among different scenarios, an extra embedding similarity loss is used as another constraint to further do a positive sample alignment. Experiments are conducted on the ASVspoof2019 dataset. The results show that our proposed method outperforms fine-tuning by the relative reduction of average equal error rate up to 81.62%.

show abstract

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Janicki

Alegre

Evans

2016

Security Comm Networks

Self Cite

View full text Add to dashboard Cite

This paper analyses the threat of replay spoofing or presentation attacks in the context of automatic speaker verification. As relatively high‐technology attacks, speech synthesis and voice conversion, which have thus far received far greater attention in the literature, are probably beyond the means of the average fraudster. The implementation of replay attacks, in contrast, requires no specific expertise nor sophisticated equipment. Replay attacks are thus likely to be the most prolific in practice, while their impact is relatively under‐researched. The work presented here aims to compare at a high level the threat of replay attacks with those of speech synthesis and voice conversion. The comparison is performed using strictly controlled protocols and with six different automatic speaker verification systems including a state‐of‐the‐art iVector/probabilistic linear discriminant analysis system. Experiments show that low‐effort replay attacks present at least a comparable threat to speech synthesis and voice conversion. The paper also describes and assesses two replay attack countermeasures. A relatively new approach based on the local binary pattern analysis of speech spectrograms is shown to outperform a competing approach based on the detection of far‐field recordings. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge

Cited by 286 publications

References 28 publications

Half-Truth: A Partially Fake Audio Detection Dataset

Half-Truth: A Partially Fake Audio Detection Dataset

Continual Learning for Fake Audio Detection

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Contact Info

Product

Resources

About