Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech

Patel, Tanvina B.; Patil, Hemant A.

doi:10.21437/interspeech.2015-467

Cited by 86 publications

(23 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Designing a single model to robustly detect unseen spoofing attacks can be challenging, as demonstrated at the ASVspoof 2015 and 2017 challenges, where the best performing systems [11,12,13,14,15,16] made use of an ensemble model combining features or scores. In this paper, we investigate LA and PA spoofing detection on the ASVspoof 2019 dataset using ensemble models.…”

Section: Introductionmentioning

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

Section: Introductionmentioning

confidence: 99%

Ensemble Models for Spoofing Detection in Automatic Speaker Verification

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The studies on fake audio detection are usually carried out from two aspects. The first is robust acoustic features based on signal processing methods [4,5,6]. The second is effective classifiers based on neural networks [7,8,9,10].…”

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

“…CQCC with Gaussian Mixture Models (GMMs) [9] is now a standard system used in spoofing detection for ASV. In [10], Cochlear filter cepstral coefficients (CFCCs) and changes in instantaneous frequencies (CFCCIFs) have been proposed for training two simple GMM classifiers for the detection of genuine and spoofing speech.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, the use of high time-frequency resolution features has become a popular approach [10][11][12]. Higher accuracy has been achieved by directly using CQT spectrograms, from which CQCC features are extracted, together with deep neural networks (DNNs).…”

Section: Introductionmentioning

confidence: 99%

Using Multi-Resolution Feature Maps with Convolutional Neural Networks for Anti-Spoofing in ASV

Wang¹,

Lee²,

Koshinaka³

2020

The Speaker and Language Recognition Workshop (Odyssey 2020)

View full text Add to dashboard Cite

This paper presents a simple but effective method that uses multi-resolution feature maps with convolutional neural networks (CNNs) for anti-spoofing in automatic speaker verification (ASV). The central idea is to alleviate the problem that the feature maps commonly used in anti-spoofing networks are insufficient for building discriminative representations of audio segments, as they are often extracted by a single-length sliding window. Resulting trade-offs between time and frequency resolutions restrict the information in single spectrograms. The proposed method improves both frequency resolution and time resolution by stacking multiple spectrograms that are extracted using different window lengths. These are fed into a convolutional neural network in the form of multiple channels, making it possible to extract more information from input signals while only marginally increasing computational costs. The efficiency of the proposed method has been conformed on the ASVspoof 2019 database. We show that the use of the proposed multiresolution inputs consistently outperforms that of score fusion across different CNN architectures. Moreover, computational cost remains small.

show abstract

Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech

Cited by 86 publications

References 18 publications

Ensemble Models for Spoofing Detection in Automatic Speaker Verification

Ensemble Models for Spoofing Detection in Automatic Speaker Verification

Continual Learning for Fake Audio Detection

Using Multi-Resolution Feature Maps with Convolutional Neural Networks for Anti-Spoofing in ASV

Contact Info

Product

Resources

About