Recognition of spoofed voice using convolutional neural networks

Liang, Huixin; Lin, Xiaodan; Zhang, Qiong; Kang, Xiangui

doi:10.1109/globalsip.2017.8308651

Cited by 16 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One possible reason is that the data volume of NIST is larger than the other two data sets, TIMIT and UME, shown in Table 1, so that the model trained by NIST has better generalization capabilities. In [39], the accuracy of case 1 is 94.37%, while our accuracy is 96.45%, indicating that our method is superior to the method in [39]. The results of the case 2 and case 3 are not given in [39].…”

Section: Cross-database Evaluationmentioning

confidence: 70%

“…In [39], the accuracy of case 1 is 94.37%, while our accuracy is 96.45%, indicating that our method is superior to the method in [39]. The results of the case 2 and case 3 are not given in [39].…”

Section: Cross-database Evaluationmentioning

confidence: 70%

“…The detection results of our proposed method and the comparison with other reported detection results are shown in Table.2. It can be seen that the average detection accuracy of our method is 2.58% higher than that of the traditional CNN model [39] and 3.66% higher than that of the SVM [38].…”

Section: Intra-database Evaluationmentioning

confidence: 83%

“…The cross-database recognition rates were lower than 90%, and the computation load was heavy. In addition, Liang et al proposed an approach based on convolutional neural network (CNN) [39] . The accuracy rates of the above methods are all less than 95%, indicating that an improvement is needed for practical applications.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Detection of Speaker De-identification Disguise Based on Dense Convolutional Network

Wang

Zhu

2020

Preprint

View full text Add to dashboard Cite

Nowadays, speaker disguise is a common operation that presents a great challenge to social security. Therefore, it is important to recognize the authenticity of speech. Most of the current researches focus on speech spoofing, which simulates a target speaker to break through the state-of-art ASV systems by increasing false acceptance rate. Meanwhile, there is another type of disguise, i.e. de-identification, which transforms a speech signal without a target to increase the false rejection rate in order not to be recognized. It has received far less attention. Therefore, in this paper, we investigate the de-identification model and propose a method to detect de-identification speeches from genuine speeches by using a very deep dense convolutional network with 135 layers. The experimental results show that the average accuracy of the proposed method outperforms the reported state-of-the-art methods.

show abstract

Section: Cross-database Evaluationmentioning

confidence: 70%

Section: Cross-database Evaluationmentioning

confidence: 70%

Section: Intra-database Evaluationmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Speaker De-identification Disguise Based on Dense Convolutional Network

Wang

Zhu

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Consequently, in a CNN, nodes in the next hidden layer are only related to some successive input data, which is implemented by weight sharing. This enables CNNs to exploit the potential spatial correlation in the data and reduces the quantity of training parameters in the network, making CNNs particularly superior in the fields of data processing and voice recognition [33][34][35].…”

Section: Background Knowledgementioning

confidence: 99%

DenseNet-Based Depth-Width Double Reinforced Deep Learning Neural Network for High-Resolution Remote Sensing Image Per-Pixel Classification

Tao

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:Deep neural networks (DNNs) face many problems in the very high resolution remote sensing (VHRRS) per-pixel classification field. Among the problems is the fact that as the depth of the network increases, gradient disappearance influences classification accuracy and the corresponding increasing number of parameters to be learned increases the possibility of overfitting, especially when only a small amount of VHRRS labeled samples are acquired for training. Further, the hidden layers in DNNs are not transparent enough, which results in extracted features not being sufficiently discriminative and significant amounts of redundancy. This paper proposes a novel depth-width-reinforced DNN that solves these problems to produce better per-pixel classification results in VHRRS. In the proposed method, densely connected neural networks and internal classifiers are combined to build a deeper network and balance the network depth and performance. This strengthens the gradients, decreases negative effects from gradient disappearance as the network depth increases and enhances the transparency of hidden layers, making extracted features more discriminative and reducing the risk of overfitting. In addition, the proposed method uses multi-scale filters to create a wider neural network. The depth of the filters from each scale is controlled to decrease redundancy and the multi-scale filters enable utilization of joint spatio-spectral information and diverse local spatial structure simultaneously. Furthermore, the concept of network in network is applied to better fuse the deeper and wider designs, making the network operate more smoothly. The results of experiments conducted on BJ02, GF02, geoeye and quickbird satellite images verify the efficacy of the proposed method. The proposed method not only achieves competitive classification results but also proves that the network can continue to be robust and perform well even while the amount of labeled training samples is decreasing, which fits the small training samples situation faced by VHRRS per-pixel classification.

show abstract

Deep-Wavelets and convolutional neural networks to support breast cancer diagnosis on thermography images

Barbosa

Silva

Santana

et al. 2022

Computer Methods in Biomechanics and Biomedical Engineering: Im

View full text Add to dashboard Cite

Recognition of spoofed voice using convolutional neural networks

Cited by 16 publications

References 16 publications

Detection of Speaker De-identification Disguise Based on Dense Convolutional Network

Detection of Speaker De-identification Disguise Based on Dense Convolutional Network

DenseNet-Based Depth-Width Double Reinforced Deep Learning Neural Network for High-Resolution Remote Sensing Image Per-Pixel Classification

Deep-Wavelets and convolutional neural networks to support breast cancer diagnosis on thermography images

Contact Info

Product

Resources

About