Voice-quality Features for Deep Neural Network Based Speaker Verification Systems

Woubie, Abraham; Koivisto, Lauri; Bäckström, Tom

doi:10.23919/eusipco54536.2021.9616242

Cited by 6 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep neural networks have been successfully used in different applications such as speaker verification [2,3] and image recognition [4,5]. In addition to artificial neural networks, spiking neural networks have been successfully used for image recognition [6,7].…”

Section: Introductionmentioning

confidence: 99%

UFace: An Unsupervised Deep Learning Face Verification System

2022

Self Cite

View full text Add to dashboard Cite

Deep convolutional neural networks are often used for image verification but require large amounts of labeled training data, which are not always available. To address this problem, an unsupervised deep learning face verification system, called UFace, is proposed here. It starts by selecting from large unlabeled data the k most similar and k most dissimilar images to a given face image and uses them for training. UFace is implemented using methods of the autoencoder and Siamese network; the latter is used in all comparisons as its performance is better. Unlike in typical deep neural network training, UFace computes the loss function k times for similar images and k times for dissimilar images for each input image. UFace’s performance is evaluated using four benchmark face verification datasets: Labeled Faces in the Wild (LFW), YouTube Faces (YTF), Cross-age LFW (CALFW) and Celebrities in Frontal Profile in the Wild (CFP-FP). UFace with the Siamese network achieved accuracies of 99.40%, 96.04%, 95.12% and 97.89%, respectively, on the four datasets. These results are comparable with the state-of-the-art methods, such as ArcFace, GroupFace and MegaFace. The biggest advantage of UFace is that it uses much less training data and does not require labeled data.

show abstract