Deep Multitask Gaze Estimation with a Constrained Landmark-Gaze Model

Abstract

The step preceding the speaker identification process consists in the determination of the authenticity of a speech sample. The focus of this thesis is on the performance of humans in detecting altered samples from replay, speech synthesis (TTS) and voice conversion (VC) systems. A listening test was constructed on the online survey platform LimeSurvey. The participants were asked to assess a series of recordings by first giving a binary evaluation ("authentic" or "altered") and then by specifying their level of confidence on a 5-point scale. Moreover, the logic behind the aural approach was studied by inspecting the criteria used by the respondents in the assessment of the recordings. The same samples were also evaluated with an automatic LFCC-GMM-based system, trained on two different datasets, in order to make a comparison. The results show that the human's performance (EER=0.10) surpasses the machine's (EER=0.35 and EER=0.46) in the detection of the altered samples. However, sophisticated voice disguise systems have now reached levels of quality that can also easily fool most humans, which makes them a real threat to security and the identification process.

A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation

“…Zhang et al (Zhang et al 2015) first proposed a CNNs-based method to estimate gaze, the method was designed based on LeNet (Lecun et al 1998) and estimates gaze from eye images. Yu et al (Yu, Liu, and Odobez 2018) proposed a multitask gaze estimation model with landmark constrain, they estimate gaze from eye images. Fischer et al (Fischer, Chang, and Demiris 2018) extracted feature from two-eye images with VGG-16 (Karen and Andrew 2014) to estimate gaze, they use an ensemble scheme to increase robustness of proposed method.…”

Learning a 3D Gaze Estimator With Adaptive Weighted Strategy

“…The results of gaze estimation are significantly affected by the head pose. Similar to [32], we normalize the image data to weaken the influence of this factor. The basic concept of data preprocessing is shown in Fig.…”

“…Fischer et al [31] recorded a new dataset of different head postures to improve the robustness of gaze estimation, applied semantic image inpainting to the area covered by glasses to eliminate the obtrusiveness of the glasses and built a bridge between training and test images. Yu et al [32] introduced a constrained landmark-Gaze model to get the relation of eye landmark locations and gaze directions. Park et al [33] used single eye image as input and simplified the task of 3D gaze estimation.…”

SalGaze: Personalizing Gaze Estimation using Visual Saliency

“…With recent advances in machine learning, the combination of appearance-based gaze estimation and deep learning has become a popular method for remote estimation of gaze [53,7,54,48,13,55]. Appearance-based algorithms have the advantage of only using an image of the person's face or eyes as input, therefore eliminating the need of any specialized hardware other than a regular camera.…”