Search

This paper presents a novel end-to-end architecture based on edge detection for autonomous driving. The architecture has been designed to bridge the domain gap between synthetic and real-world images for end-to-end autonomous driving applications and includes custom edge detection layers before the Efficient Net convolutional module. To train the architecture, RGB and depth images were used together with inertial data as inputs to predict the driving speed and steering wheel angle. To pretrain the architecture, a synthetic multimodal dataset for autonomous driving applications was created. The dataset includes driving data from 100 diverse weather and traffic scenarios, gathered from multiple sensors including cameras and an IMU as well as from vehicle control variables. The results show that including edge detection layers in the architecture improves performance for transfer learning when using synthetic and real-world data. In addition, pretraining with synthetic data reduces training time and enhances model performance when using real-world data. [ABSTRACT FROM AUTHOR]

Visual speech recognition (VSR) is a challenging task that aims to interpret speech based solely on lip movements. However, although remarkable results have recently been reached in the field, this task remains an open research problem due to different challenges, such as visual ambiguities, the intra-personal variability among speakers, and the complex modeling of silence. Nonetheless, these challenges can be alleviated when the task is approached from a speaker-dependent perspective. Our work focuses on the adaptation of end-to-end VSR systems to a specific speaker. Hence, we propose two different adaptation methods based on the conventional fine-tuning technique, the so-called Adapters. We conduct a comparative study in terms of performance while considering different deployment aspects such as training time and storage cost. Results on the Spanish LIP-RTVE database show that both methods are able to obtain recognition rates comparable to the state of the art, even when only a limited amount of training data is available. Although it incurs a deterioration in performance, the Adapters-based method presents a more scalable and efficient solution, significantly reducing the training time and storage cost by up to 80%. [ABSTRACT FROM AUTHOR]

Speaker recognition is related to human biometrics dealing with the identification of speakers from their speech. Speaker recognition is an active research area and being widely investigated using artificially intelligent mechanisms. Though speaker recognition systems were previously constructed using handcrafted statistical means of machine learning, currently it is being shifted to state-of-the-art deep learning strategies. Further, deep learning being a fast-paced domain, an absence of comprehensive survey is observed in the current deep speaker recognition technologies. In this paper, we focus on deep speaker recognition technologies. The paper particularly introduces a taxonomy, explains the progress, architectural strategies and processes of some distinctive approaches. Further, the manuscript classifies and enlists the currently available datasets and programming tools. Finally, the paper investigates the challenges and future directives of deep speaker recognition technology.

Visual speech recognition (VSR) is a challenging task that aims to interpret speech based solely on lip movements. However, although remarkable results have recently been reached in the field, this task remains an open research problem due to different challenges, such as visual ambiguities, the intra-personal variability among speakers, and the complex modeling of silence. Nonetheless, these challenges can be alleviated when the task is approached from a speaker-dependent perspective. Our work focuses on the adaptation of end-to-end VSR systems to a specific speaker. Hence, we propose two different adaptation methods based on the conventional fine-tuning technique, the so-called Adapters. We conduct a comparative study in terms of performance while considering different deployment aspects such as training time and storage cost. Results on the Spanish LIP-RTVE database show that both methods are able to obtain recognition rates comparable to the state of the art, even when only a limited amount of training data is available. Although it incurs a deterioration in performance, the Adapters-based method presents a more scalable and efficient solution, significantly reducing the training time and storage cost by up to 80%.

The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13. In CASP14, deep learning has boosted the field to unanticipated levels reaching near‐experimental accuracy. This success comes from advances transferred from other machine learning areas, as well as methods specifically designed to deal with protein sequences and structures, and their abstractions. Novel emerging approaches include (i) geometric learning, that is, learning on representations such as graphs, three‐dimensional (3D) Voronoi tessellations, and point clouds; (ii) pretrained protein language models leveraging attention; (iii) equivariant architectures preserving the symmetry of 3D space; (iv) use of large meta‐genome databases; (v) combinations of protein representations; and (vi) finally truly end‐to‐end architectures, that is, differentiable models starting from a sequence and returning a 3D structure. Here, we provide an overview and our opinion of the novel deep learning approaches developed in the last 2 years and widely used in CASP14. [ABSTRACT FROM AUTHOR]