Peter Peer

In recent years, there has been increasing interest in the conversion of images into audio descriptions. This is a field that lies at the intersection of Computer Vision (CV) and Natural Language Processing (NLP), and it involves various tasks, including creating textual descriptions of images and converting them directly into auditory representations. Another aspect of this field is the synthesis of natural speech from text. This has significant potential to improve accessibility, user experience, and the applications of Artificial Intelligence (AI). In this article, we reviewed a wide range of image-to-audio conversion techniques. Various aspects of image captioning, speech synthesis, and direct image-to-speech conversion have been explored, from fundamental encoder–decoder architectures to more advanced methods such as transformers and adversarial learning. Although the focus of this review is on synthesizing audio descriptions from visual data, the reverse task of creating visual content from natural language descriptions is also covered. This study provides a comprehensive overview of the techniques and methodologies used in these fields and highlights the strengths and weaknesses of each approach. The study emphasizes the importance of various datasets, such as MS COCO, LibriTTS, and VizWiz Captions, which play a critical role in training models, evaluating them, promoting inclusivity, and solving real-world problems. The implications for the future suggest the potential of generating more natural and contextualized audio descriptions, whereas direct image-to-speech tasks provide opportunities for intuitive auditory representations of visual content.

The study investigates the task of authorship attribution on short texts in Slovenian using the BERT language model. Authorship attribution is the task of attributing a written text to its author, frequently using stylometry or computational techniques. We create five custom datasets for different numbers of included text authors and fine-tune two BERT models, SloBERTa and BERT Multilingual (mBERT), to evaluate their performance in closed-class and open-class problems with varying numbers of authors. Our models achieved an F1 score of approximately 0.95 when using the dataset with the comments of the top five users by the number of written comments. Training on datasets that include comments written by an increasing number of people results in models with a gradually decreasing F1 score. Including out-of-class comments in the evaluation decreases the F1 score by approximately 0.05. The study demonstrates the feasibility of using BERT models for authorship attribution in short texts in the Slovenian language.

Gaze estimation is an established research problem in computer vision. It has various applications in real life, from human–computer interactions to health care and virtual reality, making it more viable for the research community. Due to the significant success of deep learning techniques in other computer vision tasks—for example, image classification, object detection, object segmentation, and object tracking—deep learning-based gaze estimation has also received more attention in recent years. This paper uses a convolutional neural network (CNN) for person-specific gaze estimation. The person-specific gaze estimation utilizes a single model trained for one individual user, contrary to the commonly-used generalized models trained on multiple people’s data. We utilized only low-quality images directly collected from a standard desktop webcam, so our method can be applied to any computer system equipped with such a camera without additional hardware requirements. First, we used the web camera to collect a dataset of face and eye images. Then, we tested different combinations of CNN parameters, including the learning and dropout rates. Our findings show that building a person-specific eye-tracking model produces better results with a selection of good hyperparameters when compared to universal models that are trained on multiple users’ data. In particular, we achieved the best results for the left eye with 38.20 MAE (Mean Absolute Error) in pixels, the right eye with 36.01 MAE, both eyes combined with 51.18 MAE, and the whole face with 30.09 MAE, which is equivalent to approximately 1.45 degrees for the left eye, 1.37 degrees for the right eye, 1.98 degrees for both eyes combined, and 1.14 degrees for full-face images.