Bagher BabaAli

Saleh Momeni, Bagher BabaAli

Handwriting recognition is a challenging and critical problem in the fields of pattern recognition and machine learning, with applications spanning a wide range of domains. In this paper, we focus on the specific issue of recognizing offline Arabic handwritten text. Existing approaches typically utilize a combination of convolutional neural networks for image feature extraction and recurrent neural networks for temporal modeling, with connectionist temporal classification used for text generation. However, these methods suffer from a lack of parallelization due to the sequential nature of recurrent neural networks. Furthermore, these models cannot account for linguistic rules, necessitating the use of an external language model in the post-processing stage to boost accuracy. To overcome these issues, we introduce two alternative architectures, namely the Transformer Transducer and the standard sequence-to-sequence Transformer, and compare their performance in terms of accuracy and speed. Our approach can model language dependencies and relies only on the attention mechanism, thereby making it more parallelizable and less complex. We employ pre-trained Transformers for both image understanding and language modeling. Our evaluation on the Arabic KHATT dataset demonstrates that our proposed method outperforms the current state-of-the-art approaches for recognizing offline Arabic handwritten text.

Saleh Momeni, Bagher BabaAli

Keystroke biometrics is a promising approach for user identification and verification, leveraging the unique patterns in individuals' typing behavior. In this paper, we propose a Transformer-based network that employs self-attention to extract informative features from keystroke sequences, surpassing the performance of traditional Recurrent Neural Networks. We explore two distinct architectures, namely bi-encoder and cross-encoder, and compare their effectiveness in keystroke authentication. Furthermore, we investigate different loss functions, including triplet, batch-all triplet, and WDCL loss, along with various distance metrics such as Euclidean, Manhattan, and cosine distances. These experiments allow us to optimize the training process and enhance the performance of our model. To evaluate our proposed model, we employ the Aalto desktop keystroke dataset. The results demonstrate that the bi-encoder architecture with batch-all triplet loss and cosine distance achieves the best performance, yielding an exceptional Equal Error Rate of 0.0186%. Furthermore, alternative algorithms for calculating similarity scores are explored to enhance accuracy. Notably, the utilization of a one-class Support Vector Machine reduces the Equal Error Rate to an impressive 0.0163%. The outcomes of this study indicate that our model surpasses the previous state-of-the-art in free-text keystroke authentication. These findings contribute to advancing the field of keystroke authentication and offer practical implications for secure user verification systems.

Pouya Mehralian, Bagher BabaAli, Ashena Gorgan Mohammadi

Self-supervised learning offers an efficient way of extracting rich representations from various types of unlabeled data while avoiding the cost of annotating large-scale datasets. This is achievable by designing a pretext task to form pseudo labels with respect to the modality and domain of the data. Given the evolving applications of online handwritten texts, in this study, we propose the novel Part of Stroke Masking (POSM) as a pretext task for pretraining models to extract informative representations from the online handwriting of individuals in English and Chinese languages, along with two suggested pipelines for fine-tuning the pretrained models. To evaluate the quality of the extracted representations, we use both intrinsic and extrinsic evaluation methods. The pretrained models are fine-tuned to achieve state-of-the-art results in tasks such as writer identification, gender classification, and handedness classification, also highlighting the superiority of utilizing the pretrained models over the models trained from scratch.

Minoo Shayaninasab, Bagher Babaali

Due to the complex nature of human emotions and the diversity of emotion representation methods in humans, emotion recognition is a challenging field. In this research, three input modalities, namely text, audio (speech), and video, are employed to generate multimodal feature vectors. For generating features for each of these modalities, pre-trained Transformer models with fine-tuning are utilized. In each modality, a Transformer model is used with transfer learning to extract feature and emotional structure. These features are then fused together, and emotion recognition is performed using a classifier. To select an appropriate fusion method and classifier, various feature-level and decision-level fusion techniques have been experimented with, and ultimately, the best model, which combines feature-level fusion by concatenating feature vectors and classification using a Support Vector Machine on the IEMOCAP multimodal dataset, achieves an accuracy of 75.42%. Keywords: Multimodal Emotion Recognition, IEMOCAP, Self-Supervised Learning, Transfer Learning, Transformer.

Minoo Shayaninasab, Bagher Babaali

Given the significance of speech emotion recognition, numerous methods have been developed in recent years to create effective and efficient systems in this domain. One of these methods involves the use of pretrained transformers, fine-tuned to address this specific problem, resulting in high accuracy. Despite extensive discussions and global-scale efforts to enhance these systems, the application of this innovative and effective approach has received less attention in the context of Persian speech emotion recognition. In this article, we review the field of speech emotion recognition and its background, with an emphasis on the importance of employing transformers in this context. We present two models, one based on spectrograms and the other on the audio itself, fine-tuned using the shEMO dataset. These models significantly enhance the accuracy of previous systems, increasing it from approximately 65% to 80% on the mentioned dataset. Subsequently, to investigate the effect of multilinguality on the fine-tuning process, these same models are fine-tuned twice. First, they are fine-tuned using the English IEMOCAP dataset, and then they are fine-tuned with the Persian shEMO dataset. This results in an improved accuracy of 82% for the Persian emotion recognition system. Keywords: Persian Speech Emotion Recognition, shEMO, Self-Supervised Learning

S. Soroush Haj Zargarbashi, Bagher Babaali

Introduction: Alzheimer's disease is a type of dementia in which early diagnosis plays a major rule in the quality of treatment. Among new works in the diagnosis of Alzheimer's disease, there are many of them analyzing the voice stream acoustically, syntactically or both. The mostly used tools to perform these analysis usually include machine learning techniques. Objective: Designing an automatic machine learning based diagnosis system will help in the procedure of early detection. Also, systems, using noninvasive data are preferable. Methods: We used are classification system based on spoken language. We use three (statistical and neural) approaches to classify audio signals from spoken language into two classes of dementia and control. Result: This work designs a multi-modal feature embedding on the spoken language audio signal using three approaches; N-gram, i-vector, and x-vector. The evaluation of the system is done on the cookie picture description task from Pitt Corpus dementia bank with the accuracy of 83:6