Speech emotion recognition (SER) in naturalistic conditions presents a significant challenge for the speech processing community. Challenges include disagreement in labeling among annotators and imbalanced data distributions. This paper presents a reproducible framework that achieves superior (top 1) performance in the Emotion Recognition in Naturalistic Conditions Challenge (IS25-SER Challenge) - Task 2, evaluated on the MSP-Podcast dataset. Our system is designed to tackle the aforementioned challenges through multimodal learning, multi-task learning, and imbalanced data handling. Specifically, our best system is trained by adding text embeddings, predicting gender, and including ``Other'' (O) and ``No Agreement'' (X) samples in the training set. Our system's results secured both first and second places in the IS25-SER Challenge, and the top performance was achieved by a simple two-system ensemble.

Automated Face Recognition Systems (FRSs), developed using deep learning models, are deployed worldwide for identity verification and facial attribute analysis. The performance of these models is determined by a complex interdependence among the model architecture, optimization/loss function and datasets. Although FRSs have surpassed human-level accuracy, they continue to be disparate against certain demographics. Due to the ubiquity of applications, it is extremely important to understand the impact of the three components -- model architecture, loss function and face image dataset on the accuracy-disparity trade-off to design better, unbiased platforms. In this work, we perform an in-depth analysis of three FRSs for the task of gender prediction, with various architectural modifications resulting in ten deep-learning models coupled with four loss functions and benchmark them on seven face datasets across 266 evaluation configurations. Our results show that all three components have an individual as well as a combined impact on both accuracy and disparity. We identify that datasets have an inherent property that causes them to perform similarly across models, independent of the choice of loss functions. Moreover, the choice of dataset determines the model's perceived bias -- the same model reports bias in opposite directions for three gender-balanced datasets of ``in-the-wild'' face images of popular individuals. Studying the facial embeddings shows that the models are unable to generalize a uniform definition of what constitutes a ``female face'' as opposed to a ``male face'', due to dataset diversity. We provide recommendations to model developers on using our study as a blueprint for model development and subsequent deployment.

Author profiling, the analysis of texts to uncover attributes such as gender and age of the author, has become essential with the widespread use of social media platforms. This paper focuses on author profiling in the Bangla language, aiming to extract valuable insights about anonymous authors based on their writing style on social media. The primary objective is to introduce and benchmark the performance of machine learning approaches on a newly created Bangla Author Profiling dataset, BN-AuthProf. The dataset comprises 30,131 social media posts from 300 authors, labeled by their age and gender. Authors' identities and sensitive information were anonymized to ensure privacy. Various classical machine learning and deep learning techniques were employed to evaluate the dataset. For gender classification, the best accuracy achieved was 80% using Support Vector Machine (SVM), while a Multinomial Naive Bayes (MNB) classifier achieved the best F1 score of 0.756. For age classification, MNB attained a maximum accuracy score of 91% with an F1 score of 0.905. This research highlights the effectiveness of machine learning in gender and age classification for Bangla author profiling, with practical implications spanning marketing, security, forensic linguistics, education, and criminal investigations, considering privacy and biases.

Name-based gender prediction has traditionally categorized individuals as either female or male based on their names, using a binary classification system. That binary approach can be problematic in the cases of gender-neutral names that do not align with any one gender, among other reasons. Relying solely on binary gender categories without recognizing gender-neutral names can reduce the inclusiveness of gender prediction tasks. We introduce an additional gender category, i.e., "neutral", to study and address potential gender biases in Large Language Models (LLMs). We evaluate the performance of several foundational and large language models in predicting gender based on first names only. Additionally, we investigate the impact of adding birth years to enhance the accuracy of gender prediction, accounting for shifting associations between names and genders over time. Our findings indicate that most LLMs identify male and female names with high accuracy (over 80%) but struggle with gender-neutral names (under 40%), and the accuracy of gender prediction is higher for English-based first names than non-English names. The experimental results show that incorporating the birth year does not improve the overall accuracy of gender prediction, especially for names with evolving gender associations. We recommend using caution when applying LLMs for gender identification in downstream tasks, particularly when dealing with non-binary gender labels.

Most works on gender bias focus on intrinsic bias -- removing traces of information about a protected group from the model's internal representation. However, these works are often disconnected from the impact of such debiasing on downstream applications, which is the main motivation for debiasing in the first place. In this work, we systematically test how methods for intrinsic debiasing affect neural machine translation models, by measuring the extrinsic bias of such systems under different design choices. We highlight three challenges and mismatches between the debiasing techniques and their end-goal usage, including the choice of embeddings to debias, the mismatch between words and sub-word tokens debiasing, and the effect on different target languages. We find that these considerations have a significant impact on downstream performance and the success of debiasing.

Age and gender recognition in the wild is a highly challenging task: apart from the variability of conditions, pose complexities, and varying image quality, there are cases where the face is partially or completely occluded. We present MiVOLO (Multi Input VOLO), a straightforward approach for age and gender estimation using the latest vision transformer. Our method integrates both tasks into a unified dual input/output model, leveraging not only facial information but also person image data. This improves the generalization ability of our model and enables it to deliver satisfactory results even when the face is not visible in the image. To evaluate our proposed model, we conduct experiments on four popular benchmarks and achieve state-of-the-art performance, while demonstrating real-time processing capabilities. Additionally, we introduce a novel benchmark based on images from the Open Images Dataset. The ground truth annotations for this benchmark have been meticulously generated by human annotators, resulting in high accuracy answers due to the smart aggregation of votes. Furthermore, we compare our model's age recognition performance with human-level accuracy and demonstrate that it significantly outperforms humans across a majority of age ranges. Finally, we grant public access to our models, along with the code for validation and inference. In addition, we provide extra annotations for used datasets and introduce our new benchmark.

Flexible laryngoscopy is commonly performed by otolaryngologists to detect laryngeal diseases and to recognize potentially malignant lesions. Recently, researchers have introduced machine learning techniques to facilitate automated diagnosis using laryngeal images and achieved promising results. Diagnostic performance can be improved when patients' demographic information is incorporated into models. However, manual entry of patient data is time consuming for clinicians. In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve detector model performance. The overall accuracy for gender, smoking history, and age was 85.5%, 65.2%, and 75.9%, respectively. We also created a new laryngoscopic image set for machine learning study and benchmarked the performance of 8 classical deep learning models based on CNNs and Transformers. The results can be integrated into current learning models to improve their performance by incorporating the patient's demographic information.

Deep learning techniques have gained a lot of traction in the field of NLP research. The aim of this paper is to predict the age and gender of an individual by inspecting their written text. We propose a supervised BERT-based classification technique in order to predict the age and gender of bloggers. The dataset used contains 681284 rows of data, with the information of the blogger's age, gender, and text of the blog written by them. We compare our algorithm to previous works in the same domain and achieve a better accuracy and F1 score. The accuracy reported for the prediction of age group was 84.2%, while the accuracy for the prediction of gender was 86.32%. This study relies on the raw capabilities of BERT to predict the classes of textual data efficiently. This paper shows promising capability in predicting the demographics of the author with high accuracy and can have wide applicability across multiple domains.

We present the Radar de Parité, an automated Natural Language Processing (NLP) system that measures the proportion of women and men quoted daily in six Canadian French-language media outlets. We outline the system's architecture and detail the challenges we overcame to address French-specific issues, in particular regarding coreference resolution, a new contribution to the NLP literature on French. Our results highlight the underrepresentation of women in news stories, while also illustrating the application of modern NLP methods to measure gender representation and address societal issues. The commonality in most applied NLP research projects is the need to reliably and scalably extract information from unstructured text data. In this paper, we describe one such application: extracting quotes from news stories to quantify gender representation. Gender representation in the media is a long debated topic. From the 1970s, there have been studies into how much women and gender-diverse people are portrayed in news stories, with the general hypothesis that they tend to be underrepresented [1, 2]. There is also research studying how they are represented, i.e., whether sexist or homophobic tropes are present when we discuss women and gender-diverse people [3, 4]. In this work, we tackle one specific aspect of representation: who is quoted and in what proportions. Our starting hypothesis is that we hear less from women than from men in news stories, that is, that men are quoted more often than is to be expected from their proportion in the general population. To fully answer this question, we formulate a quantitative approach, collecting large amounts of representative data and extracting quotes from the unstructured text. This is the goal of the Radar de Parité. We define quotes as either direct or indirect reproductions of what a person said, and we define that person as a source in news articles. In order to extract quotes, we employ a full NLP pipeline, focusing on parsing to identify speakers, verbs, and quotes, in each news story. We then predict the gender of the speaker (or source), using external genderprediction services.

With significant advances in deep learning, many computer vision applications have reached the inflection point. However, these deep learning models need large amount of labeled data for model training and optimum parameter estimation. Limited labeled data for model training results in over-fitting and impacts their generalization performance. However, the collection and annotation of large amount of data is a very time consuming and expensive operation. Further, due to privacy and security concerns, the large amount of labeled data could not be collected for certain applications such as those involving medical field. Self-training, Co-training, and Self-ensemble methods are three types of semi-supervised learning methods that can be used to exploit unlabeled data. In this paper, we propose self-ensemble based deep learning model that along with limited labeled data, harness unlabeled data for improving the generalization performance. We evaluated the proposed self-ensemble based deep-learning model for soft-biometric gender and age classification. Experimental evaluation on CelebA and VISOB datasets suggest gender classification accuracy of 94.46% and 81.00%, respectively, using only 1000 labeled samples and remaining 199k samples as unlabeled samples for CelebA dataset and similarly,1000 labeled samples with remaining 107k samples as unlabeled samples for VISOB dataset. Comparative evaluation suggest that there is $5.74\%$ and $8.47\%$ improvement in the accuracy of the self-ensemble model when compared with supervised model trained on the entire CelebA and VISOB dataset, respectively. We also evaluated the proposed learning method for age-group prediction on Adience dataset and it outperformed the baseline supervised deep-learning learning model with a better exact accuracy of 55.55 $\pm$ 4.28 which is 3.92% more than the baseline.