Gender Recognition Research Articles

Gender Self-Identification: Opinions About Transgender Women from a National Online Survey in Taiwan

Gender self-identification (transgender) is not permitted in most Asian countries. In Taiwan, individuals recognized as transgender must meet requirements mandated by the Gender Recognition Act. Currently, lifting the requirement for proof of sex-reassignment surgery is pending. The aim of this study was to survey a large sample of Taiwanese to gain a better understanding of the general population’s attitudes toward gender self-identification. A self-report survey, entitled “Opinions of Gender Self-Identification,” collected demographic information and responses (agree = 1, disagree = 0) to 14 statements about transgender women and women’s safety, personal rights, and the law; one statement discussed rights of transgender men to give birth; total scores ranged from 0 to 14. The online survey was distributed to non-government organizations across Taiwan and the Taiwanese islands and was available between April 16 and 30, 2022. Most of the 10,158 respondents were female (77.4%); ages of respondents ranged from 15 to > 65 years. The mean total score was 0.95 ± 2.27, indicating respondents strongly disagreed with support for transgender females; 91.56% disagreed with all statements. Although there were significant differences in scores between parents and non-parents, and those ≤ 35 years versus ≥ 36 years (p < .01), all strongly disagreed with gender self-identification. Given the majority of respondents were females, survey findings should be regarded with caution. Public acceptance of gender self-identification requires support from its residents. Our findings suggest that gender self-identification has not begun to approach even a moderate level of public support among survey respondents.

An Approach to ECG-based Gender Recognition Using Random Forest Algorithm

An Approach to ECG-based Gender Recognition Using Random Forest Algorithm

Voice-based age, gender, and language recognition based on ResNet deep model and transfer learning in spectro-temporal domain

In personal identity recognition systems, detecting a person's age, gender, and language using voice signal characteristics is a crucial issue, especially because of the importance of security considerations. Age, gender, and language classification problems are important in signal processing because they are used to analyze and understand human behavior, interactions, and preferences. This can be especially useful in the fields of human-computer interaction, psychology, and social science research. In this paper, a new system for detecting a speaker's age, gender, and language based on deep learning models is presented. Deep learning models have shown great efficacy in various fields of signal processing. For this paper, a range of deep models were tested, including convolutional neural networks (CNNs), recurrent neural network (RNN), and a fine-tuning ResNet34 architecture. Additionally, techniques such as transfer learning were applied to improve the efficiency of the proposed system. The input voice signals are preprocessed by applying the spectro-temporal transform to obtain additional features that can be fed to the ResNet34 model, which is designed specifically for the task of voice signal processing. The dataset used in this paper was sourced from the Mozilla common voice initiative, which is dedicated to advancing speech recognition and language identification technologies. The performance of the proposed algorithm was evaluated in the presence of Gaussian noise to determine its robustness. The experimental results demonstrated that the proposed algorithm significantly outperformed basic algorithms and other deep neural networks in terms of age and gender recognition from voice signals.

UNFCCC: A Feminist Perspective

The United Nations Framework Convention on Climate Change (UNFCCC) was the only multilateral environmental agreement to emerge from the Earth Summit in 1992 which did not include any references to gender. Recognition of gender within the UNFCCC has been exceedingly slow and largely tokenistic with a focus on ensuring ‘gender balance’ within UNFCCC meetings and processes. This article explores the emergence of gender language within the UNFCCC by reflecting upon: where we have come from; where we are now; and where we are going with respect with gender. While there was very little progress in the early days of the UNFCCC, this article shows that from 2001 onwards there have been a series of small gains, which will be explained and critique. Much work remains to be done with this paper suggesting some concrete steps such as hosting a Gender COP, ensuring financing for National Climate Change Gender Focal Points and embedding gender meaningfully within existing climate finance processes. In recommending future actions, the paper draws on insights from the Pacific and Australian experience.

Climate institutions matter: The challenges of making gender-sensitive and inclusive climate policies

Climate institutions such as the United Nations Framework Convention on Climate Change (UNFCCC), with its expert panel the Intergovernmental Panel on Climate Change (IPCC), and the European Union, as well as national and local authorities in various sectors (such as transport, industry, energy, and agriculture), play a central role in developing and enacting climate strategies. Climate institutions, particularly in the Global North, have however been slow in their recognition of gender and other climate-relevant social aspects. With the help of feminist institutionalism, we analyze the contemporary climate regime and how it deals with gender and social differences, asking how climate institutions, originating in the Global North, organize bodies and institutionalize gender norms and relations. The main aim is to highlight existing institutional inertia and obstacles to transformative institutional practices that are needed for just and inclusive climate policies. The article is conceptual with examples drawn from institutional literature as well as empirical research on the United Nations, the European Union, and states in the Global North. We conclude that there is an increasing recognition of the gendered effects of climate change particularly in terms of the need for diverse representation in decision making. Institutional inertia, in particular path-dependent policy-making in climate institutions, however makes gender often invisible or associated with women only and therefore remains a major obstacle for the realization of inclusive and equal climate policies.

Identity, Gender, Age, and Emotion Recognition from Speaker Voice with Multi-task Deep Networks for Cognitive Robotics

This paper presents a study on the use of multi-task neural networks (MTNs) for voice-based soft biometrics recognition, e.g., gender, age, and emotion, in social robots. MTNs enable efficient analysis of audio signals for various tasks on low-power embedded devices, thus eliminating the need for cloud-based solutions that introduce network latency. However, the strict dataset requirements for training limit the potential of MTNs, which are commonly used to optimize a single reference problem. In this paper, we propose three MTN architectures with varying accuracy-complexity trade-offs for voice-based soft biometrics recognition. In addition, we adopt a learnable voice representation, that allows to adapt the specific cognitive robotics application to the environmental conditions. We evaluate the performance of these models on standard large-scale benchmarks, and our results show that the proposed architectures outperform baseline models for most individual tasks. Furthermore, one of our proposed models achieves state-of-the-art performance on three out of four of the considered benchmarks. The experimental results demonstrate that the proposed MTNs have the potential for being part of effective and efficient voice-based soft biometrics recognition in social robots.

Knowledge enhancement for speech emotion recognition via multi-level acoustic feature

Speech emotion recognition (SER) has become an increasingly attractive machine learning task for domain applications. It aims to improve the discriminative capacity of speech emotion utilising a certain type of features (e.g. MFCC, Spectrograms, Wav2vec2) or multi-type combination features. However, the potential of acoustic-related deep features is frequently overlooked in existing approaches that rely solely on a single type of feature or employ a basic combination of multiple feature types. To address this challenge, a multi-level acoustic feature cross-fusion approach is proposed, aiming to compensate for missing information between various features. It helps to enhance the SER performance by integrating different types of knowledge through the cross-fusion mechanism. Moreover, multi-task learning is utilised to share useful information through gender recognition, which can also obtain multiple common representations in a fine-grained space. Experimental results show that the fusion approach can capture the inner connections between multilevel acoustic features to refine the knowledge. The SOTA results were obtained under the same experimental conditions.

Gender, power and international (mis)recognition: Russia’s quest for epistemic agency through the ‘civilisational’ crusade against the rights of sexual and gender minorities

This article explores Russia’s quest for agential equality with the US through the lens of the gendered dynamics of international (mis)recognition. It draws on the constructivist scholarship that emphasises Moscow’s unfulfilled desire for parity with, and perceived misrecognition by, the West as one of the principal drivers of post-Soviet Russian foreign policy. However, the article moves beyond these analyses by bringing to the fore the centrality of gender in the Kremlin’s pursuit of recognition. It argues that Russia’s ‘civilisational’ crusade against universal human rights, especially the rights of sexual and gender minorities, should be understood as part of the broader struggle for recognition on Russia’s terms. Since misrecognition is associated with curtailed agency and lower status, it invokes associations with femininity, which Russian elites and society generally view as a humiliating act of emasculation. Moscow’s crusade against the rights of sexual and gender minorities has been explicitly predicated on gendered meanings, discourses and policies. This crusade has been intended as a bold, remasculinising campaign that would enable Russia to assert its epistemic agency in the realm of universal human rights and establish epistemic parity with the West. Importantly, Moscow’s struggle against perceived Western misrecognition comes at a cost to sexual and gender minorities in Russia: it amounts to structural, social and physical violence against these minorities, rendering them profoundly insecure.

Pedestrian detection and gender recognition utilizing YOLO and CNN algorithms

As crowd-based activities continue to surge in locales such as markets and restaurants, the significance of understanding pedestrian flow is increasingly evident. Over recent years, advancements in dynamic pedestrian detection, facilitated by the YOLO (You Only Look Once) algorithm, have seen widespread application in areas like crowd management and occupancy estimation. The YOLO algorithm has demonstrated high accuracy and efficiency in real-time object tracking and counting. However, for specific use cases, data derived solely from monitoring pedestrian flows may prove inadequate. This study presents YOLO-Gender, a system leveraging YOLO and Convolutional Neural Network (CNN) for pedestrian tracking and gender classification. The objective is to enhance the richness of data extracted from surveillance camera footage, thus rendering it more valuable for societal applications. The YOLO suite of algorithms, hailed for their superior performance and rapid iteration speed, is among the most extensively utilized tools in the field. The proposed system is predicated on YOLO v8, the most advanced iteration of the YOLO algorithm, released in 2023, which boasts its highest accuracy to date.

Information-theoretical analysis of the neural code for decoupled face representation.

Processing faces accurately and efficiently is a key capability of humans and other animals that engage in sophisticated social tasks. Recent studies reported a decoupled coding for faces in the primate inferotemporal cortex, with two separate neural populations coding for the geometric position of (texture-free) facial landmarks and for the image texture at fixed landmark positions, respectively. Here, we formally assess the efficiency of this decoupled coding by appealing to the information-theoretic notion of description length, which quantifies the amount of information that is saved when encoding novel facial images, with a given precision. We show that despite decoupled coding describes the facial images in terms of two sets of principal components (of landmark shape and image texture), it is more efficient (i.e., yields more information compression) than the encoding in terms of the image principal components only, which corresponds to the widely used eigenface method. The advantage of decoupled coding over eigenface coding increases with image resolution and is especially prominent when coding variants of training set images that only differ in facial expressions. Moreover, we demonstrate that decoupled coding entails better performance in three different tasks: the representation of facial images, the (daydream) sampling of novel facial images, and the recognition of facial identities and gender. In summary, our study provides a first principle perspective on the efficiency and accuracy of the decoupled coding of facial stimuli reported in the primate inferotemporal cortex.

Gender Identification of Chinese Mitten Crab Juveniles Based on Improved Faster R-CNN

The identification of gender in Chinese mitten crab juveniles is a critical prerequisite for the automatic classification of these crab juveniles. Aiming at the problem that crab juveniles are of different sizes and relatively small, with unclear male and female characteristics and complex background environment, an algorithm C-SwinFaster for identifying the gender of Chinese mitten crab juveniles based on improved Faster R-CNN was proposed. This algorithm introduces Swin Transformer as the backbone network and an improved Path Aggregation Feature Pyramid Network (PAFPN) in the neck to obtain multi-scale high-level semantic feature maps, thereby improving the gender recognition accuracy of Chinese mitten crab male and female juveniles. Then, a self-attention mechanism is introduced into the region of interest pooling network (ROI Pooling) to enhance the model’s attention to the classification features of male and female crab juveniles and reduce background interference on the detection results. Additionally, we introduce an improved non-maximum suppression algorithm, termed Softer-NMS. This algorithm refines the process of determining precise target candidate boxes by modulating the confidence level, thereby enhancing detection accuracy. Finally, the focal loss function is introduced to train the model, reducing the weight of simple samples during the training process, and allowing the model to focus more on samples that are difficult to distinguish. Experimental results demonstrate that the enhanced C-SwinFaster algorithm significantly improves the identification accuracy of male and female Chinese mitten crab juveniles. The mean average precision (mAP) of this algorithm reaches 98.45%, marking a 10.33 percentage point increase over the original model. This algorithm has a good effect on the gender recognition of Chinese mitten crab juveniles and can provide technical support for the automatic classification of Chinese mitten crab juveniles.

The Lawfulness of Gender Reassignment Surgery in UAE: Rights and Responsibilities

Countries in the Middle East and North Africa lack any legislative framework to allow legal gender recognition (LGR) for their transgender populations. This legislative vacuum has forced transgender people who wish to receive LGR to undergo a lengthy, costly, and complicated judicial review process. This research explores the legal landscape surrounding gender reassignment surgery within the United Arab Emirates (UAE) and investigates the rights and responsibilities of individuals seeking such procedures. The study came to clarify the legal aspect of the sex change operation and to distinguish it from others that are like it, such as the sex correction operation, and to indicate whether there is any criminal liability on the patient or the doctor for this act by legislation. The findings from this study aim to inform legal practitioners, policymakers, and advocacy groups, fostering a more inclusive legal environment that respects the diverse gender identities of individuals within the UAE.

Gender Recognition from Speech Signal Using CNN, KNN, SVM and RF

This study focuses on gender recognition from speech, and the gender classification performances of various machine learning methods such as support vector machines (SVM), k-nearest neighbor (KNN), convolutional neural network (CNN), and random forest (RF) are investigated. In the study, the Turkish subsection of the Common Voice dataset are used. From this data set, 3000 speech data are randomly selected with a homogeneous distribution according to age and gender, and 75% of the data is used in training the models and the remaining 25% is used in testing. The first 40 Mel Frequency Cepstral Coefficients (MFCC) obtained from each speech are averaged on the time axis and then applied as input to the classifiers. In the study, after parameter optimization is performed on the training data set for all models with the grid search method, performance evaluations are made on the test set using the optimum parameters. Experimental results show that in gender classification from speech, CNN is the most prominent classifier with 98.67% accuracy, followed by SVM with 97.33%, kNN with 96.8% and RF with 95.73%.

Thermal-based gender recognition using drones: advancing biometric recognition in challenging outdoor environments

While biometric recognition typically uses features such as face, fingerprint, and iris to identify individuals, this study focuses on utilising specific characteristics to identify gender. The aim of this article is to propose a procedure for gender recognition under specific conditions. The specific condition addressed is outdoor area monitoring, which presents challenges such as varying lighting conditions and limited camera placement options. To tackle this, a proposed procedure utilises thermal images captured by the drone equipped with a thermal camera. The advantage of thermal images is their independence from ambient light conditions. The captured images are resized and processed using convolutional neural networks (CNNs) (AlexNet, VGG-16, VGG-19) for feature extraction and binary classification. A freely available database of thermal face images is used for training the CNNs, while a own created dataset of thermal images obtained by the drone is used for testing. The findings indicate that the optimised CNNs achieve classification accuracies of 82.4% (VGG-16), 82.9% (AlexNet), and 85.5% (VGG-19). The original contribution of this study lies in demonstrating the suitability of face thermal images obtained through drones for gender recognition purposes.

Identifying key gait parameters in gender recognition and classification performance analysis using machine learning algorithms

Identifying key gait parameters in gender recognition and classification performance analysis using machine learning algorithms

Real-Time Convolutional Neural Networks for Emotion and Gender Classification

Emotion and gender recognition are important areas of research in the field of computer vision and human-computer interaction. The proposed CNN architecture is designed to extract features from facial images and classify them into six basic emotions (happy, sorrow, anger, fear, surprise, and disgust) and two genders (male and female) in real-time. To extract and categorize characteristics from facial photographs, the suggested CNN architecture consists of convolutional layers, pooling layers, and fully connected layers. The suggested system performs at the cutting edge for both emotion and gender recognition tasks when tested on publicly accessible datasets. The proposed real- time CNN architecture has potential applications in various fields, including social robotics, human-computer interaction, and affective computing.

Mel-Scale Frequency Extraction and Classification of Dialect-Speech Signals With 1D CNN Based Classifier for Gender and Region Recognition

Mel-Scale Frequency Extraction and Classification of Dialect-Speech Signals With 1D CNN Based Classifier for Gender and Region Recognition

Online Handwriting-Based Gender Recognition Using Statistical and Machine Learning Approaches

Online Handwriting-Based Gender Recognition Using Statistical and Machine Learning Approaches

성별 다양성에 대한 헌법적 접근

The term ‘third gender’ refers to a variety of gender identities that do not fit into the binary system of male and female, including transgender, non-binary, and genderqueer. This term signifies individuals whose gender identity differs from their biological sex, playing a significant role in social and legal recognition and policy. While legal approaches to gender have traditionally been based on binary gender norms, there is a growing legal framework recognizing the third gender. In 2017, the Federal Constitutional Court of Germany ruled that the legal requirement to register a person's gender as either male or female at birth does not fulfill the constitutional guarantee of equality irrespective of gender. Consequently, Germany established a legal avenue for registering a third gender. The Federal Constitutional Court recognized the connection between personal dignity and gender identity. It also acknowledged the substantial impact of gender on an individual's identity and social interactions. Such changes reflect the legal acknowledgment of social diversity and inclusiveness, contributing to enhanced recognition and understanding of the third gender. Our society also needs legislative efforts to adapt to the changing perceptions and recognition of gender beyond the binary thinking of male and female.

Age standardization and time-of-day performance for the Oldenburg Sentence Test (OLSA): results from the population-based Gutenberg Health Study

PurposeThe Oldenburg Sentence Test (OLSA) is a German matrix test designed to determine speech recognition thresholds (SRT). It is widely used for hearing-aids and cochlear implant fitting, but an age-adjusted standard is still lacking. In addition, knowing that the ability to concentrate is an important factor in OLSA performance, we hypothesized that OLSA performance would depend on the time of day it was administered. The aim of this study was to propose an age standardization for the OLSA and to determine its diurnal performance.MethodsThe Gutenberg Health Study is an ongoing population-based study and designed as a single-centre observational, prospective cohort study. Participants were interviewed about common otologic symptoms and tested with pure-tone audiometry and OLSA. Two groups—subjects with and without hearing loss—were established. The OLSA was performed in two runs. The SRT was evaluated for each participant. Results were characterized by age in 5-year cohorts, gender and speech recognition threshold (SRT). A time stamp with an hourly interval was also implemented.ResultsThe mean OLSA SRT was − 6.9 ± 1.0 dB (group 1 male) and − 7.1 ± 0.8 dB (group 1 female) showing an inverse relationship with age in the whole cohort, whereas a linear increase was observed in those without hearing loss. OLSA-SRT values increased more in males than in females with increasing age. No statistical significance was found for the diurnal performance.ConclusionsA study with 2900 evaluable Oldenburg Sentence Tests is a novelty and representative for the population of Mainz and its surroundings. We postulate an age- and gender-standardized scale for the evaluation of the OLSA. In fact, with an intergroup standard deviation (of about 1.5 dB) compared to the age dependence of 0.7 dB/10 years, this age normalization should be considered as clinically relevant.