Automatic gender identification system for Bengali speech

Rahman, Sheik S.; Kabir, Fasihul; Huda, Mohammad Nurul

doi:10.1109/eict.2015.7392013

Cited by 4 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ershad's seizure of power in 1982 had effectively caused the BNP to lose control of the government but it also provided an opportunity for the Awami league to enter into a coalition with him. When Awami league broke their promise to oppose election in 1986, almost all other parties including the BNP boycotted them (Rahman, 2015). This distance between supporting elites affected the flow of the movement.…”

Section: Elite Politicsmentioning

confidence: 99%

Reevaluating the Underlying Factors of 1990’s Mass Uprising against Authoritarian Regime in Bangladesh: An Analysis in the Light of Causal Model of Internal Conflict

Rahman¹

2023

ARSS

View full text Add to dashboard Cite

From the early beginning of the authoritarian government of Ershad, there was widespread opposition to his autocratic authority, which persisted for eight years before the 1990 rebellion brought an end to it. Like the majority of movements in Bangladesh, this one was started by students who put in heroic effort to see it through to a victorious finish. This was an urban-centric movement. With the aid of an established academic model of internal conflict, this study aims to investigate the revolt and support its underlying causes - particularly its socioeconomic and cultural causes - as well as its political causes. This study has been conducted by qualitative method, in which the information has been collected from secondary sources. As the analytical framework, this study uses Michael E. Brown’s internal conflict causal model. According to this analysis, the major structural causes that led to the uprising were communal violence, a weakened educational system, corruption, and paramilitary activity on the part of the government. In terms of political factors, this study points to the authority’s use of torture or other oppressive measures against people’s fundamental rights, the state’s non-secular policy, the scope of political opportunity, public support and sympathy for the students, the authority’s political error, and the coordinated actions of political elites as being important causes of the uprising. Economic and social factors contributing to the rebellion include the rising cost of living, the debt crisis, regular failure to meet growth targets, and a highly divisive and bourgeois-centric economic system. Once more, this study reveals that the government’s actions against national culture through various policies, the extreme application of military culture, people’s negative memories of the Pakistani era’s authoritarian regime, and the positive perception of the student community in society are the cultural and perceptual factors that led to the uprising. The findings of the study will give relevant academicians, decision-makers, and the general public essential knowledge about Bangladeshi history as well as the fundamental causes of internal strife. They might contrast these conclusions with some important recent occurrences in Bangladesh. They may use it to address the fundamental issues in various facets of our society. As a result, the research may help them identify likely and long-lasting remedies for the advancement of our civilization.

show abstract

Section: Elite Politicsmentioning

confidence: 99%

Reevaluating the Underlying Factors of 1990’s Mass Uprising against Authoritarian Regime in Bangladesh: An Analysis in the Light of Causal Model of Internal Conflict

Rahman¹

2023

ARSS

View full text Add to dashboard Cite

show abstract

Gender Classification in Bangla Language Using Deep Learning-Based Voice Analysis

Labib,

Monsur,

Shuvo

et al. 2023

2023 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)

View full text Add to dashboard Cite

Gender classification of running subjects using full-body kinematics

2016

View full text Add to dashboard Cite

This paper proposes novel automated gender classification of subjects while engaged in running activity. The machine learning techniques include preprocessing steps using principal component analysis followed by classification with linear discriminant analysis, and nonlinear support vector machines, and decision-stump with AdaBoost. The dataset consists of 49 subjects (25 males, 24 females, 2 trials each) all equipped with approximately 80 retroreflective markers. The trials are reflective of the subject's entire body moving unrestrained through a capture volume at a self-selected running speed, thus producing highly realistic data. The classification accuracy using leave-one-out cross validation for the 49 subjects is improved from 66.33% using linear discriminant analysis to 86.74% using the nonlinear support vector machine. Results are further improved to 87.76% by means of implementing a nonlinear decision stump with AdaBoost classifier. The experimental findings suggest that the linear classification approaches are inadequate in classifying gender for a large dataset with subjects running in a moderately uninhibited environment.

show abstract

Automatic gender identification system for Bengali speech

Cited by 4 publications

References 24 publications

Reevaluating the Underlying Factors of 1990’s Mass Uprising against Authoritarian Regime in Bangladesh: An Analysis in the Light of Causal Model of Internal Conflict

Reevaluating the Underlying Factors of 1990’s Mass Uprising against Authoritarian Regime in Bangladesh: An Analysis in the Light of Causal Model of Internal Conflict

Gender Classification in Bangla Language Using Deep Learning-Based Voice Analysis

Gender classification of running subjects using full-body kinematics

Contact Info

Product

Resources

About