Low Resource Language Analysis Using Deep Learning Algorithm for Gender Classification

Voice signals are the essential input source for applications based on human and computer interaction technology. Gender identification through voice is one of most challenging tasks. For signal analysis, deep learning algorithms provide an alternative to traditional conventional classification. To identify gender female, male ‘first-time’ transgender, algorithm used improve robustness model with Mel Frequency Cepstrum Coefficients (MFCC) as a feature signals. This article presents accuracy help recorded live The samples third in Hindi language. These language transgender very low resources unavailable at any recognized sources. simulation results do not depend duration text independent. recurrent neural network – Bidirectional Long Short-term Memory (RNN BiLSTM) has been simulated outcome compared earlier reported literature. gender-wise average proposed achieved 91.44%, 94.94%, 96.11% males, females, respectively, using high comparison other genders. On hand, obtained 94.16%.