scholarly journals Gender Recognition System Using Speech Signal

2012 ◽  
Vol 2 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Md. Sadek Ali
Keyword(s):  
Speech Signal ◽  
Recognition System ◽  
Gender Recognition

scholarly journals A rough set theory and deep learning based predictive system for gender recognition using audio speech

2021 ◽  
Author(s):  
Ghazaala Yasmin ◽  
ASIT KUMAR DAS ◽  
Janmenjoy Nayak ◽  
S Vimal ◽  
Soumi Dutta
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Set Theory ◽  
Rough Set ◽  
Gender Discrimination ◽  
Rough Set Theory ◽  
Recognition System ◽  
Gender Recognition ◽  
Learning Techniques

Abstract Speech is one of the most delicate medium through which gender of the speakers can easily be identified. Though the related research has shown very good progress in machine learning but recently, deep learning has imparted a very good research area to explore the deficiency of gender discrimination using traditional machine learning techniques. In deep learning techniques, the speech features are automatically generated by the reinforcement learning from the raw data which have more discriminating power than the human generated features. But in some practical situations like gender recognition, it is observed that combination of both types of features sometimes provides comparatively better performance. In the proposed work, we have initially extracted and selected some informative and precise acoustic features relevant to gender recognition using entropy based information theory and Rough Set Theory (RST). Next, the audio speech signals are directly fed into the deep neural network model consists of Convolution Neural Network (CNN) and Gated Recurrent Unit network (GRUN) for extracting features useful for gender recognition. The RST selects precise and informative features, CNN extracts the locally encoded important features, and GRUN reduces the vanishing gradient and exploding gradient problems. Finally, a hybrid gender recognition system is developed combining both generated feature vectors. The developed model has been tested with five bench mark and a simulated dataset to evaluate its performance and it is observed that combined feature vector provides more effective gender recognition system specially when transgender is considered as a gender type together with male and female.

scholarly journals Continuous kannada speech segmentation and speech recognition based on threshold using MFCC And VQ

2019 ◽  
Vol 9 (6) ◽  
pp. 4684
Author(s):  
Vanajakshi Puttaswamy Gowda ◽  
Mathivanan Murugavelu ◽  
Senthil Kumaran Thangamuthu
Keyword(s):  
Speech Recognition ◽  
Language Processing ◽  
Speech Signal ◽  
Recognition Rate ◽  
Recognition System ◽  
Training Data ◽  
Speech Segmentation ◽  
Significant Feature ◽  
Mel Frequency Cepstral Coefficients ◽  
Simple Method

<p><span>Continuous speech segmentation and its  recognition is playing important role in natural language processing. Continuous context based Kannada speech segmentation depends  on context, grammer and semantics rules present in the kannada language. The significant feature extraction of kannada speech signal  for recognition system is quite exciting for researchers. In this paper proposed method  is  divided into two parts. First part of the method is continuous kannada speech signal segmentation with respect to the context based is carried out  by computing  average short term energy and its spectral centroid coefficients of  the speech signal present in the specified window. The segmented outputs are completely  meaningful  segmentation  for different scenarios with less segmentation error. The second part of the method is speech recognition by extracting less number Mel frequency cepstral coefficients with less  number of codebooks  using vector quantization .In this recognition is completely based on threshold value.This threshold setting is a challenging task however the simple method is used to achieve better recognition rate.The experimental results shows more efficient  and effective segmentation    with high recognition rate for any continuous context based kannada speech signal with different accents for male and female than the existing methods and also used minimal feature dimensions for training data.</span></p>

An effective real time gender recognition system for smart cameras

2019 ◽  
Vol 11 (6) ◽  
pp. 2407-2419 ◽  
Author(s):  
Vincenzo Carletti ◽  
Antonio Greco ◽  
Alessia Saggese ◽  
Mario Vento
Keyword(s):  
Real Time ◽  
Recognition System ◽  
Gender Recognition ◽  
Smart Cameras

A Novel Hybrid Metaheuristic Approach to Perceive Gender Based Identification System

2020 ◽  
Vol 13 ◽  
Author(s):  
Aparna Shukla ◽  
Suvendu Kanungo
Keyword(s):  
Search Space ◽  
Recognition System ◽  
High Dimensional ◽  
Identification System ◽  
Hybridization Technique ◽  
Optimization Approach ◽  
Gender Recognition ◽  
Accuracy Rate ◽  
Tree Classifier ◽  
Gender Based

Background: Gender recognition is one of the most challenging perceptible tasks that receiving attention in the increasing digital data era as the requirement of personalized, reliable and ethical system inevitable. A problem that we address in this paper, greatly deals with the gender based identification system. We are motivated by this problem as many recent social interactions and existing services rely on the gender of an individual, and also in forensic identification, the gender information provides the feasibility for easy and quick investigation. Objective: The paper primarily focused on the gender based identification problem and culminate a robust gender based recognition system with the higher accuracy rate. We attempted to perceive the gender of an individual through the multimodal biometric system by integrating the three prominent biometric traits namely: fingerprint, palm-print and hand in a specific manner. The proposed multimodal biometric for gender recognition system provides a better accuracy rate improvement with the optimal feature set which are generated from available high dimensional features set. Method: Aiming for the objective to reduce the search space, a hybrid meta-heuristic approach GSA-Firefly (GFF) is introduced in this paper. The optimization approach GFF is proposed to retrieve the optimal number of features from the high dimensional features generated by fusing the texture features of all the three considered biometric traits along with the fingerprint minutiae features. Further, the decision tree classifier is used to classify the gender of an individual. Results: The feasibility of the proposed approach is measured with different qualitative performance parameters. In light of achieving the accuracy rate of 99.2%, it shows that its performance comparatively better against other techniques reported in the literature with the different sets of classier. Conclusion: The hybridization technique that effectively integrate meta-heuristic approaches GSA and firefly outperforms other similar approaches with respect to obtaining the optimal features of multimodal biometric for gender based identification system. Further, the novel technique enhance the overall performance of the system by reducing the search space over time and space.

Sign in / Sign up

Export Citation Format

Share Document