Gender Recognition Inclusive with Transgender from Speech Classification

Automatic gender classification system has prompted a pertinent of increasing amount of applications, particularly the rise of social platforms and criminal investigation. Focus of substantial past researches was limited towards the discrimination of male and female gender only. Recently transgender has achieved legal recognition. So, any gender classification system should consider this third gender also. But unfortunately there is a lack of good gender classification system which can discriminate all the three types of gender well. This proposed work uses judiciously chosen acoustic features for classification of three classes of genders from their solo voice. The proposed system has been pursued with the sampled audio data extracted from audio signal. From the sampled data, acoustic features like tempo, pitch and spectral flux have been extracted using the idea of pattern recognition. The extracted feature set has been served for classification to predict the gender of a given unknown voice.

[1]  Oksam Chae,et al.  Gender Classification Using Local Directional Pattern (LDP) , 2010, 2010 20th International Conference on Pattern Recognition.

[2]  Petri Toiviainen,et al.  A Matlab Toolbox for Music Information Retrieval , 2007, GfKl.

[3]  Shariful Islam,et al.  GENDER RECOGNITION SYSTEM USING SPEECH SIGNAL , 2012 .

[4]  Birger Kollmeier,et al.  Robust speech detection in real acoustic backgrounds with perceptually motivated features , 2011, Speech Commun..

[5]  Arijit Ghosal,et al.  Automatic male-female voice discrimination , 2014, 2014 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT).

[6]  Joan Claudi Socoró,et al.  A Review of Physical and Perceptual Feature Extraction Techniques for Speech, Music and Environmental Sounds , 2016 .

[7]  Naveen Kumar,et al.  Robust Multichannel Gender Classification from Speech in Movie Audio , 2016, INTERSPEECH.

[8]  Gaurav Aggarwal,et al.  Speech Feature Extraction for Gender Recognition , 2016 .

[9]  Shrikanth S. Narayanan,et al.  An Overview on Perceptually Motivated Audio Indexing and Classification , 2013, Proceedings of the IEEE.

[10]  Shweta Srivastava,et al.  Weka: A Tool for Data preprocessing, Classification, Ensemble, Clustering and Association Rule Mining , 2014 .

[11]  Peter Grosche,et al.  Extracting Predominant Local Pulse Information From Music Recordings , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[12]  Meinard Müller,et al.  Chroma Toolbox: Matlab Implementations for Extracting Variants of Chroma-Based Audio Features , 2011, ISMIR.

[13]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[14]  Liming Chen,et al.  Gender identification using a general audio classifier , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).