Voice Based Age, Accent and Gender Recognition

( An International Open Access , Peer-reviewed, Refereed Journal )

IJIRTEXPLORE- Search Thousands of research papers

ISSN: 2349-6002 ESTD Year: 2014

UGC approved journal no 47859

Voice Based Age, Accent and Gender Recognition
Author(s):
Nithin Kumar B, Manoj K R, Nagendra N S, Deepa Angadi
Keywords:
Random Forest, K Nearest Neighbors, XGBoost, MFCC features.
Abstract
Gender, Age and Accent recognition that is solely achieved by human speech which is an interesting subject in the field of Automatic Speech Recognition systems. In this project, we have introduced a way of classifying a human’s speech into different classes of Gender, Age and Accent. The classification used in this project is mainly based on Machine Learning Models. The Models are systematically trained on the audio data that is obtained from Mozilla Common Voice. The dataset only contained the audio files with the respective labels associated with it. The noisy data from the dataset have been filtered out before it is fed into the Machine Learning models. In our project, we are using Mel Frequency Cepstral Coefficients (MFCC). We are extending Accent classification into American, European and Indian. But, in our project “Voice based Age, Accent and Gender Recognition” we have extended our work to the classification of speech into Gender, Age and Accent.
Article Details
Unique Paper ID: 152296 Publication Volume & Issue: Volume 8, Issue 2 Page(s): 841 - 845
Article Preview & Download

Share This Article

International conference on Management, Science, Technology, Engineering, Pharmact and Humanities.

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org