Speaker Recognition Using GFCC and Deep Neural Networks

Speaker Recognition Using GFCC and Deep Neural Networks

sai santosh nooney

sai santosh nooney

Saint Petersburg, Florida

Artificial Intelligence

  • 0 Collaborators

  • 0 Followers

    Follow

Description

Extract GFCC features from 34 speaker's speech data

Train Deep Neural Network with text-independent and text-dependent speech data at various SNR levels and test to identify the speakers.

Speech data consists of both female and male voices of approximately 5000 sentences. SNR levels range from -6dB to +6dB and speech data are to be considered randomly among the data sets for randomness in the dataset.

Gallery

sai s. added photos to project Speaker Recognition Using GFCC and Deep Neural Networks

Medium 164f9b13 aa92 4286 9446 14685bccdc76

Speaker Recognition Using GFCC and Deep Neural Networks

Extract GFCC features from 34 speaker's speech data

Train Deep Neural Network with text-independent and text-dependent speech data at various SNR levels and test to identify the speakers.

Speech data consists of both female and male voices of approximately 5000 sentences. SNR levels range from -6dB to +6dB and speech data are to be considered randomly among the data sets for randomness in the dataset.

sai s. added photos to project Speaker Recognition Using GFCC and Deep Neural Networks

Medium 1f343919 4f47 40ca 8435 6d0a6be3828b

Speaker Recognition Using GFCC and Deep Neural Networks

Extract GFCC features from 34 speaker's speech data

Train Deep Neural Network with text-independent and text-dependent speech data at various SNR levels and test to identify the speakers.

Speech data consists of both female and male voices of approximately 5000 sentences. SNR levels range from -6dB to +6dB and speech data are to be considered randomly among the data sets for randomness in the dataset.

Default user avatar 57012e2942

sai s. created project Speaker Recognition Using GFCC and Deep Neural Networks

Medium 800ae5d6 01e6 4698 a210 f33316bbf694

Speaker Recognition Using GFCC and Deep Neural Networks

Extract GFCC features from 34 speaker's speech data

Train Deep Neural Network with text-independent and text-dependent speech data at various SNR levels and test to identify the speakers.

Speech data consists of both female and male voices of approximately 5000 sentences. SNR levels range from -6dB to +6dB and speech data are to be considered randomly among the data sets for randomness in the dataset.

No users to show at the moment.

No users to show at the moment.