The speech recognition exercises in this paper are intended to identify the speeches having MFCC and GMM as a basis. As a practical biometric technique for phone applications, speech recognition offers a lot of promise and doesn’t require specialized or complex hardware. Signal processing is usually done in two stages: testing and training, to accomplish the objective of speech recognition. Speaker specific feature parameters are computed from the speech during the training phase. The characteristics are utilized to create statistical representations of various speakers. Speech samples from unidentified speakers are compared with the models and categorised throughout the testing phase. This study presents the development of an MFCC & GMM voice recognition algorithm. The well recognised Mel Frequency Cepstral coefficients, or {MFCCs}, have been employed as characteristics because of the documented changes in the crucial bandwidths of the human ear with frequency. We created a system model utilizing the GMM (Gaussian Mixture Model) in order to make the system realistic. With the help of the EM (Expectation Minimization) algorithm, GMM parameters are computed. MFCCs are computed throughout the testing and training stages. During a training session and a subsequent assessment session, speakers repeated distinct sentences. Speech can be falsely rejected or accepted up to a certain threshold. The location of this decision threshold is when the probabilities of the two errors are equal. The MATLAB environment was used to construct the codes.
Skip Nav Destination
,
,
,
Article navigation
10 October 2024
1ST INTERNATIONAL CONFERENCE ON DEEP LEARNING, IOT, DRONE TECHNOLOGY, SMART CITIES, AND APPLICATIONS
29–30 November 2023
Nashik, India
Research Article|
October 10 2024
Utilizing parametric models for real-time speaker recognition by stimulating frequency characteristics Available to Purchase
Ajay Kumar Mishra;
Ajay Kumar Mishra
a)
1
Department of Electronics & Telecommunication Engineering, Sandip Institute of Technology & Research Centre
, Sandip Foundation, Nashik, Maharashtra, India
-422213a)Corresponding author: [email protected]
Search for other works by this author on:
Ankur Saxena;
Ankur Saxena
b)
1
Department of Electronics & Telecommunication Engineering, Sandip Institute of Technology & Research Centre
, Sandip Foundation, Nashik, Maharashtra, India
-422213
Search for other works by this author on:
Sushant Janardhan Pawar;
Sushant Janardhan Pawar
c)
1
Department of Electronics & Telecommunication Engineering, Sandip Institute of Technology & Research Centre
, Sandip Foundation, Nashik, Maharashtra, India
-422213
Search for other works by this author on:
Bhagwat Kakde
Bhagwat Kakde
d)
1
Department of Electronics & Telecommunication Engineering, Sandip Institute of Technology & Research Centre
, Sandip Foundation, Nashik, Maharashtra, India
-422213
Search for other works by this author on:
Ajay Kumar Mishra
1,a)
Ankur Saxena
1,b)
Sushant Janardhan Pawar
1,c)
Bhagwat Kakde
1,d)
1
Department of Electronics & Telecommunication Engineering, Sandip Institute of Technology & Research Centre
, Sandip Foundation, Nashik, Maharashtra, India
-422213
a)Corresponding author: [email protected]
AIP Conf. Proc. 3156, 060002 (2024)
Citation
Ajay Kumar Mishra, Ankur Saxena, Sushant Janardhan Pawar, Bhagwat Kakde; Utilizing parametric models for real-time speaker recognition by stimulating frequency characteristics. AIP Conf. Proc. 10 October 2024; 3156 (1): 060002. https://doi.org/10.1063/5.0227649
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
15
Views
Citing articles via
The implementation of reflective assessment using Gibbs’ reflective cycle in assessing students’ writing skill
Lala Nurlatifah, Pupung Purnawarman, et al.
Effect of coupling agent type on the self-cleaning and anti-reflective behaviour of advance nanocoating for PV panels application
Taha Tareq Mohammed, Hadia Kadhim Judran, et al.
Design of a 100 MW solar power plant on wetland in Bangladesh
Apu Kowsar, Sumon Chandra Debnath, et al.
Related Content
Determination of SNR and SINAD for 8 bit ADC in time domain
AIP Conf. Proc. (October 2024)
Synthetic aperture radar image enhancement for object detection
AIP Conf. Proc. (October 2024)