Accuracy Comparison using Different Modeling Techniques under Limited Speech Data of Speaker Recognition Systems

Satyanand Singh; Ajeet Singh

Accuracy Comparison using Different Modeling Techniques under Limited Speech Data of Speaker Recognition Systems

Satyanand Singh * §

Contact

Ajeet Singh

Contact

§ JNTU Hyderabad

Accuracy Comparison using Different Modeling Techniques under Limited Speech Data of Speaker Recognition Systems

Article Fingerprint

ReserarchID

O066S

Accuracy Comparison using Different Modeling Techniques under Limited Speech Data of Speaker Recognition Systems Banner

Key Research Insights

Synthesized scholarly intelligence & interactive research assistant

This converted HTML version may contain rendering inconsistencies. Please refer to the PDF for the authoritative version, or click here to provide feedback.

Abstract

Pointing towards programmed machine learning by human, a technique for speaker recognition with speaker identity in light of man machine interface is an interest of science. Motivated by the same, we propose a philosophy to recognize speakers. Inside of our investigation, obtaining speech signal, analysis of spectrogram, neutralization, extraction of speaker specific features for recognition, mapping of speech using Novel Vector Quantization (NFVQ) is presented. NFVQ is particularly suitable for colossal arrangement of information and yield discourse mapping. Furthermore Speaker Recognition by utilizing NFVQ Model additionally will be exhibited in this paper. During feature extraction, traditional triangular shaped bins have been replaced by Gaussian shaped filter (GF) and Tukey filter (TF) to calculate Mel Frequency Cepstral Coefficients (MFCC). This work performs an experimental evaluation of three simple modelling techniques namely, Fuzzy c-means, FVQ2 and NFVQ. Among these NFVQ shows significant improved performance compared to Fuzzy c-means and FVQ2. For about 10 s of training and testing speech data of speakers the efficiency for NFVQ, FVQ2 and Fuzzy c-means are 98.8%, 73.33, and 8, respectively, for a set of 630 speakers taken from the TIMIT database. We additionally got 5% outright EER change for both-sex trials on the 10 s-10 s condition contrasted with the FVQ2 approach. Index-terms: gaussian filter, triangular filter, tukey filter, subbands, MFCC, vector quantization, novel fuzzy vector quantization.

References

2 Cites in Article

Reference Format

1. P. Premakanthan,W. Mikhael (2001). Speaker verification/recognition and the importance of selective feature extraction. Circuits and Systems Proceedings of the 44th IEEE. Vol. 1. Midwest Symposium, 1, 57-61.
CrossRef DOI
2. Ji Ming,Timothy Hazen,James Glass,Douglas Reynolds (2007). Robust Speaker Recognition in Noisy Conditions. IEEE Transactions on Audio, Speech and Language Processing, 15(5), 1711-1723.
CrossRef DOI

Download References

Funding

No external funding was declared for this work.

Conflict of Interest

The authors declare no conflict of interest.

Ethical Approval

No ethics committee approval was required for this article type.

Data Availability

Not applicable for this article.

How to Cite This Article

Satyanand Singh, Ajeet Singh. 2016. "Accuracy Comparison using Different Modeling Techniques under Limited Speech Data of Speaker Recognition Systems". Global Journal of Science Frontier Research - F: Mathematics & Decision GJSFR-F Volume 16 (GJSFR Volume 16 Issue 9 (F2)).

More Citation Formats

Select Citation Style:

Download Citation

GJSFR Volume 16 Issue 9 (F2)

Explore Journals Explore Volume Read This Issue

Journal Specifications

Crossref Journal DOI 10.17406/GJSFR

Print ISSN 0975-5896

e-ISSN 2249-4626

Keywords

Not Found

Classification

GJSFR-F Classification MSC 2010: 97N80

Submission ReceivedFebruary 21, 2016
Peer Review Double Blind
Handling Editor
Accepted March 17, 2016
Published March 28, 2016

Version of record

v1.2

Issue date

March 28, 2016

Language

English

Order Article Reprint

Experience in AR

Explore published articles in an immersive Augmented Reality environment. Our platform converts research papers into interactive 3D books, allowing readers to view and interact with content using AR and VR compatible devices.

View in VR

Read in 3D

Your published article is automatically converted into a realistic 3D book. Flip through pages and read research papers in a more engaging and interactive format.

View in 3D

Article Matrices

Total Score: 102

Country: India

Subject: Global Journal of Science Frontier Research - F: Mathematics & Decision

Authors: Satyanand Singh, Ajeet Singh (PhD/Dr. count: 0)

View Count (all-time): 308

Total Views (Real + Logic): 1275

Total Downloads (simulated): 55

Publish Date: 2016 03, Tue

Monthly Totals (Real + Logic):

Month 1: 38 views
Month 2: 33 views
Month 3: 38 views
Month 4: 44 views
Month 5: 66 views
Month 6: 42 views
Month 7: 18 views
Month 8: 42 views
Month 9: 47 views
Month 10: 41 views
Month 11: 38 views
Month 12: 37 views
Month 13: 32 views
Month 14: 28 views
Month 15: 33 views
Month 16: 33 views
Month 17: 19 views
Month 18: 21 views
Month 19: 44 views
Month 20: 33 views
Month 21: 31 views
Month 22: 36 views
Month 23: 40 views
Month 24: 33 views
Month 25: 35 views
Month 26: 35 views
Month 27: 31 views
Month 28: 15 views
Month 29: 31 views
Month 30: 44 views
Month 31: 46 views
Month 32: 34 views
Month 33: 33 views
Month 34: 34 views
Month 35: 35 views
Month 36: 26 views
Month 37: 19 views
Month 38: 20 views
Month 39: 41 views
Month 40: 18 views
Month 41: 40 views
Month 42: 31 views
Month 43: 25 views
Month 44: 21 views
Month 45: 27 views
Month 46: 28 views
Month 47: 33 views
Month 48: 21 views
Month 49: 46 views
Month 50: 35 views
Month 51: 15 views
Month 52: 44 views
Month 53: 35 views
Month 54: 42 views
Month 55: 30 views
Month 56: 22 views
Month 57: 28 views
Month 58: 25 views
Month 59: 29 views
Month 60: 24 views
Month 61: 31 views
Month 62: 38 views
Month 63: 36 views
Month 64: 43 views
Month 65: 44 views
Month 66: 36 views
Month 67: 39 views
Month 68: 47 views
Month 69: 31 views
Month 70: 26 views
Month 71: 36 views
Month 72: 37 views
Month 73: 24 views
Month 74: 26 views
Month 75: 35 views
Month 76: 36 views
Month 77: 14 views
Month 78: 33 views
Month 79: 48 views
Month 80: 29 views
Month 81: 28 views
Month 82: 34 views
Month 83: 41 views
Month 84: 39 views
Month 85: 36 views
Month 86: 35 views
Month 87: 13 views
Month 88: 39 views
Month 89: 31 views
Month 90: 32 views
Month 91: 13 views
Month 92: 36 views
Month 93: 37 views
Month 94: 29 views
Month 95: 39 views
Month 96: 12 views
Month 97: 18 views
Month 98: 28 views
Month 99: 38 views
Month 100: 41 views
Month 101: 35 views
Month 102: 18 views
Month 103: 25 views
Month 104: 35 views
Month 105: 35 views
Month 106: 22 views
Month 107: 39 views
Month 108: 14 views
Month 109: 14 views
Month 110: 28 views
Month 111: 12 views
Month 112: 32 views
Month 113: 49 views
Month 114: 29 views
Month 115: 54 views
Month 116: 33 views
Month 117: 22 views
Month 118: 34 views
Month 119: 32 views
Month 120: 49 views
Month 121: 34 views
Month 122: 41 views
Month 123: 34 views
Month 124: 27 views
Month 125: 61 views
Month 126: 57 views
Month 127: 52 views
Month 128: 25 views

Total Views: 1.3K

Total Downloads: 55

All Trends