| Autor: |
Reddy, K. Subba, Preethi, J. Chandu, Swapna, B., Vyshnavi, M. Sushma, Reddy, M. Madhu Mohan, Charan, K. Sree Sai |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2023, Vol. 2821 Issue 1, p1-6, 6p |
| Abstrakt: |
Nowadays, INTERNET-OF-THINGS (IoT) expedients are increasing rapidly in number to all aspects of our lives. An essential role of IoT devices that it can be used for speaker authenticated systems with the idea of speaker identification system. The Speaker Identification can be made by using the combination of K-means Clustering and Gaussian Mixture Model Scoring (GMM After using this combination, the results are very expressive for the small datasets. For the large datasets, the time complexity is more, and the memory usage is also more at the time of clustering. To overcome this problem, we came across the advanced clustering techniques such as, Mini-batch K-means Clustering & Gaussian Mixture Model Scoring (GMM), Spherical K-means Clustering & Gaussian Mixture Model Scoring (GMM). By using the above hybrid techniques of K-means clustering, the time complexity for clustering the large datasets will be reduced, and the memory usage of those datasets is minimum. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
