Abstract | ||
---|---|---|
Gaussian mixture model (GMM) has been widely used for modeling speakers. In speaker identification, one major problem is how to generate a set of GMMs for identification purposes based upon the training data. Due to the hill-climbing characteristic of the maximum likelihood (ML) method, any arbitrary estimate of the initial model parameters will usually lead to a sub-optimal model in practice. To resolve this problem, this paper proposes a hybrid training method based on genetic algorithm (GA). It utilizes the global searching capability of GA and combines the effectiveness of the ML method. Experimental results based on TI46 and TIMIT showed that this hybrid GA could obtain more optimized GMMs and better results than the simple GA and the traditional ML method. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1016/j.engappai.2004.08.035 | Eng. Appl. of AI |
Keywords | Field | DocType |
ml method,sub-optimal model,identification purpose,gaussian mixture model,initial model parameter,simple ga,hybrid training method,major problem,speaker recognition,traditional ml method,genetic classification method,hybrid ga,maximum likelihood,hill climbing,genetics,genetic algorithm | Training set,TIMIT,Speaker identification,Pattern recognition,Computer science,Maximum likelihood,Speech recognition,Speaker recognition,Artificial intelligence,Mixture model,Machine learning,Genetic algorithm | Journal |
Volume | Issue | ISSN |
18 | 1 | Engineering Applications of Artificial Intelligence |
Citations | PageRank | References |
12 | 0.74 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Q. Y. Hong | 1 | 50 | 15.79 |
Sam Kwong | 2 | 4590 | 315.78 |