On the determination of epsilon during discriminative GMM training

Autor:	Michel Alves Lacerda, Jussara Ribeiro, Shi-Huang Chen, Leonardo Mendes Souza, Rodrigo Capobianco Guido, Luciene Cavalcanti Rodrigues, Sylvio Barbon Junior, Lucimar Sasso Vieira, João Paulo Lemos Escola, Paulo Ricardo Franchi Zulato
Přispěvatelé:	Guido, R. C., Chen, S. -H., Barbon Junior, S, Souza, L. M., Vieira, L. S., Rodrigues, L. C., Escola, J. P. L., Zulato, P. R. F., Lacerda, M. A., Ribeiro, J.
Rok vydání:	2010
Předmět:	Iterative method business.industry Computer science Pattern recognition Markov model Mixture model Speech processing Speaker recognition symbols.namesake Discriminative model Computer Science::Sound symbols Artificial intelligence Gradient descent business Gaussian process
Zdroj:	ISM
Popis:	Discriminative training of Gaussian Mixture Models (GMMs) for speech or speaker recognition purposes is usually based on the gradient descent method, in which the iteration step-size, epsilon, uses to be defined experimentally. In this letter, we derive an equation to adaptively determine epsilon, by showing that the second-order Newton-Raphson iterative method to find roots of equations is equivalent to the gradient descent algorithm.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8879da397f7d054c2c5bde8a4a76a28b https://hdl.handle.net/11368/3004528 Zobrazit plný text záznamu