A Study on Margin-Based Discriminative Training of Acoustic Models

碩士 === 國立臺灣師範大學 === 資訊工程研究所 === 98 === This thesis sets the goal at investigating the consistency properties underlying the most popular algorithms for discriminative training of acoustic models. Various margin- and boosting-based training data selection methods are also extensively explored in conj...

Full description

Bibliographic Details
Main Authors: Yueng-Tien Lo, 羅永典
Other Authors: Berlin Chen
Format: Others
Language:zh-TW
Published: 2010
Online Access:http://ndltd.ncl.edu.tw/handle/45277599585626688219