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...
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 |
Similar Items
-
Investigating Acoustic Modeling and Semi-supervised Discriminative Training for Speech Recognition
by: Lo, Tien-Hong, et al.
Published: (2019) -
Training Data Selection for Discriminative Training of Acoustic Models
by: Fang-Hui, Chu, et al.
Published: (2008) -
Discriminative training of acoustic models in a segment-based speech recognizer
by: Sandness, Eric D. (Eric David), 1979-
Published: (2014) -
Evaluation of Combinational Use of Discriminant Analysis-Based Acoustic Feature Transformation and Discriminative Training
by: TAKEDA, Kazuya, et al.
Published: (2010) -
Discriminative training of acoustic models for mispronunciation detection and diagnosis of non-native English
Published: (2015)