Parallel Training of Neural Networks for Speech Recognition

被引：0

作者：

Vesely, Karel ^{[1
]}

Burget, Lukas ^{[1
]}

Grezl, Frantisek ^{[1
]}

机构：

[1] Brno Univ Technol, Speech FIT, Brno 61266, Czech Republic

来源：

TEXT, SPEECH AND DIALOGUE | 2010年 / 6231卷

关键词：

neural network; phoneme classification; posterior features; backpropagation training; data parallelization;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The feed-forward multi-layer neural networks have significant importance in speech recognition. A new parallel-training tool TNet was designed and optimized for multiprocessor computers. The training acceleration rates are reported on a phoneme-state classification task.

引用

页码：439 / 446

页数：8