Boosting Gaussian mixtures in an LVCSR system

Boosting Gaussian mixtures in an LVCSR system
复制标题

在 LVCSR 系统中增强高斯混合

DOI:
10.1109/icassp.2000.861945
复制
发表时间:
2000
期刊:
2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
影响因子:
--
通讯作者:
M. Padmanabhan
M. Padmanabhan
中科院分区:
--
文献类型:
--
作者:
G. Zweig;M. Padmanabhan

文献摘要

被引文献

相似文献

在本文中,我们将增强功能应用于帧级电话分类的问题,并使用结果系统执行语音邮件转录。我们开发了经典的Adaboost算法的平行,分层和受限版,这使得该技术能够用于大规模的语音识别任务中,具有成千上万的高斯和数千万培训框架。我们报告了框架识别精度和单词错误率的较小但一致的提高。
In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale speech recognition tasks with hundreds of thousands of Gaussians and tens of millions of training frames. We report small but consistent improvements in both frame recognition accuracy and word error rate.