The 2006 RWTH parliamentary speeches transcription system
The 2006 RWTH parliamentary speeches transcription system
复制标题
2006年RWTH议会演讲转录系统
DOI：
10.21437/interspeech.2006-27
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
H. Ney
中科院分区：
文献类型：
--
作者：
J. Lööf;M. Bisani;Christian Gollan;G. Heigold;Björn Hoffmeister;Christian Plahl;R. Schlüter;H. Ney
在这项工作中，RWTH自动语音识别系统开发的第二TC-STAR评估活动2006年。该系统旨在转录欧洲议会全体会议（EPPS）的欧洲英语和西班牙语演讲以及西班牙议会的演讲。RWTH系统应用两遍搜索策略，其中四元组一遍解码器包括作为第一遍的快速声道长度归一化变体。该系统还包括几个适应和规范化方法，最小分类误差训练模型，贝叶斯风险最小化。对于所有相关的个别组成部分，对比结果是在EPPS西班牙语和英语数据。索引术语：语音识别，说话人标准化，VTLN
In this work, the RWTH automatic speech recognition systems developed for the second TC-STAR evaluation campaign 2006 are presented. The systems were designed to transcribe parliamentary speeches taken from the European Parliament Plenary Sessions (EPPS) in European English and Spanish, as well as speeches from the Spanish Parliament. The RWTH systems apply a two pass search strategy with a fourgram one-pass decoder including a fast vocal tract length normalization variant as first pass. The systems further include several adaptation and normalization methods, minimum classification error trained models, and bayes risk minimization. For all relevant individual components contrastive results are presented on the EPPS Spanish and English data. Index Terms: speech recognition, speaker normalisation, VTLN
影响因子：
4.3
作者：
LEGGETTER, CJ;WOODLAND, PC
通讯作者：
WOODLAND, PC