公开(公告)号：WO2014029099A1

公开(公告)日：2014-02-27

申请号：PCT/CN2012/080527

申请日：2012-08-24

Applicant: MICROSOFT CORPORATION ,  HUO, Qiang ,  YAN, Zhijie ,  ZHANG, Yu ,  XU, Jian

Inventor： HUO, Qiang ,  YAN, Zhijie ,  ZHANG, Yu ,  XU, Jian

IPC: G10L15/14 ,  G10L15/22 ,  G10L15/06

CPC classification number: G10L15/063 ,  G10L15/14 ,  G10L2015/0631

Abstract: Methods and systems for i-vector based clustering training data in speech recognition are described. An i-vector may be extracted from a speech segment of a speech training data to represent acoustic information. The extracted i-vectors from the speech training data may be clustered into multiple clusters using a hierarchical divisive clustering algorithm. Using a cluster of the multiple clusters, an acoustic model may be trained. This trained acoustic model may be used in speech recognition.

Abstract translation: 描述了基于i矢量的聚类训练数据在语音识别中的方法和系统。 可以从语音训练数据的语音段中提取i向量以表示声学信息。 来自语音训练数据的提取的i向量可以使用分级分割聚类算法聚类成多个聚类。 使用多个群集的群集，可以训练一个声学模型。 该训练的声学模型可用于语音识别。

公开(公告)号：WO2014137760A2

公开(公告)日：2014-09-12

申请号：PCT/US2014/019147

申请日：2014-02-27

Applicant: MICROSOFT CORPORATION

Inventor： LI, Jinyu ,  YAN, Zhijie ,  HUO, Qiang ,  GONG, Yifan

IPC: G10L15/22

CPC classification number: G10L15/14 ,  G10L15/10

Abstract: A high-dimensional posterior-based feature with partial distance elimination may be utilized for speech recognition. The log likelihood values of a large number of Gaussians are needed to generate the high-dimensional posterior feature. Gaussians with very small log likelihoods are associated with zero posterior values. Log likelihoods for Gaussians for a speech frame may be evaluated with a partial distance elimination method. If the partial distance of a Gaussian is already too small, the Gaussian will have a zero posterior value. The partial distance may be calculated by sequentially adding individual dimensions in a group of dimensions. The partial distance elimination occurs when less than all of the dimensions in the group are sequentially added.

Abstract translation: 具有部分距离消除的高维后验特征可用于语音识别。 需要大量高斯的对数似然值来产生高维后验特征。 具有非常小的对数似然性的高斯与零后验值相关联。 用于语音帧的高斯的对数可能性可以用部分距离消除方法来评估。 如果高斯的部分距离已经太小，则高斯将具有零后验值。 可以通过在一组维度中依次添加个体维度来计算部分距离。 当小于组中的所有维度被顺序地添加时，发生部分距离消除。