Speech Recognition using Soft Decision Trees

被引：0

作者：

Ajmera, Jitendra ^{[1
]}

Akamine, Masami ^{[1
]}

机构：

[1] Toshiba Corp Res & Dev Ctr, Saiwai Ku, Kawasaki, Kanagawa 2128582, Japan

来源：

INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5 | 2008年

关键词：

speech recognition; decision trees; Gaussian mixture model (GMM); hidden Markov model (HMM);

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：

This paper presents recent developments at our site toward speech recognition using decision tree based acoustic models. Previously, robust decision trees have been shown to achieve better performance compared to standard Gaussian mixture model (GMM) acoustic models. This was achieved by converting hard questions (decisions) of a standard tree into soft questions using sigmoid function. In this paper, we report our work where soft-decision trees are trained from scratch. These soft-decision trees are shown to yield better speech recognition accuracy compared to standard GMM acoustic models on Aurora digit recognition task.

引用

页码：940 / 943

页数：4