Research on Polynomial-Fitting Speech-Trajectory Model in Chinese Continuous Speech Recognition

OU Zhi-jian; WANG Zuo-ying

您当前的位置：

首页 >

文章列表页 >

Research on Polynomial-Fitting Speech-Trajectory Model in Chinese Continuous Speech Recognition

更新时间：2025-07-16

- Research on Polynomial-Fitting Speech-Trajectory Model in Chinese Continuous Speech Recognition
- Acta Electronica Sinica Vol. 31, Issue 4, Pages: 608-611(2003)
- 作者机构：
  
  清华大学电子工程系,北京,100084
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.34
- Published：2003
- 稿件说明：
移动端阅览
OU Zhi-jian, WANG Zuo-ying. Research on Polynomial-Fitting Speech-Trajectory Model in Chinese Continuous Speech Recognition[J]. Acta Electronica Sinica, 2003, 31(4): 608-611.
DOI：

OU Zhi-jian, WANG Zuo-ying. Research on Polynomial-Fitting Speech-Trajectory Model in Chinese Continuous Speech Recognition[J]. Acta Electronica Sinica, 2003, 31(4): 608-611. DOI：

摘要

尽管作为当前最为流行的语音识别模型

HMM由于采用状态输出独立同分布假设

忽略了对语音轨迹动态特性的描述.本文基于一个更为灵活的语音描述统计框架—广义DDBHMM

提出了一个具体的多项式拟合语音轨迹模型

以及新的训练和识别算法

更好地刻划了真实的语音特性.本文还给出了一种有效的剪枝算法

得到一个实用化模型.汉语大词汇量非特定人连续语音识别的实验表明

这种剪枝的多项式拟合语音轨迹模型以较少的计算量明显改善了识别系统的性能.

Abstract

Although as the most popular model for speech recognition

HMM takes no account of the dynamics of the speech trajectory

since it assumes the outputs of a state to be independent and identically distributed.In this paper

based on a more flexible statistical framework for speech description-the generalized DDBHMM

a particular polynomial-fitting speech-trajectory model is proposed with new algorithms for training and recognition.It describes the real characteristics of speech more reasonably.With the effective path-pruning algorithm additionally proposed

it becomes a practicable model.Experiments on Chinese large-vocabulary speaker-independent continuous speech recognition showed that with this path-pruned polynomial-fitting speech-trajectory model

the recognition performance is improved distinctively at relatively low computational cost.

关键词

Keywords

references

Views

769

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

From Linear Prediction HMM to a New Combined Model for Speech Recognition

Interpolation Adaptation Algorithm Based on Gaussian Similarity Analysis

Research of Lung Cancer Recognition Based on Chest CT Images

Speaker-dependent Medium Vocabulary Continuous Speech Recognition Based on HMM and VQ

Related Author

WANG Zuo-ying

OU Zhi-jian

LU Da-jin

WANG Zuo-ying

LV Ping

HE Wei

JIANG Hui-yan

CAO Wen-ming

Related Institution

School of Software,Northeastern University

Research Institute of Intelligent Information SystemZhejiang University of TechnologyHangzhouZhejiang 310014China

Lab of Artificial Neural NetworksInstitute of SemiconductorsCASBeijing 100083China

Research Institute of Intelligent Information System,Zhejiang University of Technology

Lab of Artificial Neural Networks,Institute of Semiconductors,CAS

⁰