SPEECH RECOGNITION USING CONTINUOUS  MIXTURE DENSITY HIDDEN MARKOV MODELS

石洪波

您当前的位置：

首页 >

文章列表页 >

SPEECH RECOGNITION USING CONTINUOUS MIXTURE DENSITY HIDDEN MARKOV MODELS

更新时间：2026-09-14

- SPEECH RECOGNITION USING CONTINUOUS MIXTURE DENSITY HIDDEN MARKOV MODELS
- 采用连续混合密度隐马尔柯夫模型的语音识别
- Issue 4, (1997)
- 作者机构：
  
  山西经济管理学院
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：1997
- 稿件说明：
移动端阅览
石洪波. SPEECH RECOGNITION USING CONTINUOUS MIXTURE DENSITY HIDDEN MARKOV MODELS[J]. 1997, (4).
DOI：

石洪波. SPEECH RECOGNITION USING CONTINUOUS MIXTURE DENSITY HIDDEN MARKOV MODELS[J]. 1997, (4). DOI：

摘要

介绍了采用连续Ｍ元高斯混合密度的隐式马尔柯夫模型的语音识别实验系统，对语音特征矢量用非线性归一化算法进行预处理．另外，还提出一种基于语音知识的模型初始化方法．实验证明：语音的预处理和模型初始化方法都取得了较明显的效果．

Abstract

This paper discusses a speech recognition system using the continuous mixture density Hidden Markov Model. We use a nonlinear programming method to proceed time warping about feature vector. Moreover

we present a method based on speech knowledge to initialize model.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Configuration Design and Research of a Hybrid Quadruped Perilla Sowing Robot

Study on the Removal of CO2 in Confined Space by High⁃Gravity Enhanced Potassium Hydroxide Coupled Potassium Glycinate Solution

Adaptive Shock Wave Overpressure Sensing for Dynamic Explosion Testing

PEG⁃Like Polymers Based on Low Molecular Weight PEI as Gene Vectors

Adaptive DFT Channel Estimation Algorithm Based on Joint Delay and SNR Estimation in OFDM System

Related Author

No data

Related Institution

No data

⁰