A RBF  Gamma  HMM Combined Model for Continuous Speech Recognition

Li Yijun

您当前的位置：

首页 >

文章列表页 >

A RBF Gamma HMM Combined Model for Continuous Speech Recognition

更新时间：2025-12-08

- A RBF Gamma HMM Combined Model for Continuous Speech Recognition
- Acta Electronica Sinica Issue 9, Pages: 81-85(1999)
- 作者机构：
  
  1. 北京大学计算机科学技术研究所栅格图象研究室,北京,100871
  2. 哈尔滨工业大学计算机系,哈尔滨,150001
  3. 北京大学计算机科学技术研究所栅格图象研究室!北京100871哈尔滨工业大学计算机系,哈尔滨,150001
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.34
- Published：1999
- 稿件说明：
移动端阅览
[1]李易军,徐近霈,吴枫.用于连续语音识别的RBF-Gamma-HMM组合模型[J].电子学报,1999(09):81-85.

Li Yijun. A RBF Gamma HMM Combined Model for Continuous Speech Recognition[J]. Acta Electronica Sinica, 1999, (9): 81-85.
[1]李易军,徐近霈,吴枫.用于连续语音识别的RBF-Gamma-HMM组合模型[J].电子学报,1999(09):81-85. DOI：

Li Yijun. A RBF Gamma HMM Combined Model for Continuous Speech Recognition[J]. Acta Electronica Sinica, 1999, (9): 81-85. DOI：

摘要

本文提供了一个有特色的、易扩展的多模块ＲＢＦ Ｇａｍｍａ神经网与ＨＭＭ组合的连续语音识别模型，兼有ＲＢＦ网表达音元空间、Ｇａｍｍａ网综合时序相关信息、ＨＭＭ作音元时间集成和扩展等功能，以实现功能互补．以本模型为基础，将本文提出的各种改进分类性能的学习算法用于特定人连续数字语音识别，其字正识率达到９８９％，串正识率达到９４８％．

Abstract

A continuous speech recognition model integrated by multi module RBF Gamma neural networks and HMMs is proposed in this paper.In this model

the abilities of RBF Gamma nets that effectively represent the space of speech units and synthesize the temporal correlation information of speech sequence are combined with the abilities of HMMs that integrate and expand the speech units in time domain.They are mutually complementary in function and improve the recognition accuracy obviously.A speaker dependent continuous digits recognition system is realized according to this model and using the learning algorithms proposed in this paper for improving classification performance.The tested digit accuracy is 98.9% and the string accuracy is 94.8%.

关键词

Keywords

references

Views

105

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

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

Regionalized Decision Algorithm for Human-Machine Shared Control Based on Gaussian Hidden Markov Model

Research on Time-Serial Location Data Publication Based on Local Differential Privacy

Advance in Multiscale Geometric Analysis Image Hidden Markov Tree Model

Interpolation Adaptation Algorithm Based on Gaussian Similarity Analysis

Related Author

Lin Daofa

Luo Wanbo & Yang Jiayuan

杨家沅

LIU Yang

SU Wei-xing

ZHU Tian-he

LIU Fang

KANG Hai-yan

Related Institution

四川大学计算中心成都 610064

Centre of Computing Technology, Sichuan University

Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, Tiangong University

BBT-E-6 Complete Vehicle, BMW Brilliance Automotive Ltd.

School of Information Management, Beijing Information Science and Technology University

⁰