Unsupervised Speaker Adaptation Based On FVQ/HMM

ZHAO Li; ZOU Cai-rong; WU Zhen-yang

您当前的位置：

首页 >

文章列表页 >

Unsupervised Speaker Adaptation Based On FVQ/HMM

更新时间：2025-07-16

- Unsupervised Speaker Adaptation Based On FVQ/HMM
- Acta Electronica Sinica Vol. 30, Issue 7, Pages: 967-969(2002)
- 作者机构：
  
  东南大学无线电工程系,江苏,南京,210096
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.42
- Published Online：25 July 2002，
  
  Published：2002
- 稿件说明：
移动端阅览
ZHAO Li, ZOU Cai-rong, WU Zhen-yang. Unsupervised Speaker Adaptation Based On FVQ/HMM[J]. Acta Electronica Sinica, 2002, 30(7): 967-969.
DOI：

ZHAO Li, ZOU Cai-rong, WU Zhen-yang. Unsupervised Speaker Adaptation Based On FVQ/HMM[J]. Acta Electronica Sinica, 2002, 30(7): 967-969. DOI：

摘要

本文提出了一种新的语音识别方法

它综合了VQ、HMM和无教师说话人自适应算法的优点

在每个状态通过用矢量量化误差值取代传统HMM的输出概率值来建立FVQ/HMM

同时采用基于模糊矢量量化的无教师自适应算法

来改变FVQ/HMM的各状态的码字

从而实现对未知说话人的码本适应.本文通过非特定人汉语数码(孤立和连续数码)语音识别实验

把该新的组合方法同基于CHMM的自适应和识别方法进行了比较

实验结果表明该方法的自适应和识别效果优于基于CHMM的方法.

Abstract

We proposed a new speech recognition method by the integration of the VQ

HMM and an unsupervised speaker adaptation algorithm

it comply a VQ-distortion measure at each state instead of a output probability used by a traditional HMM

and uses an fuzzy adaptive VQ algorithm to alter the codewords for speaker adaptation.In this paper

the new combined method is compared with CHMM by the task of speaker-independent Chinese spoken digit (isolated/connected) recognition

and the results confirmed that the good performance of the new method and superior to traditional CHMM.

关键词

Keywords

references

Views

980

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An In-Vehicle Interaction Speech Enhancement and Recognition Method Based on Lightweight Models in Complex Environment

An End-to-End Chinese Speech Recognition Algorithm Integrating Language Model

Advanced Map Matching Algorithms: A Survey and Trends

Hardware Realization of Semiconductor Neurocomputer and Its Application to Continuous Speech Recognition

An Automatic Caption Generator for Mandarin Broadcast News

Related Author

LIAN Xiao-yu

XIA Nan

DAI Gao-le

YANG Hong-qin

LÜ Kun-ru

WU Chun-guo

LIANG Yan-chun

YUAN Yu-ping

Related Institution

School of Information Science and Engineering， Dalian Ploytechnic University

College of Computer Science and Technology， Jilin University

Ministry of Education Key Laboratory of Symbol Computation and Knowledge Engineering， Jilin University

School of Computer Science， Zhuhai College of Science and Technology

Computer and Software, Hangzhou Dianzi University

⁰