Multi-Pass Decoding Algorithm Based on a Speech Recognition Chip

ZHU Xuan; CHEN Yi-ning; LIU Jia; LIU Run-sheng

您当前的位置：

首页 >

文章列表页 >

Multi-Pass Decoding Algorithm Based on a Speech Recognition Chip

更新时间：2025-07-16

- Multi-Pass Decoding Algorithm Based on a Speech Recognition Chip
- Acta Electronica Sinica Vol. 32, Issue 1, Pages: 150-153(2004)
- 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： TN912.3
- Published：2004
- 稿件说明：
移动端阅览
ZHU Xuan, CHEN Yi-ning, LIU Jia, et al. Multi-Pass Decoding Algorithm Based on a Speech Recognition Chip[J]. Acta Electronica Sinica, 2004, 32(1): 150-153.
DOI：

ZHU Xuan, CHEN Yi-ning, LIU Jia, et al. Multi-Pass Decoding Algorithm Based on a Speech Recognition Chip[J]. Acta Electronica Sinica, 2004, 32(1): 150-153. DOI：

摘要

本文提出了一种新的用于片上的语音识别多级搜索算法.该算法以连续隐含马尔可夫模型(Continuous Density HMM

CDHMM)为基本识别框架.在保证识别率基本不变的前提下

大大降低了片内存储空间的占用量

减少了识别搜索时间.在第二级识别候选词条的选取准则上

提出一种基于置信度的选择方法

更进一步改善了识别速度

增强了识别的稳健性.在200个语音命令的识别任务下

系统的识别率为98.83％.而当识别词条增加到600条时

该算法也具有良好的识别性能.

Abstract

A novel multi-pass decoding algorithm is proposed to realize a CDHMM-based embedded speech recognition system.Compared with traditional Viterbi decoding algorithm

both the memory consumption and recognition time decreases significantly with little recognition accuracy's reduction at the same time.Furthermore

the confidence measure is adopted as the principle to determine the candidates in the second pass

which makes the recognition process more efficient.For the task of 200 voice commands

the accuracy rate achieves 98.83%.And then

its performance can still keep steadily while the scale of recognition vocabulary is up to 600 commands.

关键词

Keywords

references

Views

1203

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Efficient Implementation of National Security Algorithms SM2, SM3 and SM4 Based on RISC-V Instruction Extension Method

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

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

An Automatic Caption Generator for Mandarin Broadcast News

Related Author

WANG Ming-deng

YAN Ying-jian

GUO Peng-fei

ZHANG Fan

LIAN Xiao-yu

XIA Nan

DAI Gao-le

YANG Hong-qin

Related Institution

School of Cyber Science and Technology, Zhejiang University

School of Cryptography Engineering, Information Engineering University

School of Information Science and Engineering， Dalian Ploytechnic University

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

School of Computer Science， Zhuhai College of Science and Technology

⁰