语音识别

连续语音识别系统中的OnePass搜索方法

One Pass Search Algorithm in Contnuous Speech Recognition System

基于DSP的语音识别系统及其结构

A Speech Recognition System and Structure Based on the DSP

孩子们在使用苹果Siri和亚马逊Alexa等智能语音识别装置来播放儿歌或询问这样的问题：“月亮有多大？”

Voice-recognition gadgets1 such as Apple 's Siri and Amazon 's Alexa are being used by children to play nursery rhymes or ask questions such as " how big is the moon ? "

小词表实时语音识别系统的定点DSP实现

Fixed Point DSP Application of A Small Glossary Real Time Speech Recognition System

利用DSP的电话网语音识别技术的应用研究

The application research of telephone speech recognition by DSP

基于MCE/GPD的语音识别及其一种Robust应用中初始参数的选择

Speech Recognition Based on MCE / GPD and Selections of initial Parameters in a Robust Application

基于SoC的孤立词语音识别算法的C语言仿真

Simulation Based on C Language of Algorithms of Isolated Word Speech Recognition for System on Chip

该设计已经应用于以OpenRISC为核心的语音识别SoC设计平台上。

The design has been applied in a speech recognition SoC .

小波网络和RBF网络的抗噪语音识别

Noise-robust speech recognition based on wavelet network and RBF network

SONAR可同时支持说话人识别与语音识别。

SONAR both supports Automatic Speaker Recognition and Automatic Speech Recognition .

基于BDIAgent技术的情感机器人语音识别技术研究

Research of Affective Robot Based on BDI Agent

采用上下文相关音素HMM的连续语音识别

Continuous Speech Recognition Based on the Context-Dependent Phonetic HMM

文章构造了基于经典HMM模型的汉语连续语音识别系统。

A baseline system based on classical HMM is implemented in this paper .

基于数据模拟和HMM自适应的电话语音识别研究

A Study on Telephone Speech Recognition Based on Data Simulation and HMM Adaptation

端点自由DP应用于语音识别中的时间轴校正

Free-regions DP used for time alignment on speech recognition

第五章阐述了本文所建立的基于HMM建模的蒙古语连续语音识别系统的框架及其实现以及蒙语语音识别应用技术研究。

In Chapter five , I introduce a Mongolian speech recognition system basing on HMM.

基于分段模糊c－均值的连续密度HMM语音识别模型参数估计

The segmental fuzzy c-means algorithm for estimating parameters of continuous density hidden Markov models

汉语语音识别的平滑声韵基元HMM算法

Smoothed-unit HMM Algorithm in Mandarin Speech Recognition

基于连续高斯混合密度HMM的汉语全音节语音识别研究

A study of speech recognition of complete Chinese syllables based on continuous Gaussian Mixture HMM

本文建立了一个孤立词语音识别系统，并利用MATLAB的语音工具箱voicebox对系统进行了仿真和分析。

This article has established an isolated-word speech recognition system , and has carried on the simulation and analysis using MATLAB pronunciation toolbox voice box to the system .

论文针对强噪音环境提出一种PZT振动拾音器作为语音识别的前端输入。

A noise-free PZT sensor is made as speech signal input equipment to an auto speech recognition system .

万事达（MasterCard）正在试用被称为“自拍付”（selfiepay）的面部识别以及语音识别。

MasterCard is trialling facial recognition - dubbed " selfie pay " - and voice recognition .

用于语音识别中的SOFM矢量量化方法

A Method of SOFM as a Vector Quantizer in Speech Recognition

而本实例的成功开发，更进一步说明了SALT技术在语音识别应用中的巨大优势。

The success development of this instance improve that we have gone still one step further to state the enormous advantage in phonetic recognition by the use of SALT technology .

语音识别中结合进化计算的MMI训练方法

Evolutionary Computation - based MMI Training in Speech Recognition

论述了语音识别的算法DTW，讲解其具体的实现过程及特点。

The DTW algorithm of speech recognition is discussed in this paper .

用DP（动态编程）匹配算法实现语音识别，简单且能快速响应。

In this paper , we introduce a DP ( Dynamic Programming ) matching algorithm for speech recognition .

基于FPGA，针对孤立词语音识别算法，提出了完整的设计流程、设计方案和测试方案，并对每个模块的结构进行了详细说明。

The complete design flow , design scheme and test scheme based on FPGA for isolated-word speech recognition are given together with detailed specifications of every module .

在PⅡ350微机上的实际运行表明，无论是有监督的连续语音识别，还是文稿理解或数据文件分析，其结果都与人脑的判别一致。

The tests run on a P II 350 personal computers shows that the judgment results of continuous speech recognition with reference , text understanding and data file analysis are the same as the human brain .

近年来在大词汇连续语音识别的研究取得了长足的进步，隐马尔柯夫模型（HMM）是连续语音识别的核心部分。

Recently-peat progress has been made in the field of Large Vocabulary Continuous Speech Recognition , and HMM stands the kernel .