搜索资源列表
newpnn
- 基于GMM的概率神经网络PNN具有良好的泛化能力,快速的学习能力,易于在线更新,并具有统计学的贝叶斯估计理论基础,已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点,还具有许多GMM没有的优点,如强鲁棒性,需要更少的训练语料,可以和其他网络其他理论无缝整合等。-GMM based probabilistic neural network PNN good generalization ability, the
mfcc 计算语音信号的MFCC系数的代码
- 语音识别中,计算语音信号的MFCC系数的代码,要求输入的语音信号为.PCM格式-Speech recognition, speech signal MFCC coefficients calculated the code, requiring the input voice signal. PCM format
HTK-3.4.1.tar.gz
- 语音识别,Speech Recognition Speech Recognition Speech Recognition Speech Recognition software-only
YuyinShiyan
- 使用voicebox进行说话人识别,初步介绍如何用GMM(Gaussian Mixture Model)的方法来进行说话人辨识(Speaker Identification),并在Matlab下,尝试通过调整参数来提高得分-For speaker recognition using the voicebox, initially describes how to use GMM (Gaussian Mixture Model) approach to speaker recognition (S
demo_WINCE_6.0_TTS
- 使用TTS进行语音合成和语音识别。里面有生成的exe,可直接进行测试-Use TTS speech synthesis and speech recognition. Generated exe can be directly tested
dtmf
- 单音多频信号的产生和识别,采用FFT变换。应用于电话拨号。是学习数字信号处理的大作业。-Tone multi-frequency signal generation and recognition, the use of FFT transform. Applies to telephone dial-up. Digital Signal Processing is the study of large operations.
DTMF
- WAV格式的DTMF的音源,其中有对DTMF的介绍和应用。做DTMF识别的时候应该要用到。-DTMF WAV format audio source, including the introduction and application of DTMF. DTMF recognition should be made to use the time to.
voidetest
- 基于神经网络的语言情感识别系统,可以识别人讲话时是喜,怒,高兴还是平静,具有较高的识别率。-The language of emotion recognition system based on neural network can recognize human speech is happy, angry, happy or calm, has a high recognition rate.
20040716delOffice
- Agent一词的中文意思是“代理”,故名思意,这类代理软件的主要作用是提供一种 易于理解和使用的操作界面,接受用户的指令、代替用户完成某些复杂繁琐的工作、或为用户 提供帮助。科学研究表明:从人机工程的角度考虑,赋予电脑或程序更多人性化色彩,如支持 语音合成输出信息、语音识别输入指令、智能提示、动画等,能够充分提高人机交互的有效性 和易用性。-Agent-term Chinese means " agent" , hence the name implies, th
dtw
- 语音识别,dtw算法,matlab程序 语音识别,dtw算法,matlab程序-Speech recognition, dtw algorithm, matlab program speech recognition, dtw algorithm, matlab program
nengliang
- 自己写的语音识别系统, 自己写的语音识别系统,-Write their own speech recognition system, write your own speech recognition system,
MFCC
- 语音识别,语音特征提取。 语音识别,语音特征提取-Speech recognition, speech feature extraction. Speech recognition, speech feature extraction
dtw
- 基于matlab的语音识别系统,主要是DTW 语音识别模式-Matlab-based speech recognition system, mainly DTW speech recognition mode
dial-recog
- matlab环境下实现拨号号码语音识别。-matlab dial number speech recognition.
yuyinquzaoyuanshi_1
- 语音信号的识别,去噪,处理,简单的应用matlab中的一些去噪函数,选择最优函数-Recognition of speech signals, noise, handling, simple application of some denoising matlab function, selecting the optimal function
yuyinshibie
- 语音识别过程详解-Detailed speech recognition process
voice-recognition-program
- 改程序是博创公司生产的博创机器人的语音识别程序,改程序是用VC编程,-Reform program is produced by Borch Borch robot voice recognition program, change the program with VC programming,
1111
- 通过求取均值来得到的语音压缩源代码,希望对语音的同学有所帮助-this is the source code of Voice Compression , it is wise to help students who learn Speech Recognition
voice
- 语音识别芯片资料 产品介绍 应用于消费类电子产品上的交互式语音集成芯片(RSC-100/164T,RSC-300/364,RSC4XX)是一种高性能、低成本的8位MCU,所有这类芯片内部集成有ADC、DAC、ROM(除了RSC-100/300)、RAM和麦克风的预放大电路,并拥有以下多种功能:与说话者无关/有关的语音识别、语音确认(PASSWORD)、语音和音乐合成,录音和回放、快速数字拨号(只有RSC-300/364)、持续监听。 产品线有两种通用目的的微处理器(RSC系列)
speech-recognition
- speech recognition full project with source code-speech recognition full project with source code..