搜索资源列表
SpeechSource
- speech file to be analyzed Format : binary file 16 bit-samples 240 samples per fr a me -speech file to be analyzed Format : 16 bit binary file-samples of 240 samples per fram e
CELP_Linux.tar
- Linux下的CELP语言编码，压缩语音质量极好。支持2K到32K的压缩。实现部分使用C语言编写。可用做Linux下的动态库，有例子。-under Linux CELP language coding, compression excellent speech quality. Support 2 K to 32 K compression. Part of the use of C language. Linux can be don
tdpsola
- 此算法是针对语音合成，采用时域的基音同步叠加算法，对波形进行韵律特征提取，修改，以及合成（包括短时能量分析，短时过零率分析等等算法）！算法是用matlab编写的-Speech synthesis, using time-domain synchronous Pitch stack algorithm, rhythm right waveform feature extraction, modification, and synthesi
speechtools
- 我是做语音识别的，这是我做的一个关于端点检测的小程序，里面还有一个工具包-I have to do speech recognition, which is what I am doing on a small endpoint detection procedures, there is also a tool kits
speakerrecognition
- 语音识别中的两种特征提取方法lpcc和mfcc，还有一个是文本无关的识别算法dtw，另外还有一个是预处理消噪部分的。共享一下，这些都是我调试过的，好用。-Speech Recognition two feature extraction methods and mfcc lpcc. There is a text-independent recognition algorithm dtw, in addition to a pretre
whd
- 本软件是一套完全基于神经网络的语音识别处理软件。 本软件为纯绿色软件，无须安装，解压到任意一个目录下，直接运行主程序 whd.exe ，卸载时删除所在目录即可，软件不会给系统留下任何垃圾，请放心试用，但为了您的数据安全，在使用时请先将重要数据保存备份，呵呵，我信不过微软啊:) 本软件使用的是本人自行开发的神经网络处理系统，但因工程浩大，且本人穷，只能独立编写，所以现在这个试用版所使用的神经网络系统并不完整，只实现了我最初设计
Sampling.and.Quantization
- Speech Quantization_Compare SNRs of speech cs5 with mu-law companding and uniform quantization -Speech Quantization_Compare remnants of spee ch cs5 with mu-law companding and uniform quant ization
FUNDAMENTAL
- 《FUNDAMENTALS OF SPEECH RECOGNITION（语音识别基本原理）》（英文），大家可以好好学习下-"FUNDAMENTALS OF SPEECH RECOGNITION (voice consensus other basic tenets) "(English), you can learn where
SAPI_Speech
- 采用Microsoft Speech SDK5.1实现Text2Speech。-Microsoft Speech SDK5.1 achieve Text2Speech.
FormantTracker(matlab)
- 检测语音信号的共振峰 ％ gender = gender_detector(X,Fs) ％ ％ This function will use a pitch detection algorithm to decide if the speaker is MALE(0) or FEMALE (1). ％ It is designed to work with short speech samples (up to or
Calculate_LPC
- LPC美尔倒谱特征的C源程序 这是我根据赵力那本“语音信号处理”后面的源代码写的LPC美尔倒谱特征的C源代码， 基本上没做什么修改，需要的朋友就可以不用自己再录入了。 程序调试通过，可以直接用。 -LPC Cepstrum C source code is under Zhao The "speech signal processing," the source generation behin
yuyin20061121
- 采用微软SPEECH SDK5.1开发的一个将SPR和TTS合在一起的语音识别程序，支持训练，但是训练特定词功能尚为完成，希望有同志能接着开发，并希望能将开发后的代码共享一下email:xxhhxx@163.com-SPEECH SDK5.1 using Microsoft development of the SPR and will be a combination of TTS voice identification proce
pitch_detect
- 语音信号的基音提取对于语音编码，识别都十分重要，该程序用于提取语音信号的基音-voice signal from the pitch for speech coding, identification is important, The procedure used to extract the speech signal Pitch
recognition1111
- 这是个说话人识别的源码，希望对大家在点和-This is a speech recognition source code, we hope that the right point and
speech_recognize(hmm)
- 工具：ultraedit32 说明：汇总了经典hmm各种算法源码及相关语音系统设计实现的代码。-tools : ultraedit32 : hmm summary of the various classical algorithm source code and related system design to achieve Speech codes.
ss.tar
- 另一个 谱减法去除语音噪声的c语言程序2。。。效果也还可以 。推荐大家下载。-remove noise c Speech Language Program 2. . . The results can also. Suggest you download.
POSTagger
- （1）从已经标注好词性的语料中统计得到词性标记的二元转移矩阵，以及每个词以确定的词性标记出现的次数等数据（训练阶段） （2）利用动态规划算法快速选取词性标记路径，得到词性标记结果 （3）可以选择不同的词性标记集 -(1) from the good part-of-speech tagging has been the Corpus statistics to be part of speech marking th
java_langdu_daima
- 一个用java编的语音合成软件 不许要微软的tts也能朗读-java with a series of the speech synthesis software not allowed to Microsoft can also read tts
VQ-DHMM
- 语音识别配套的VQ及DHMM模型训练程序，C语言，已经定点化，可直接移植到8位MCU或16位DSP中。与目前市面的语音识别玩具的算法基本一致，非常实用，仅供大家参考，别去抢人家饭碗才好。-speech recognition and matching VQ DHMM model training procedures, C language, has been positioned, can be directly transplant
itpp-3.10.9
- fastica 等算法的 C++实现 可以用于 mathematical, signal processing, speech processing, and communications -ICA C algorithm can be used in mathematical achievement. signal processing, speech processing, and communications