搜索资源列表
语音处理与识别
- 本书给出80个语音处理习题和4个语音处理程序，对相关人员有很大价值-the book is 80 speech processing and Exercise 4 speech processing procedures, the relevant personnel be of great value
10-2guard
- 程序名：Guard.c //该程序是特定人语音识别 //在程序中通过三条语句的训练演示特定人连续音识别，其中第一条语句为触发命令。 //在程序开始首先训练触发命令，然后提示训练两条命令，训练完毕开始语音识别。 //当识别出触发名称后，发布命令则会听到应答-procedures Name : Guard.c / / The procedure is a specific person voice recognition / / procedures adopted by the three ph
e34
- 这是用vc++编写的程序,在语音识别中经常用用到,是语音识别的第一步:time alignment. 分别用两种方式完成:1.非递归2.递归-This a vc++ program which is useful in voice recognizing and it is also the basic of the voice recognizing .I use two ways to accomplish it:1 nonrecursion 2.recursion
WAVE文件格式剖析
- WAVE文件作为多媒体中使用的声波文件格式之一，它是以RIFF格式为标准的。RIFF是英文Resource Interchange File Format的缩写，每个WAVE文件的头四个字节便是“RIFF”。WAVE文件由文件头和数据体两大部分组成。其中文件头又分为RIFF／WAV文件标识段和声音数据格式说明段两部分。WAVE文件各部分内容及格式见附表。-WAVE as a multimedia documents used in the acoustic format, it is based
JAVA的声音处理方法 (转自伊氏女人)-----淘特网
- 数字音频格式有很多种，其质量与采样频率和采样精度两个参数有关。频率的表示单位为赫兹〔Hz〕，它表示每秒采样次数。采样频率越高，音质就越好。采样精度为每次采样所存储的数据数量，它决定每个数字信号所能够表示的离散振幅的数量。存储每个样本的数据越多，音质就越好。但是高品质的声音需要占用大量的内存和磁盘空间。考虑到网络带宽，在Internet连接上传输就需要花费很长的时间。对于Applet来说，保证声音文件的最小化是极为重要的。-digital audio format there are many,
Hidden Markov Models for Speech Recognition-lect19
- HMM模型在语音识别中的应用，相信对HMM模型感兴趣的语音或图像等专业人员应该明白价值。-It is about Hidden Markov Models (HMM) method in Speech Recognition research. those interested in HMM or speech/image processing should know it s value.
pitchana
- 在语音中提取基音频率的程序。输入为.wav格式的语音文件，输出各帧基音频率。-This is a project of pitch extract of voice. When input is a wave file(.wav), the output will be the fundamental frequency of each frame.
Natural gradient ML or nonlinear decorrelation alg
- 极小边际熵等价于叉四阶累积量的平方和最小。通过迭代使四阶累积矩阵对角化，实现交叉四阶累积量的平方和的极小化。他是语音识别的重要预处理算法-minimum entropy equivalent to the marginal four bands fork cumulative amount of square and smallest. Through iterative four bands so that the cumulative matrix diagonalization, four
语音识别的前期研究
- 本课题为给语音识别系统提供语音信号端点检测的功能，对语音信号端点检测进行了探讨和研究,主要是侧重语音区间的端点检测...(附软件源码)-Voice Active Detection (VAD) is discussed in this project. Detection between speech section and speechless section and emphasized.(code available).
FIRDsgn
- 有限脉冲响应过滤器。This program designs a Finite Impulse Response (FIR) filter. The window-based method is used to obtain a low-pass, high-pass, band-pass or band-stop FIR filter-finite impulse response filters. This program designs a Finite Impulse Response
phoenix1.3.tar
- Phoenix is a speaker dependent (user trained) connected word recognition system. Phoenix is designed as a real-time recognition system in that recogniton takes place in parallel to utterance input and partial results are available before the en
recnet-1.3.tar
- recnet is a complete speech recognition system for the DARPA TIMIT and Resource Management tasks. It uses recurrent networks to estimate phone probabilities and Markov models to find the most probable sequence of phones or words.-recnet is a co
cb_Spectrum
- 用vc编的用于语音的频谱的检测，可以显示语音的频谱图。-It is used to detect spectral of speech and display the spectralgram.
snd_wave
- 用VC编的用于显示语音的波形图，可以将microphone中的语音波形显示促。是自动的显示程序。-VC series of the show for the wave of voice, the microphone to voice waveform display promoting. The show is automatic procedures.
real_time_audio_meter
- 用VC编的用于实时地对录音的轨迹的测试。可以自动显示-It is developed with VC.It can test the trail of speech at realtime and provide an auto display.
resmidi
- 用VC编的用于语音的录音和播放，可实时显示。-This software is developed with VC which is mainly used to record and play speech,furthermore,it can be displayed realtime.
is
- 语音质量客观评估，IS测度， Itakura-Saito (IS) Objective Speech Quality Measure-objective speech quality assessment, IS measure, Itakura - Saito (IS) Objective Speech Quality Measure
segSNR+IS
- 提供了segmantal SNR及IS的计算代码，用于语音增强后评价用。
MCI
- 一个简单实用的播放器，适用于常用格式的音频播放-This is the main application source file that contains the application class CWav3App.
read
- 语音识别系统能够朗读文本。主要是调用了win7的一个语音系统API。可以当做一个阅读器使用。-Speech recognition systems can read text. Is mainly a voice call system win7 API. Can be used as a reader.