搜索资源列表
10-1snoopy
- 该程序是非特定人语音识别程序,原来在SPCE500A下运行,能识别并应答16个命令,存储空间为128K字节。 //我们将其进行了修改,使其能在SPCE061A下运行,由于存储空间为32K字,只能识别并应答9个命令。 //在这个例程当中,我们示范了如何使用语音识别引擎对8个已经经过训练的命令进行识别。 //第一个命令 \"Snoopy\",可以作为使能命令,也就是说使用者只能在该命令之后发出其他命令。 //例如,用户只有在发出 \"Snoopy\"命令并且听到响应\"Snoopy here\"之后
telephoneSearch
- 实现如下的功能: 在电话语音识别中需要识别电话号码,这需要识别0到9十个数字,而识别前首 先需要训练这十个数字,请编写程序设计一个电话号码表,要求数字组数最少。其中:每一组数字都是八位(例如:62 781 704),0到9十个数字中每两个数字之间至少连接一次(象62781707,其中出现了:6-2、2—7、7-8、8—1、1—7、7—0、0—7七个连接,7-0和0¬ —7是不同的连接),每个数字在开头、结尾至少各出现一次(象62781707其中,6在开头出现一认,7在结尾出现一次)
VAD_2
- 该程序是AMR-WB+声码器中的VAD(Voice Activity Detection)程序.测试时使用8kHz采样率,16bit量化的wav文件. -AMR-WB Vocoder the VAD (Voice Activity Dete ction) program. test the use of 8 kHz sampling rate and 16bit wav quantify the document.
yuyinshibiedsp
- 用DSP实现的一个简单的语音识别系统,只要实现单个词的识别即可,采样率8k,帧长30ms,帧移10ms,系统采样后分帧--端点检测,将检测到的原始语音信号保存下来,基本上一个字在30帧左右,然后提取每帧的LPC参数--将LPC参数转换为LPC倒谱系数,然后利用DTW方法和模板比较.-a brief speech recognition system, as long as the realization of a single word can be identified. 8 k sampli
wavesurfer-1.8.5.tar
- WaveSurfer.著名的语音分析工具,语音研究者必备!-WaveSurfer. Famous speech analysis tools, voice, researchers must!
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 transplanted to eight 16-bit MCU or DSP.
uLaw-linear
- 可用于DSP应用的u率与线性数据的转换,u率压扩是广泛应用于电信语音从13位到8位非线性压缩标准-can be used for DSP applications u rate and linear data conversion, u rate pressure expansion is widely used in telecommunications voice from 13-8 nonlinear compression standard
VoiceReconize
- 语音识别代码,机器人语音控制系统 CMDs=零,一,二,三,四,五,六,七,八,九,执行,各关节归零,大臂正转,大臂反转,小臂正转,小臂反转,手腕正转,手腕反转,手爪张开,手爪闭合,上升,下降,大臂运行,大臂负运行,小臂运行,小臂负运行,手腕运行,手腕负运行,手爪运行,手爪负运行,升降运行,升降负运行,大臂归零,小臂归零,手腕归零,手爪归零,升降归零,速度加,原点记忆,系统复位,示教盒,暂停,急停,回原点,速度减,区号加,区号减,单步再现,周期再现,连续再现,返回,继续,数据记忆,读取
voiceshengchengqi
- 一个使用数学方法生成波形声音文件的源代码,可以载入预置数学公式,保存8位和16位单声道声音文件,可以设置振幅、频率、持续、采样等参数,可以调整波形斜面,回声。很好用的-use of a mathematical method to generate waveform audio files of source code, can be included in the preset mathematical formula, and the preservation of eight 16 mon
xvoice-0.8.1
- xvoice:linux的语音识别源码-xvoice : linux source of Speech Recognition
DTMF_8
- DTMF Decoder Based on VC6 (Input 8 bit pcm)
volnorm-0.8.3.tar
- Volume normalization algorithm
dctQ
- 基于8*8分块的DCT域水印嵌入算法水印图像为64*64的,原始图像为256*256的,把原始图像变成64*1024的
luyin
- 用MATLAB采集和播放一段(5s长,采样率为8k,每个样本位数8位)的语音信号。
大名鼎鼎的开源语言识别工具CMU Sphinx
- 大名鼎鼎的开源语言识别工具CMU Sphinx,版本3.0.8-The famous open-source speech recognition tool for CMU Sphinx, version 3.0.8
record
- vc源代码,在VC6.0, 8.0均测试通过。语音信号采集,并有波形示-voice collecting tool
soundin
- % this a experiment that input is done using the sound card %2003,6,3 %Usage:[second,voltage,frequency,magnitude]=soundin (VoiceFrequencyFactor,rate) %VoiceFrequencyFactor is set as 1/8 and rate as 8000, when the Frequency is % below 40hz ro
fft
- Special Requirements ?nx must be a power of 2. ?The index array must be set up by bitrev_index before the function DSP_bitrev_cplx is called. ?If nx ?4K, one can use the char (8-bit) data type for the "index" variable. This would requ
38decoder
- 3-8译码器,经过综合仿真,可以实现功能-3-8 decoder, after a comprehensive simulation function can be achieved
Speech_LPC
- This GUI is used to analyze the speech signal at the selected region of 256 samples. All the calculation is based on the sampling of 8 KHz. First 3 formants of the selected block of samples are derived from the LPC-8 coefficients. -This GUI is used t
