资源列表
Continuous-speech-
- 语音识别中关于连续语音的应用,当说话比较长时,句子比较长是语言识别的难点,本章重点解决连续语音的识别问题-On continuous speech voice recognition applications, when the talk is longer, a longer sentence is the difficulty of speech recognition, this chapter focused on solving the problem of continuous sp
Speech-enhancement-
- 基于matlab仿真的语音增强算法,语音增强是语音识别的预处理,通过语音增强可以很好的进行语言识别-Matlab simulation-based speech enhancement algorithms, speech recognition, speech enhancement is pre-processing, through the speech enhancement for speech recognition can be good
IIR_Cheby2_HP_Bilinear
- IIR型切比学府滤波器 并且分析了他的归一化后的 频率响应 和特定输入信号经过滤波后的结果 得出零极点图-IIR model than learning filter and analysis cut the normalization of the frequency response and specific input signal through the filter results from zero pole figure
adpcm
- 用ADPCM算法将语音文件(.wav格式)的16位数据压缩成4位数据的程序,还有将4位压缩后的数据解压成语音文件-ADPCM encoder and decoder
Robust-Parallel-Speech-Recognition-in-Multiple-En
- Robust Parallel Speech Recognition in Multiple Energy Bands
pitchdetect
- 在语音的倒谱中,将语音的短时谱经过变换后,在倒谱中用于基音检测。-For pitch detection.
G711
- G.711标准A律和u律8kHz采样16比特数字语音编码的C语言实现-Standard G.711 A-law and u law 8kHz sampling 16-bit digital speech coding in C language
G721
- G.721标准c语言实现,输入8kHz16bit数字语音输出定比特率32kbps编码比特流-G.721 standard c language, enter 8kHz16bit digital voice output given bit rate 32kbps coded bit stream
FEATURE-SELECTION-FOR-A-DTW-BASED
- FEATURE SELECTION FOR A DTW-BASED SPEAKER VERIFICATION SYSTEM
voice-maker
- 语音信号的内插与抽取 某大学c++的实践作业-Interpolation of speech signals collected by a university with the practical operation c++
speech
- 能够实现中英文混合朗读,并且可以根据语音显示出文字。-Mixing can be achieved in English reading, and can display text based on voice.
mean-K-KPCA
- 通过核 K- 均值聚类的方法对语音帧进行聚类 , 由于聚类的中心能够很好地代表类内的特征, 用中心样本帧取代该类, 减少了核矩阵的维数, 然后再采用稀疏 KPCA方法对核矩阵进行特征提取。-Through the nuclear K-means clustering method for clustering of speech frames, the cluster center can be a good representative of the class characteristics