搜索资源列表
vad3
- 用双门限检测法做语音分割，程序比较具体，并且能够直接仿真出图，只要把输入语音自己录制一下就可以了，是我自己做的，希望您多多指教-dual-threshold detection so segmentation, procedures more specific, and can map out a direct simulation. As long as the importation of voice recording what they could, yes I do hope you
VibTest
- 基于声音采集卡的采集源代码,并能显示波形图,做声音采集的可以借鉴.-acquisition card based on the voice of the acquisition source code, and can show that the waveform map, so voices can draw on the acquisition.
AutoGetHz
- google Map 地图中文字自动提取软件
adaptation
- 语音识别自适应训练原理的论文，包括MLLR，MAP-adaptation for speech recognition
map
- speech recognition speaker adaption map algorithm
HMM
- ：为了使应力变异在顽健语音识别系统中能够达到较好的识别效果，研究了基于隐马 尔可夫模型(HMM)的自适应技术，提出了将最大后验概率(MAP)和最大似然回归方法(MLLR)用 于应力变异语音的自适应中。实验结果表明，与基本系统相比，两种方法均有效地提高系统识别 率。以SD为初始模型的最大后验概率方法在150个训练样本时识别效果最好，可以达到90．4％ 。-: In order to stress variation in the robustness of speech recogni
FFT_lowpass
- 采用FFT和低通滤波器的两种语音除噪算法比较，MATLAB编程，附效果图-Using FFT and low pass filter audio noise canceling algorithm for the two compare, MATLAB programming, with a results map
AnalogVoiceSignal
- 观测实时模拟信号（语音）的频谱 用音频设备采集一段语音，将语音存为.wav格式。对wav文件作分段傅里叶变换分析。语音是分音节的，应把它分段分析，而且实际运用中的数字信号处理的FFT的点数是有限的，一般只能达到千点。用傅里叶反变换IFFT，从频域恢复信号。画出频谱图和语音波形图。 -Observing real-time analog signal (voice) of the spectrum collected with the audio devices section of
Speech_Adaptin_using_MLLR_and_MAP
- 说话人自适应是提高非特定人语音识别系统识别性能的有效手段，本文针对非母语说话人，结合常规的白适应技术MLLR和MAP，探索云南纳西族和傈僳族两种母语说话人的汉语普通话语音识别问题，实验结果显示有显著效果。-Speaker adaptation is a powerful means of improving the performance of speakerindependent speech recognition system．Aimed at Yunnan minority Naxi a
Speech-Recognition-Using-Neural-Networks
- speech recognision is used to develop automatic speech regonision system and also to normalise it and then map it to a particular user voice.
shiyan5
- 用于显示男声，女声，高音，低音，以及变音后的频谱及原声图。完全放心使用即可！-Used to show male, female, treble, bass, and after the change the sound spectrum and acoustic map. Complete ease of use can be!
trainscg_10
- 利用matlab软件BP网络工具箱，画出预测语音种类和实际语音种类的分类图-BP neural network using matlab software toolbox, paint and forecast the actual voice voice types and species classification map