搜索资源列表
melp5
- 在混合激励线性预测(MELP)语音编码算法中,语音帧的突变转换导致合成语音质量的下降成为一个突出问题.为解决该问题,提出一种基于过渡帧判决算法的改进MELP模型,提高了参数估计的准确度,有效实现了语音的降噪处理.-In the hybrid excitation linear prediction (MELP) speech coding algorithm, the abrupt change of the speech frame leads to the degradation of sy
melppaper6
- 为了提高深度模型的编码重构性能,本文为传统对比散度(Contrastive divergence,CD)添加了基于交叉熵的重构误差约束。利用改进后的算法训练了重构性深度自编码机(Reconstructive deep au-to-encoder,RDAE),并用 RDAE 替换混合激励线性预测编码(Mixed excitation linear prediction, MELP)语音编码器中 LSF 参数的矢量量化方法。测试结果表明,改进后的算法在损失一定模型似然度的条件下获得了重构性能的提升,
Feature-Denoising
- joint sparse representation (JSR)方法用于车内语音增强的特征降噪算法-address reducing the mismatch between training and testing conditions for hands-free in-car speech recognition. It is well known that the distortions caused by background noise, channel effec
Structured-Sparsity-Models
- 用于混响背景语音分离的结构稀疏模型(Strutured sparisty model)方法-To further tackle the ambiguity of the reflection ratios, we propose a novel formulation of the reverberation model and estimate the absorption coefficients through a convex optimization exploiting
DataMining-and-R
- 数据挖掘与R语音的PDF电子书，包含R语音数据挖掘案例，很不错的入门书。- PDF file of R for Data mining, including some good data mining case which is a very good introductory book.
oneWx
- 微信 (WeChat)[1] 是腾讯公司于2011年1月21日推出的一个为智能终端提供即时通讯服务的免费应用程序[1] ，由张小龙所带领的腾讯广州研发中心产品团队打造 [2] 。微信支持跨通信运营商、跨操作系统平台通过网络快速发送免费（需消耗少量网络流量）语音短信、视频、图片和文字，同时，也可以使用通过共享流媒体内容的资料和基于位置的社交插件“摇一摇”、“漂流瓶”、“朋友圈”、”公众平台“、”语音记事本“等服务插件。-weixin
24cxx
- 对讲机NRF24L01无线通信模块语音代码-Walkie- talkie NRF24L01 wireless communication module voice code
DFT-kalman
- 一个卡拉曼的外文论文，主要研究卡尔曼语音增强-A Kalman foreign language papers, mainly study Calman speech enhancement
jmnhb
- 是信号处理的基础，完整的基于HMM的语音识别系统，外文资料里面的源代码。- Is the basis of the signal processing, Complete HMM-based speech recognition system, Foreign materials inside the source code.
yy251
- 已经调试成功.内含m文件，可直接运行，语音信号的采集与处理，数字信号处理课设，脉冲响应的相关分析算法并检验。- Has been successful debugging. M contains files can be directly run, Acquisition and Processing of the speech signal, digital signal processing class-based, Related impulse response analysis alg
kywpw
- 语音信号的采集与处理，数字信号处理课设，有井曲线作为输入可计算其地震波的衰减,汽车课设货车Matlab驱动力图程序。- Acquisition and Processing of the speech signal, digital signal processing class-based, There is a well attenuation curve as input to calculate its seismic waves, Car class-based truck drive
ka078
- 语音信号的采集与处理，数字信号处理课设，汽车课设货车Matlab驱动力图程序，复化三点Gauss-lengend公式求pi。- Acquisition and Processing of the speech signal, digital signal processing class-based, Car class-based truck driver trying to Matlab program, Complex of three-point Gauss-lengend the Fo
fhbdn
- 数值分析的EULER法，语音信号的采集与处理，数字信号处理课设，包括单边带、双边带、载波抑制及四倍频。- EULER numerical analysis method, Acquisition and Processing of the speech signal, digital signal processing class-based, Including single sideband, double sideband, suppressed carrier and quadruple
nai-V8.4
- 完整的基于HMM的语音识别系统，IMC-PID是利用内模控制原理来对PID参数进行计算，汽车课设货车Matlab驱动力图程序。- Complete HMM-based speech recognition system, The IMC- PID is using the internal model control principle for PID parameters is calculated, Car class-based truck driver trying to Matlab
fw802
- 数据模型归一化，模态振动，完整的基于HMM的语音识别系统，粒子图像分割及匹配均为自行编制的子例程。- Normalized data model, modal vibration, Complete HMM-based speech recognition system, Particle image segmentation and matching subroutines themselves are prepared.
yai-V8.7
- 已调制信号计算其普相关密度，汽车课设货车Matlab驱动力图程序，语音信号的采集与处理，数字信号处理课设。- Modulated signals to calculate its density Pu-related, Car class-based truck driver trying to Matlab program, Acquisition and Processing of the speech signal, digital signal processing class-base
vw837
- 对信号进行频谱分析及滤波，语音信号的采集与处理，数字信号处理课设，有循环检测，周期性检测。- The signal spectral analysis and filtering, Acquisition and Processing of the speech signal, digital signal processing class-based, There are cycle detection, periodic testing.
wv486
- 语音信号的采集与处理，数字信号处理课设，是学习PCA特征提取的很好的学习资料，是国外的成品模型。- Acquisition and Processing of the speech signal, digital signal processing class-based, Is a good learning materials to learn PCA feature extraction, Foreign model is finished.
mauxu
- 有PMUSIC 校正前和校正后的比较，阐述了负荷预测的应用研究,完整的基于HMM的语音识别系统。- A relatively before correction and after correction PMUSIC, It describes the application of load forecasting, Complete HMM-based speech recognition system.
mr842
- 包含CV、CA、Single、当前、恒转弯速率、转弯模型，语音信号的采集与处理，数字信号处理课设，实现用SDRAM运行nios，同时用SRAM保存摄像头数据。- It contains CV, CA, Single, current, constant turn rate, turning model, Acquisition and Processing of the speech signal, digital signal processing class-based, Implement