Location:
Search - dct speech
Search list
Description: 介绍基于SVM模型的语音识别方法的处理与研究，通过把SVM 与DCT相结合来进行语音的识别。-Introduced the SVM model based on speech recognition method of treatment and research, through the combination of SVM with the DCT for speech recognition.
Platform: |
Size: 626688 |
Author: kellan |
Hits:
Description: 采用BP算法来实现压缩感知的信号重构示例。BP算法由线性规划来实现，稀疏基为DCT基，信号为语音信号-an example of using BP algorithm for signal reconstruction in compressed sensing. BP algorithm is implemented by linear programming, sparse basis is the DCT basis, the signal used is speech
Platform: |
Size: 1024 |
Author: Haiyan Guo |
Hits:
Description: ICTCLAS分词的总体流程包括：1）初步分词；2）词性标注；3）人名、地名识别；4）重新分词；5）重新词性标注这五步。就第一步分词而言，又细分成：1）原子切分；2）找出原子之间所有可能的组词方案；3）N-最短路径中文词语粗分三步。
在所有内容中，词典库的读取是最基本的功能。ICTCLAS中词典存放在Data目录中，常用的词典包括coreDict.dct（词典库）、BigramDict.dct（词与词间的关联库）、nr.dct（人名库）、ns.dct（地名库）、tr.dct（翻译人名库），它们的文件格式是完全相同的，都使用CDictionary类进行解析。如果想深入了解ICTCLAS词典结构，可以参考sinboy的《ICTCLAS分词系统研究（二）--词典结构》一文，详细介绍了词典结构。
-ICTCLAS word of the overall process include: 1) initial segmentation 2) POS tagging 3) names, places identification 4) to re-word 5) This five-step re-speech tagging. The first word, the thin, divided into: 1) atom splitting 2) to identify all the possible atomic set of words between the program 3) N-shortest paths Chinese words rough three steps.
Platform: |
Size: 1965056 |
Author: ounata |
Hits:
Description: 论文首先介绍了传统的语音特征参数MFCC，它是基于人耳听觉
特性设计的一种特征参数，在静音环境下能得到较高的识别率，但在
信噪比较低时识别率急剧下降，不利于实用化。本文通过对MFCC算
法的分析和研究，发现其中的FFT和DCT在整个时频空间使用固定的
。分析窗，这不符合语音信号特性，而小波变换具有多分辨率特性，更
符合人耳的听觉特性。因此，本文将小波变换和MFCC算法相结合，
提出了三种新的语音识别特-Speech recognition has wide use in the field of communication and so
on·Speech feature parameter extraction is an important part of the speech
recognition system．The performance of the feature parameter haftuences
the system’S performance directly．And the environmental noise is a kev
factor of restricting the performance of the feature parameter．This paper，s
research object is extracting the speech feature parameter under the noise
environment·Then it analyzes the auditory model of human，deeply
analyzes and researches the traditional speech feature parameter MFCC，
and proposes three improved MFCC parameters based on theⅥ，avelet
transformation and the auditory characteristic ofhuman．Besides，the paper
also gives all improved method about the feature parameter ZCPA．
Platform: |
Size: 2001920 |
Author: 周卓然 |
Hits:
Description: 读入语音信号并对其进行dct变换进行压缩变换的matlab程序-Reading the speech signal compression transform Matlab procedures and dct transform
Platform: |
Size: 1024 |
Author: liu |
Hits:
Description: 语音信号的压缩感知及其重构 代码 dct-Perception of speech signal compression and reconstruction code dct
Platform: |
Size: 1024 |
Author: slf |
Hits:
Description: 对语音信号的一幀信号（1024点）进行DCT
对正弦信号进行DCT,对比实验图.修改实验代码,设置阈值,绝对值小于阈值的置0,再反变换看波形.
-One frame of the speech signal signal (1024) of the sinusoidal signal to DCT DCT, comparative experiments FIG. Modify experimental code, set the threshold value, the absolute value is smaller than the threshold value is set to 0, then the inverse transform to see the waveform.
Platform: |
Size: 94208 |
Author: shelly |
Hits:
Description: a robust non blind audio and speech watermarking
in the DCT domain
Platform: |
Size: 3072 |
Author: yassinov |
Hits:
Description: 传统的短时谱估计语音增强算法通常假设语音谱分量相互独立，没有考虑语音谱分量间的相关性。针对这
一问题，该文提出一种新的基于多元Laplace分布模型的短时谱估计算法。首先，假设语音的离散余弦变换(DCT)
系数服从多元Laplace分布，以此利用谱分量间的相关性；在此基础上，利用多元随机矢量的高斯尺度混合模型表
示，推导得到语音DCT系数矢量的最小均方误差(MMSE)估计的解析表达式；并进一步推导了基于该分布模型的
语音存在概率，对最小均方误差估计子进行修正。实验结果表明，该算法在抑制背景噪声和减少语音失真等方面优
于传统的语音增强方法。-The spectral components of speech are usually assumed to be independent in traditional short-time
spectrum estimation, which is not the case in practice. Tosolve this problem, a new speech enhancement algorithm
with multivariate Laplace speech model is proposed in this paper. Firstly, the speech Discrete Cosine Transform
(DCT) coefficients are modeled by a multivariate Laplace distribution, so the correlations between speech spectral
components can be exploited. And then a Minimum-Mean-Square-Error (MMSE) estimator based on the proposed
model is derived using a Gaussian scale mixture representation of random vectors. Furthermore, the speech
presence uncertainty with the new model is derived to modify the MMSE estimator. Experimental results show
that the developed method has better noise suppression performance and lower speech distortion compared to the
traditional speech enhancement method.
Platform: |
Size: 1054720 |
Author: 立枣酒 |
Hits:
Description: 语音信号的DCT变换以及OMP算法重构 -Sensing Reconstruction program is based compressed speech signals
Using OMP algorithm to reconstruct speech
Framing program includes speech, and omp, programs can be run properly.
Platform: |
Size: 172032 |
Author: 畅江 |
Hits:
Description: 其变换矩阵的基向量很近似于托伯利兹矩阵的特征向量，而托伯利兹矩阵又体现了人类语言及图像信号的相关性。因此，DCT常常被认为是语音与图像信号变换的准最佳变换。-The transformation matrix of the basis vectors is approximate to the Vento Belize matrix eigenvectors, and the support matrix of Belize and reflects the relationship between human language and image signal. Therefore, DCT is often considered as a quasi optimal transformation of speech and image signal transformation.
Platform: |
Size: 1024 |
Author: 科研 |
Hits:
Description: 利用梅爾倒頻譜演算法，計算語音訊號的特徵值。裡面有DCT與三角帶通。(The Mel Cepstrum algorithm is used to calculate the eigenvalues of speech signals. There are DCT and V-belt.)
Platform: |
Size: 9216 |
Author: goodall |
Hits:
Description: java实现MFCC系数的提取，包括FFT运算和DCT运算，mel滤波器的设计等(The extraction of MFCC coefficient by Java)
Platform: |
Size: 82944 |
Author: 木木· |
Hits: