Location:
Search - sparse speech
Search list
Description: 国外欠定语音盲分离的博士论文，作者为Paul D. O’Grady，LOST算法的作者。该博士论文包括语音信号分离，非负矩阵分解等内容。-Sparse Separation of Under-Determined Speech Mixtures，A dissertation submitted for the degree of Doctor of Philosophy
Platform: |
Size: 5888000 |
Author: 云上 |
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: 用ksvdbox12来构造反映源语音特性的稀疏过完备基示例。训练信号为两个说话人的语音信号。-Use the ksvdbox12 to construct sparse over-complete basis reflecting the characteristics of the training signals. Training signals used in the example are speech signals of two speakers.
Platform: |
Size: 1024 |
Author: Haiyan Guo |
Hits:
Description: 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 of the sample frame to replace the class with the center, reducing the dimension of the nuclear matrix, and then use Sparse KPCA method for feature extraction of the nuclear matrix.
Platform: |
Size: 185344 |
Author: piano |
Hits:
Description: 维纳滤波、理想二进制掩膜以及理想二进制掩膜和稀疏编码相结合的语音加强-speech enhancement algorithms ,including wiener filter , IBM and research on IBM and sparse coding jointly
Platform: |
Size: 8025088 |
Author: barbara |
Hits:
Description: 针对稀疏表示识别方法需要大量样本训练过完备字典且特征冗余度较高的问题，提出了结合过完备字典学习与PCA降维的小样本语音情感识别算法.该方法首先用PCA降维方法将特征降维，再将处理后的特征用于过完备字典训练与稀疏表示识别方法，从而给出了语音情感特征的稀疏表示方法，并确定了新算法的具体步骤.为验证其有效性，在同等特征维数下，将方法与BP, SVM进行比较，并对比、分析语音情感特征稀疏化前后对语音情感识别率、时间效率以及空间效率的影响.试验结果表明，所提出方法的识别率比SVM与BP高 与采用稀疏化前的特征相比，稀疏化后的特征向量更便于处理，平均识别率提高约15 ，时间效率提高近原来的1 /2，空间效率提升近原来的1 /3.
-Identification methods for sparse representation requires a lot of training samples and high over-complete dictionary feature redundancy problem, a combination of over-complete dictionary learning and PCA dimension small sample speech emotion recognition algorithms. Firstly, the PCA dimension reduction methods feature reduction, feature and then treatment for the over-complete dictionary training and recognition sparse representation, which gives a speech emotion feature sparse representation, and to determine the specific steps of the new algorithm. To verify its validity, in Under the same number of features, the method and BP, SVM compare and contrast, analyze the impact before and after the speech emotion feature sparse speech emotion recognition rate, time-efficient and space-efficient. experimental results show that the recognition rate of the proposed method than High SVM and BP compared to pre-thinning characteristics using eigenvectors easier after thinning processing, the av
Platform: |
Size: 629760 |
Author: wangming |
Hits:
Description: Compressive sampling is an emerging technique that promises to effectively recover a sparse signal from far fewer measurements than its dimension. The compressive sampling theory assures almost an exact recovery of a sparse signal if the signal is sensed randomly where the number of the measurements taken is proportional to the sparsity level and a log factor of the signal dimension. Encouraged by this emerging technique, this thesis briefly reviews the application of Compressive sampling in speech processing. It comprises the basic study of two necessary condition of compressive sensing theory: sparsity and incoherence. In this thesis, various sparsity domain and sensing matrix for speech signal and different pairs that satisfy incoherence condition has been compiled.-Compressive sampling is an emerging technique that promises to effectively recover a sparse signal from far fewer measurements than its dimension. The compressive sampling theory assures almost an exact recovery of a sparse signal if the signal is sensed randomly where the number of the measurements taken is proportional to the sparsity level and a log factor of the signal dimension. Encouraged by this emerging technique, this thesis briefly reviews the application of Compressive sampling in speech processing. It comprises the basic study of two necessary condition of compressive sensing theory: sparsity and incoherence. In this thesis, various sparsity domain and sensing matrix for speech signal and different pairs that satisfy incoherence condition has been compiled.
Platform: |
Size: 1024 |
Author: Anuj |
Hits:
Description: 3基于稀疏编码的语音增强方法研究.pdf-3 Research sparse coding speech enhancement method based on. Pdf
Platform: |
Size: 369664 |
Author: li |
Hits:
Description: 4基于稀疏编码的语音增强方法.pdf-4 sparse coding speech enhancement based on 4 sparse coding speech enhancement method based on.Pdf.Pdf method
Platform: |
Size: 337920 |
Author: li |
Hits:
Description: 基于字典的语音增强中稀疏编码计算稀疏矩阵的一种改进算法，称作larc-Dictionary-based computing sparse coding speech enhancement sparse matrix, an improved algorithm, called larc
Platform: |
Size: 5523456 |
Author: 杨振中 |
Hits:
Description: 基于字典学习的语音增强中字典更新的算法，称作近似K-SVD算法，其中包含了OMP算法用于稀疏编码计算系数矩阵-Dictionary-based learning dictionary speech enhancement algorithm update, called approximate K-SVD algorithm, which contains the sparse coding algorithm is used to calculate the coefficient matrix OMP
Platform: |
Size: 11540480 |
Author: 杨振中 |
Hits:
Description: 基于字典学习的语音增强中稀疏编码计算稀疏矩阵的一种算法，称作OMP。与一般的OMP不同，本程序针对列向量进行计算，结合给出的总体程序以及KSVD of speech enhancemant.rar文件可以进行字典学习语音增强。-Enhanced sparse coding algorithm to calculate a sparse matrix, called the dictionary-based learning OMP voice. OMP different with the general, the procedure for calculating the column vector, combined with the overall process and gives KSVD of speech enhancemant.rar dictionary file can learn speech enhancement.
Platform: |
Size: 2048 |
Author: 杨振中 |
Hits:
Description: 基于1范数的稀疏信号反卷积算法的程序代码，语音信号、迭代算法-The sparse signal deconvolution algorithm based on 1 norm of program code, speech signal, an iterative algorithm
Platform: |
Size: 146432 |
Author: 海红 |
Hits:
Description: Compressive sensing (CS) has been proposed for signals with sparsity
in a linear transform domain. We explore a signal dependent
unknown linear transform, namely the impulse response matrix operating
on a sparse excitation, as in the linear model of speech production,
for recovering compressive sensed speech. Since the linear
transform is signal dependent and unknown, unlike the standard
CS formulation, a codebook of transfer functions is proposed in a
matching pursuit (MP) framework for CS recovery. It is found that
MP is efficient and effective to recover CS encoded speech as well
as jointly estimate the linear model. Moderate number of CS measurements
and low order sparsity estimate will result in MP converge
to the same linear transform as direct VQ of the LP vector derived
the original signal. There is also high positive correlation between
signal domain approximation and CS measurement domain
approximation for a large variety of speech spectra.
Platform: |
Size: 63183872 |
Author: TELECOM |
Hits:
Description: 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 effects, etc., are highly nonlinear in the log-spectral or cepstral
domain. This letter introduces a joint sparse representation
(JSR) to estimate the underlying clean feature vector a noisy
feature vector. Performing a joint dictionary learning by sharing
the same representation coefficients, the proposed method intends
to capture the complex relationships (or mapping functions) between
clean and noisy speech. Speech recognition experiments on
realistic in-car data demonstrate that the proposed method shows
excellent recognition performance with a relative improvement of
39.4 compared with the “baseline” frontends.
Platform: |
Size: 576512 |
Author: bigbigtom |
Hits:
Description: 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 joint sparsity model
formulated upon spatio-spectral sparsity of concurrent speech
representation. The acoustic parameters are then incorporated
for separating individual speech signals through either structured
sparse recovery or inverse filtering the acoustic channels.
The experiments conducted on real data recordings of spatially
stationary sources demonstrate the effectiveness of the proposed
approach for speech separation and recognition.
Platform: |
Size: 1575936 |
Author: bigbigtom |
Hits:
Description: 语音增强，基于数据融合的语音增强方法，用来处理稀疏噪声-Speech enhancement, speech enhancement based on data fusion method, used to deal with sparse noise
Platform: |
Size: 839680 |
Author: 丁一 |
Hits:
Description: This paper proposes a new variant of the least square autoregressive (LSAR) method for speech reconstruction, which can estimate
via least squares a segment of missing samples by applying the linear
prediction (LP) model of speech. First, we show that the use of a single
high-order linear predictor can provide better results than the classic
LSAR techniques based on short- and long-term predictors without the
need of a pitch detector. However, this high-order predictor may reduce
the reconstruction performance due to estimation errors, especially in the
case of short pitch periods, and non-stationarity. In order to overcome
these problems, we propose the use of a sparse linear predictor which
resembles the classical speech model, based on short- and long-term correlations, where many LP coefficients are zero. The experimental results
show the superiority of the proposed approach in both signal to noise
ratio and perceptual performance.
Platform: |
Size: 54272 |
Author: pashaa
|
Hits:
Description: This paper describes a novel speech coding concept created by introducing sparsity constraints in a linear prediction scheme both on
the residual and on the prediction vector. The residual is efficiently
encoded using well known multi-pulse excitation procedures due to
its sparsity. A robust statistical method for the joint estimation of the
short-term and long-term predictors is also provided by exploiting
the sparse characteristics of the predictor. Thus, the main purpose
of this work is showing that better statistical modeling in the context
of speech analysis creates an output that offers better coding properties. The proposed estimation method leads to a convex optimization problem, which can be solved efficiently using interior-point
methods. Its simplicity makes it an attractive alternative to common speech coders based on minimum variance linear prediction.
Platform: |
Size: 125952 |
Author: pashaa
|
Hits:
Description: A Sparse Representation-Based Wavelet Domain
Speech Steganography Method
Platform: |
Size: 1710080 |
Author: maysam
|
Hits: