摘要 :
The performance of most speech enhancement algorithms declines under low-SNR conditions because of residual noise (or speech distortion) and the degradation of voice activity detector (VAD) performance. We therefore propose a spee...
展开
The performance of most speech enhancement algorithms declines under low-SNR conditions because of residual noise (or speech distortion) and the degradation of voice activity detector (VAD) performance. We therefore propose a speech enhancement approach based on noise eigenspace projection. When noisy speech is projected into the noise eigenspace, the noise energy is packed to a subspace consisting of dimensions with larger eigenvalues. This subspace is fairly dominated by noise. Removing the noise subspace can greatly reduce the noise at the cost of little speech loss. At the same time, the eigenspace dimensions having little noise are used to make a robust VAD. Using the proposed algorithm as a pre-processing block for conventional enhancement algorithms can efficiently reduce the residual noise under low-SNR conditions.
收起
摘要 :
How to reduce noise with less speech distortion is a challenging issue for speech enhancement. We propose a novel approach for reducing noise with the cost of less speech distortion. A noise signal can generally be considered to c...
展开
How to reduce noise with less speech distortion is a challenging issue for speech enhancement. We propose a novel approach for reducing noise with the cost of less speech distortion. A noise signal can generally be considered to consist of two components, a "white-like" component with a uniform energy distribution and a "color" component with a concentrated energy distribution in some frequency bands. An approach based on noise eigenspace projections is proposed to pack the color component into a subspace, named "noise subspace". This subspace is then removed from the eigenspace to reduce the color component. For the white-like component, a conventional enhancement algorithm is adopted as a complementary processor. We tested our algorithm on a speech enhancement task using speech data from the Texas Instruments and Massachusetts Institute of Technology (TIMIT) dataset and noise data from NOISEX-92. The experimental results show that the proposed algorithm efficiently reduces noise with little speech distortion. Objective and subjective evaluations confirmed that the proposed algorithm outperformed conventional enhancement algorithms.
收起
摘要 :
In many practical environments we wish to extract several desired speech signals, which are contaminated by nonstationary and stationary interfering signals. The desired signals may also be subject to distortion imposed by the aco...
展开
In many practical environments we wish to extract several desired speech signals, which are contaminated by nonstationary and stationary interfering signals. The desired signals may also be subject to distortion imposed by the acoustic room impulse responses (RIRs). In this paper, a linearly constrained minimum variance (LCMV) beamformer is designed for extracting the desired signals from multimicrophone measurements. The beamformer satisfies two sets of linear constraints. One set is dedicated to maintaining the desired signals, while the other set is chosen to mitigate both the stationary and nonstationary interferences. Unlike classical beamformers, which approximate the RIRs as delay-only filters, we take into account the entire RIR [or its respective acoustic transfer function (ATF)]. The LCMV beamformer is then reformulated in a generalized sidelobe canceler (GSC) structure, consisting of a fixed beamformer (FBF), blocking matrix (BM), and adaptive noise canceler (ANC). It is shown that for spatially white noise field, the beamformer reduces to a FBF, satisfying the constraint sets, without power minimization. It is shown that the application of the adaptive ANC contributes to interference reduction, but only when the constraint sets are not completely satisfied. We show that relative transfer functions (RTFs), which relate the desired speech sources and the microphones, and a basis for the interference subspace suffice for constructing the beamformer. The RTFs are estimated by applying the generalized eigenvalue decomposition (GEVD) procedure to the power spectral density (PSD) matrices of the received signals and the stationary noise. A basis for the interference subspace is estimated by collecting eigenvectors, calculated in segments where nonstationary interfering sources are active and the desired sources are inactive. The rank of the basis is then reduced by the application of the orthogonal triangular decomposition (QRD). This procedure relaxes the comm-
on requirement for nonoverlapping activity periods of the interference sources. A comprehensive experimental study in both simulated and real environments demonstrates the performance of the proposed beamformer.
收起
摘要 :
The capability of orthogonal projection (OP) approach degrades severely in the presence of array model mismatch, especially when the training samples are mixed with the strong desired signal. Therefore, an improved OP robust adapt...
展开
The capability of orthogonal projection (OP) approach degrades severely in the presence of array model mismatch, especially when the training samples are mixed with the strong desired signal. Therefore, an improved OP robust adaptive beamforming is proposed based on correlated projection and eigenspace processing in wide input signal-to-noise ratio to remove the desired signal self-null effect and improve robustness. In the proposed approach, the interference subspace is constructed combining the correlated projection and eigenspace processing first. Then, the interference-plus-noise covariance matrix is accurately reconstructed via super-resolution spatial spectrum estimator to eliminate desired signal from sample covariance matrix. Subsequently, the desired signal steering vector is corrected applying correlated projection and then the adaptive weighted vector is modified by OP approach. Simulation results demonstrate that the capability of the proposed approach is almost consistently same as the optimal beamformer in many scenarios.
收起
摘要 :
Computing the morphological similarity of diffusion tensors (DTs) at neighboring voxels within a DT image, or at corresponding locations across different DT images, is a fundamental and ubiquitous operation in the postprocessing o...
展开
Computing the morphological similarity of diffusion tensors (DTs) at neighboring voxels within a DT image, or at corresponding locations across different DT images, is a fundamental and ubiquitous operation in the postprocessing of DT images. The morphological similarity of DTs typically has been computed using either the principal directions (PDs) of DTs (i.e., the direction along which water molecules diffuse preferentially) or their tensor elements. Although comparing PDs allows the similarity of one morphological feature of DTs to be visualized directly in eigenspace, this method takes into account only a single eigenvector, and it is therefore sensitive to the presence of noise in the images that can introduce error in to the estimation of that vector. Although comparing tensor elements, rather than PDs, is comparatively more robust to the effects of noise, the individual elements of a given tensor do not directly reflect the diffusion properties of water molecules. We propose a measure for computing the morphological similarity of DTs that uses both their eigenvalues and eigenvectors, and that also accounts for the noise levels present in DT images. Our measure presupposes that DTs in a homogeneous region within or across DT images are random perturbations of one another in the presence of noise. The similarity values that are computed using our method are smooth (in the sense that small changes in eigenvalues and eigenvectors cause only small changes in similarity), and they are symmetric when differences in eigenvalues and eigenvectors are also symmetric. In addition, our method does not presuppose that the corresponding eigenvectors across two DTs have been identified accurately, an assumption that is problematic in the presence of noise. Because we compute the similarity between DTs using their eigenspace components, our similarity measure relates directly to both the magnitude and the direction of the diffusion of water molecules. The favorable performanc- - e characteristics of our measure offer the prospect of substantially improving additional postprocessing operations that are commonly performed on DTI datasets, such as image segmentation, fiber tracking, noise filtering, and spatial normalization.
收起
原文获取