Noisy Feature Vectors Research Articles

From Noise Addition to Denoising: A Self-Variation Capture Network for Point Cloud Optimization.

Point clouds obtained from 3D scanners are often noisy and cannot be directly used for subsequent high-level tasks. In this article, we propose a novel point cloud optimization method capable of denoising and homogenizing point clouds. Our idea is based on the assumption that the noise is generally much smaller than the effective signal. We perform noise perturbation on the noisy point cloud to get a new noisy point cloud, called self-variation point cloud. The noisy point cloud and self-variation point cloud have different noise distribution, but the same point cloud distribution. We compute the potential commonality between two noisy point clouds to obtain a clean point cloud. To implement our idea, we propose a Self-Variation Capture Network (SVCNet). We perturb the point cloud features in the latent space to obtain self-variation feature vectors, and capture the commonality between two noisy feature vectors through the feature aggregation and averaging. In addition, an edge constraint module is introduced to suppress low-pass effects during denoising. Our denoising method does not take into account the noise characteristics, and can filter the drift noise located on the underlying surface, resulting in a uniform distribution of the generated point cloud. The experimental results show that our algorithm outperforms the current state-of-the-art algorithms, especially in generating more uniform point clouds. In addition, extended experiments demonstrate the potential of our algorithm for point clouds upsampling.

Feature recovery for noise‐robust speaker verification

Noisy condition is an important extrinsic degradation affecting speaker verification system performance. A feature-recovery approach is proposed to eliminate noise-dependent variability in feature space. A frame of the noisy feature vector is recovered using the information of itself and the neighbour feature vectors. Experiments are conducted on noisy test sets for text-dependent speaker verification tasks and the results indicate that the system can achieve significant performance improvement by using recovered feature vectors.

Model-based clustered sparse imputation for noise robust speech recognition

In the sparse imputation approach, missing spectral components of speech are estimated using the compressive sensing technique. For this purpose, a dictionary of clean speech components must be prepared. Noisy feature vectors are then reconstructed by the dictionary queries. In this approach, the dictionary elements should adequately cover all the possible varieties of the speech feature vectors; so, for a subject speech frame, there will be lots of irrelevant components inside the dictionary. These components make a huge size for the dictionary that in turn, slow down the estimation process and may produce artifacts in the final estimation. To face this problem, the current work proposes to cluster the dictionary queries in some smaller subspaces; the relevant subspace for a subject feature vector could be found through the posterior criterion. Moreover, this is shown that the likelihood of the Gaussian models developed for the subspaces could role as a regularization term and act as an extra prior knowledge in the estimation process and increases the final performance, significantly. To evaluate the benefits of the proposed methods, some well-designed ASR experiments are conducted on two different speech corpora, an English noisy connected digit database (Aurora 2) and a Persian continuous speech corpus (FARSDAT). The experiments show that the proposed methods not only increase the absolute word recognition accuracy but also make the entire process few times faster than the original sparse imputation approach.

Feature Denoising Using Joint Sparse Representation for In-Car Speech Recognition

We 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 from 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.

Capacity/Storage Tradeoff in High-Dimensional Identification Systems

The asymptotic tradeoff between the number of distinguishable objects and the necessary storage space (or equivalently, the search complexity) in an identification system is investigated. In the discussed scenario, high-dimensional (and noisy) feature vectors extracted from objects are first compressed and then enrolled in the database. When the user submits a random query object, the extracted noisy feature vector is compared against the compressed entries, one of which is output as the identified object. The first result this paper presents is a complete single-letter characterization of achievable storage and identification rates (measured in bits per feature dimension) subject to vanishing probability of identification error as the dimensionality of feature vectors becomes very large. This single-letter characterization is then extended for a multistage system whereby depending on the number of entries, the identification is performed by utilizing part or all of the recorded bits in the database. Finally, it is shown that a necessary and sufficient condition for a two-stage system to achieve single-stage capacities at each stage is Markovity of the optimal test channels.

Cepstral Vector Normalization Based on Stereo Data for Robust Speech Recognition

In this paper, a set of feature vector normalization methods based on the minimum mean square error (MMSE) criterion and stereo data is presented. They include multi-environment model-based linear normalization (MEMLIN), polynomial MEMLIN (P-MEMLIN), multi-environment model-based histogram normalization (MEMHIN), and phoneme-dependent MEMLIN (PD-MEMLIN). Those methods model clean and noisy feature vector spaces using Gaussian mixture models (GMMs). The objective of the methods is to learn a transformation between clean and noisy feature vectors associated with each pair of clean and noisy model Gaussians. The direct approach to learn the transformation is by using stereo data; that is, noisy feature vectors and the corresponding clean feature vectors. In this paper, however, a nonstereo data based training procedure, is presented. The transformations can be modeled just like a bias vector (MEMLIN), or by using a first-order polynomial (P-MEMLIN) or a nonlinear function based on histogram equalization (MEMHIN). Further improvements are obtained by using phoneme-dependent bias vector transformation (PD-MEMLIN). In PD-MEMLIN, the clean and noisy feature vector spaces are split into several phonemes, and each of them is modeled as a GMM. Those methods achieve significant word error rate improvements over others that are based on similar targets. The experimental results using the SpeechDat Car database show an average improvement in word error rate greater than 68% in all cases compared to the baseline when using the original clean acoustic models, and up to 83% when training acoustic models on the new normalized feature space

Method of noise reduction using correction vectors based on dynamic aspects of speech and noise normalization

A method and apparatus are provided for reducing noise in a signal. Under one aspect of the invention, a correction vector is selected based on a noisy feature vector that represents a noisy signal. The selected correction vector incorporates dynamic aspects of pattern signals. The selected correction vector is then added to the noisy feature vector to produce a cleaned feature vector. In other aspects of the invention, a noise value is produced from an estimate of the noise in a noisy signal. The noise value is subtracted from a value representing a portion of the noisy signal to produce a noise-normalized value. The noise-normalized value is used to select a correction value that is added to the noise-normalized value to produce a cleaned noise-normalized value. The noise value is then added to the cleaned noise-normalized value to produce a cleaned value representing a portion of a cleaned signal.

Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech

A method and apparatus are provided for reducing noise in a training signal and/or test signal. The noise reduction technique uses a stereo signal formed of two channel signals, each channel containing the same pattern signal. One of the channel signals is “clean” and the other includes additive noise. Using feature vectors from these channel signals, a collection of noise correction and scaling vectors is determined. When a feature vector of a noisy pattern signal is later received, it is multiplied by the best scaling vector for that feature vector and the best correction vector is added to the product to produce a noise reduced feature vector. Under one embodiment, the best scaling and correction vectors are identified by choosing an optimal mixture component for the noisy feature vector. The optimal mixture component being selected based on a distribution of noisy channel feature vectors associated with each mixture component.

Noise adaptation algorithms for robust speech recognition

This paper proposes three noise adaptation algorithms which allow improvements in the performance of speech recognition systems under noisy conditions. They are VQ-based feature mapping techniques which hierarchically transform noisy feature vectors into clean feature vectors. The first algorithm was originally used for unsupervised speaker adaptation. It is based on hard clustering and iteratively adapts the noisy input data to a small set of codebooks created from clean data. The second algorithm is a modified version of the first one. It redefines the mapping function using the notion of cluster scope. The last algorithm proposes a fuzzy clustering technique as a substitute to the original hard clustering technique. In the NATO digit task, these algorithms significantly improve the performance of CRIM's speech recognition system.