Search

The use of higher-order polynomial acoustic features can improve the performance of automatic speech recognition (ASR). However, dimensionality of polynomial representation can be prohibitively large, making acoustic model training using polynomial features infeasible for large vocabulary ASR systems. This paper presents a multi-layer polynomial training framework for acoustic modeling, which recursively expands the acoustic features into their second-order polynomial feature space. After each expansion the dimensionality of resultant features is reduced by a linear transformation. Experimental results obtained for two large-vocabulary continuous speech recognition tasks show that the proposed method outperforms conventional mixture models. More recently the acoustic modelling community has shifted its focus to deep neural networks. We also train multi-layer polynomial features in a similar way: allowing backpropagation and using mean-normalized stochastic gradient descent algorithm. This has led to encouraging results. Specifically, appending a sigmoid-based feed-forward deep neural network with a final polynomial layer has resulted in significant word error rate improvement.

A series of aromatic azothiazole and azobenzothiazole compounds containing vinyl have been designed as monomers. The polymers containing azothiazole and azobenzothiazole NLO chromophore in each side chain have been synthesized via free radical polymerization. The third-order NLO coefficient of monomers containing azothiazole and azobenzothiazole and their polymers were measured by Z-scan technique. The conjugation and push–pull electronic effect on the heteroatomic ring group contributes much to enhancing the NLO property.

We have developed a new set of lyophilized kits, composed of 3 different kits, for the instant preparation of no-carrier-added

Most state-of-the-art phone classifiers use the same features and decision criteria for all phones, despite the fact that different broad classes are characterized by different manners and place of articulation that result in different acoustic features. This paper uses manifold learning to address structure in the acoustic space. Previous approaches to dimensionality reduction based on manifold learning assumed that the acoustic space can be characterized by a uniform manifold structure. In this paper we relax this assumption by learning different manifold structures for broad phonetic classes. Because all known classifiers make confusions between broad classes, we designed a two-level classifier in which the top level consists of a number of partially overlapping broad classes. Since the resulting classifiers are not statistically independent, we propose a new method for fusing the classifiers. Experimental results show that our two-level classifier obtained slightly better results when broad-class specific manifolds were learned, compared to a uniform manifold. However, the accuracy is still considerably lower than what could be obtained with oracle knowledge about broad class membership. From this we infer that phones do not form compact clusters in acoustic space.

Radioiodinated meta-iodobenzylguanidine (MIBG) in high effective specific activity was prepared using 3-tributylstannylbenzylguanidine as the precursor. The labeling was carried out in aqueous solution with the insoluble and lyophilized precursor suspended in the solvent. Simply by filtration, the starting material and by-products were readily separated from the labeled solution. Less than 1.15 ppb tin has remained in the filtrate as determined by the atom fluorescence spectrometry. By this approach, high specific activity (3.4 GBq/µmol) [(131)I]MIBG was obtained in 72.3 ± 3% (n = 3) radiochemical yield and 97.3 ± 2% (n = 3) radiochemical purity. The whole preparation could be finished in less than 10 min. According to this method, a kit for the preparation of (123)I-MIBG and (131)I-MIBG is currently being developed.

Background The prediction accuracy of several linear genomic prediction models, which have previously been used for within-line genomic prediction, was evaluated for multi-line genomic prediction. Methods Compared to a conventional BLUP (best linear unbiased prediction) model using pedigree data, we evaluated the following genomic prediction models: genome-enabled BLUP (GBLUP), ridge regression BLUP (RRBLUP), principal component analysis followed by ridge regression (RRPCA), BayesC and Bayesian stochastic search variable selection. Prediction accuracy was measured as the correlation between predicted breeding values and observed phenotypes divided by the square root of the heritability. The data used concerned laying hens with phenotypes for number of eggs in the first production period and known genotypes. The hens were from two closely-related brown layer lines (B1 and B2), and a third distantly-related white layer line (W1). Lines had 1004 to 1023 training animals and 238 to 240 validation animals. Training datasets consisted of animals of either single lines, or a combination of two or all three lines, and had 30 508 to 45 974 segregating single nucleotide polymorphisms. Results Genomic prediction models yielded 0.13 to 0.16 higher accuracies than pedigree-based BLUP. When excluding the line itself from the training dataset, genomic predictions were generally inaccurate. Use of multiple lines marginally improved prediction accuracy for B2 but did not affect or slightly decreased prediction accuracy for B1 and W1. Differences between models were generally small except for RRPCA which gave considerably higher accuracies for B2. Correlations between genomic predictions from different methods were higher than 0.96 for W1 and higher than 0.88 for B1 and B2. The greater differences between methods for B1 and B2 were probably due to the lower accuracy of predictions for B1 (~0.45) and B2 (~0.40) compared to W1 (~0.76). Conclusions Multi-line genomic prediction did not affect or slightly improved prediction accuracy for closely-related lines. For distantly-related lines, multi-line genomic prediction yielded similar or slightly lower accuracies than single-line genomic prediction. Bayesian variable selection and GBLUP generally gave similar accuracies. Overall, RRPCA yielded the greatest accuracies for two lines, suggesting that using PCA helps to alleviate the “n ≪ p” problem in genomic prediction. Electronic supplementary material The online version of this article (doi:10.1186/s12711-014-0057-5) contains supplementary material, which is available to authorized users.

Background Most studies on genomic prediction with reference populations that include multiple lines or breeds have used linear models. Data heterogeneity due to using multiple populations may conflict with model assumptions used in linear regression methods. Methods In an attempt to alleviate potential discrepancies between assumptions of linear models and multi-population data, two types of alternative models were used: (1) a multi-trait genomic best linear unbiased prediction (GBLUP) model that modelled trait by line combinations as separate but correlated traits and (2) non-linear models based on kernel learning. These models were compared to conventional linear models for genomic prediction for two lines of brown layer hens (B1 and B2) and one line of white hens (W1). The three lines each had 1004 to 1023 training and 238 to 240 validation animals. Prediction accuracy was evaluated by estimating the correlation between observed phenotypes and predicted breeding values. Results When the training dataset included only data from the evaluated line, non-linear models yielded at best a similar accuracy as linear models. In some cases, when adding a distantly related line, the linear models showed a slight decrease in performance, while non-linear models generally showed no change in accuracy. When only information from a closely related line was used for training, linear models and non-linear radial basis function (RBF) kernel models performed similarly. The multi-trait GBLUP model took advantage of the estimated genetic correlations between the lines. Combining linear and non-linear models improved the accuracy of multi-line genomic prediction. Conclusions Linear models and non-linear RBF models performed very similarly for genomic prediction, despite the expectation that non-linear models could deal better with the heterogeneous multi-population data. This heterogeneity of the data can be overcome by modelling trait by line combinations as separate but correlated traits, which avoids the occasional occurrence of large negative accuracies when the evaluated line was not included in the training dataset. Furthermore, when using a multi-line training dataset, non-linear models provided information on the genotype data that was complementary to the linear models, which indicates that the underlying data distributions of the three studied lines were indeed heterogeneous. Electronic supplementary material The online version of this article (doi:10.1186/s12711-014-0075-3) contains supplementary material, which is available to authorized users.

Modeling the second-order statistics of articulatory trajectories is likely to improve the performance in classifying phone segments compared to using only linear combinations of MFCCs. Nevertheless, the extremely high dimensionality of the feature space spanned by a combination of monomials of degree-1 and degree-2 makes it difficult to effectively exploit the discriminative information in the full covariance matrix. This paper proposes a novel algorithm, dubbed Knowledge-based Quadratic Discriminant Analysis (KnQDA), for reducing the number of dimensions of the space spanned by degree-1 and degree-2 monomials by using phonetic knowledge for selecting the set of degree-2 monomials that are most likely to improve classification. KnQDA seeks a trade-off between overfitting and undertraining, which further improves the learnability. Binary classifications on all pairs of phones in TIMIT show the effectiveness of the proposed method, especially on those phone pairs that overlap strongly in the linear feature space.

Item does not contain fulltext Interspeech 2012

MDCT/IMDCT has been widely adopted to transform an audio sequence from time domain to transform domain by various audio codec standards. This paper presents a unified algorithm and its hardware design for cosine modulated filter bank. In algorithm derivation, both MDCT and IMDCT are first converted to a half size DCT-IV with input or output permutation. The DCT-IV is then realized by a fast DCT-II algorithm. Both radix-3 and radix-2 DCT-II algorithms are analyzed and a unified computing kernel is concluded.

Since the emergence of peer-to-peer (P2P) networking in the last 90s, P2P traffic, being a significant portion of the network traffic today, has constituted a highly desirable class for identification. How to improve the accuracy of the P2P traffic identification efficiently is still a challenging problem. The support vector machine (SVM) is a powerful learning mechanism and has shown remarkable success in many applications. In this paper, we propose a new approach for P2P traffic identification, which uses the support vector machine and a new technology called smooth processing. The experiments of identifying P2P traffic show that the generalization performance and the accuracy of identification are improved significantly compared to that of the traditional methods

An improved method for transient sonar signal classification is presented. In the ocean, noise exists nearly everywhere and the accuracy of classifying sonar signals is decreased to some extent. To remove the noise's negative effect, this algorithm is specially designed to extract the robust signal feature in the environment with low SNR. Additionally, the amplitude of the wavelet coefficient is always regarded as the unique standard for feature extraction. This algorithm combines the class separability criterion with the amplitude of the wavelet coefficients in order to choose both the most principal and most discriminative features of the transient sonar signals. Then the features are tested by the original DARPA data set and modified data set contaminated by a relatively strong noise with the back-propagation neural network.