Evaluation of Speaker Normalization Methods for Vowel Recognition Using Fuzzy ARTMAP and K-NN

A procedure that uses fuzzy ARTMAP and K-Nearest Neighbor (K-NN) categorizers to evaluate intrinsic and extrinsic speaker normalization methods is described. Each classifier is trained on preprocessed, or normalized, vowel tokens from about 30% of the speakers of the Peterson-Barney database, then tested on data from the remaining speakers. Intrinsic normalization methods included one nonscaled, four psychophysical scales (bark, bark with end-correction, mel, ERB), and three log scales, each tested on four different combinations of the fundamental (Fo) and the formants (F1 , F2, F3). For each scale and frequency combination, four extrinsic speaker adaptation schemes were tested: centroid subtraction across all frequencies (CS), centroid subtraction for each frequency (CSi), linear scale (LS), and linear transformation (LT). A total of 32 intrinsic and 128 extrinsic methods were thus compared. Fuzzy ARTMAP and K-NN showed similar trends, with K-NN performing somewhat better and fuzzy ARTMAP requiring about 1/10 as much memory. The optimal intrinsic normalization method was bark scale, or bark with end-correction, using the differences between all frequencies (Diff All). The order of performance for the extrinsic methods was LT, CSi, LS, and CS, with fuzzy AHTMAP performing best using bark scale with Diff All; and K-NN choosing psychophysical measures for all except CSi.

Eliminating Redundant Training Data Using Unsupervised Clustering Techniques

Training data for supervised learning neural networks can be clustered such that the input/output pairs in each cluster are redundant. Redundant training data can adversely affect training time. In this paper we apply two clustering algorithms, ART2 -A and the Generalized Equality Classifier, to identify training data clusters and thus reduce the training data and training time. The approach is demonstrated for a high dimensional nonlinear continuous time mapping. The demonstration shows six-fold decrease in training time at little or no loss of accuracy in the handling of evaluation data.

Speaker Normalization Methods for Vowel Cognition: Comparative Analysis Using Neural Network and Nearest Neighbor Classifiers

Intrinsic and extrinsic speaker normalization methods are systematically compared using a neural network (fuzzy ARTMAP) and L1 and L2 K-Nearest Neighbor (K-NN) categorizers trained and tested on disjoint sets of speakers of the Peterson-Barney vowel database. Intrinsic methods include one nonscaled, four psychophysical scales (bark, bark with endcorrection, mel, ERB), and three log scales, each tested on four combinations of F0 , F1, F2, F3. Extrinsic methods include four speaker adaptation schemes, each combined with the 32 intrinsic methods: centroid subtraction across all frequencies (CS), centroid subtraction for each frequency (CSi), linear scale (LS), and linear transformation (LT). ARTMAP and KNN show similar trends, with K-NN performing better, but requiring about ten times as much memory. The optimal intrinsic normalization method is bark scale, or bark with endcorrection, using the differences between all frequencies (Diff All). The order of performance for the extrinsic methods is LT, CSi, LS, and CS, with fuzzy ARTMAP performing best using bark scale with Diff All; and K-NN choosing psychophysical measures for all except CSi.

The impact of learning context on the acquisition of sociopragmatic variation patterns in non-native speaker teachers of English

The study is a cross-linguistic, cross-sectional investigation of the impact of learning contexts on the acquisition of sociopragmatic variation patterns and the subsequent enactment of compound identities. The informants are 20 non-native speaker teachers of English from a range of 10 European countries. They are all primarily mono-contextual foreign language learners/users of English: however, they differ with respect to the length of time accumulated in a target language environment. This allows for three groups to be established – those who have accumulated 60 days or less; those with between 90 days and one year and the final group, all of whom have accumulated in excess of one year. In order to foster the dismantling of the monolith of learning context, both learning contexts under consideration – i.e. the foreign language context and submersion context are broken down into micro-contexts which I refer to as loci of learning. For the purpose of this study, two loci are considered: the institutional and the conversational locus. In order to make a correlation between the impact of learning contexts and loci of learning on the acquisition of sociopragmatic variation patterns, a two-fold study is conducted. The first stage is the completion of a highly detailed language contact profile (LCP) questionnaire. This provides extensive biographical information regarding language learning history and is a powerful tool in illuminating the intensity of contact with the L2 that learners experience in both contexts as well as shedding light on the loci of learning to which learners are exposed in both contexts. Following the completion of the LCP, the informants take part in two role plays which require the enactment of differential identities when engaged in a speech event of asking for advice. The enactment of identities then undergoes a strategic and linguistic analysis in order to investigate if and how differences in the enactment of compound identities are indexed in language. Results indicate that learning context has a considerable impact not only on how identity is indexed in language, but also on the nature of identities enacted. Informants with very low levels of crosscontextuality index identity through strategic means – i.e. levels of directness and conventionality; however greater degrees of cross-contextuality give rise to the indexing of differential identities linguistically by means of speaker/hearer orientation and (non-) solidary moves. When it comes to the nature of identity enacted, it seems that more time spent in intense contact with native speakers in a range of loci of learning allows learners to enact their core identity; whereas low levels of contact with over-exposure to the institutional locus of learning fosters the enactment of generic identities.

On the role of molecular clustering on infrared absorption line shapes of acetylene in a supersonic expansion

A supersonic expansion containing acetylene seeded into Ar and produced from a circular nozzle is investigated using CW/cavity ring down spectroscopy, in the 1.5 μm range. The results, also involving experiments with pure acetylene and acetylene-He expansions, as well as slit nozzles, demonstrate that the denser central section in the expansion is slightly heated by the formation of acetylene aggregates, resulting into a dip in the monomer absorption line profiles. Acetylene-Ar aggregates are also formed at the edge of the circular nozzle expansion cone. © 2008 Elsevier B.V. All rights reserved.

UNC-6 (netrin) stabilizes oscillatory clustering of the UNC-40 (DCC) receptor to orient polarity.

The receptor deleted in colorectal cancer (DCC) directs dynamic polarizing activities in animals toward its extracellular ligand netrin. How DCC polarizes toward netrin is poorly understood. By performing live-cell imaging of the DCC orthologue UNC-40 during anchor cell invasion in Caenorhabditis elegans, we have found that UNC-40 clusters, recruits F-actin effectors, and generates F-actin in the absence of UNC-6 (netrin). Time-lapse analyses revealed that UNC-40 clusters assemble, disassemble, and reform at periodic intervals in different regions of the cell membrane. This oscillatory behavior indicates that UNC-40 clusters through a mechanism involving interlinked positive (formation) and negative (disassembly) feedback. We show that endogenous UNC-6 and ectopically provided UNC-6 orient and stabilize UNC-40 clustering. Furthermore, the UNC-40-binding protein MADD-2 (a TRIM family protein) promotes ligand-independent clustering and robust UNC-40 polarization toward UNC-6. Together, our data suggest that UNC-6 (netrin) directs polarized responses by stabilizing UNC-40 clustering. We propose that ligand-independent UNC-40 clustering provides a robust and adaptable mechanism to polarize toward netrin.

Multilevel approaches applied to the capacitated clustering problem

This paper presents two multilevel refinement algorithms for the capacitated clustering problem. Multilevel refinement is a collaborative technique capable of significantly aiding the solution process for optimisation problems. The central methodologies of the technique are filtering solutions from the search space and reducing the level of problem detail to be considered at each level of the solution process. The first multilevel algorithm uses a simple tabu search while the other executes a standard local search procedure. Both algorithms demonstrate that the multilevel technique is capable of aiding the solution process for this combinatorial optimisation problem.

Robust Speaker Recognition in Noisy Conditions

This paper investigates the problem of speaker identi-fication and verification in noisy conditions, assuming that speechsignals are corrupted by environmental noise, but knowledgeabout the noise characteristics is not available. This research ismotivated in part by the potential application of speaker recog-nition technologies on handheld devices or the Internet. Whilethe technologies promise an additional biometric layer of securityto protect the user, the practical implementation of such systemsfaces many challenges. One of these is environmental noise. Due tothe mobile nature of such systems, the noise sources can be highlytime-varying and potentially unknown. This raises the require-ment for noise robustness in the absence of information about thenoise. This paper describes a method that combines multicondi-tion model training and missing-feature theory to model noisewith unknown temporal-spectral characteristics. Multiconditiontraining is conducted using simulated noisy data with limitednoise variation, providing a “coarse” compensation for the noise,and missing-feature theory is applied to refine the compensationby ignoring noise variation outside the given training conditions,thereby reducing the training and testing mismatch. This paperis focused on several issues relating to the implementation of thenew model for real-world applications. These include the gener-ation of multicondition training data to model noisy speech, thecombination of different training data to optimize the recognitionperformance, and the reduction of the model’s complexity. Thenew algorithm was tested using two databases with simulated andrealistic noisy speech data. The first database is a redevelopmentof the TIMIT database by rerecording the data in the presence ofvarious noise types, used to test the model for speaker identifica-tion with a focus on the varieties of noise. The second database isa handheld-device database collected in realistic noisy conditions,used to further validate the model for real-world speaker verifica-tion. The new model is compared to baseline systems and is foundto achieve lower error rates.

Gene selection by cooperative competition clustering

Clustering analysis of data from DNA microarray hybridization studies is an essential task for identifying biologically relevant groups of genes. Attribute cluster algorithm (ACA) has provided an attractive way to group and select meaningful genes. However, ACA needs much prior knowledge about the genes to set the number of clusters. In practical applications, if the number of clusters is misspecified, the performance of the ACA will deteriorate rapidly. In fact, it is a very demanding to do that because of our little knowledge. We propose the Cooperative Competition Cluster Algorithm (CCCA) in this paper. In the algorithm, we assume that both cooperation and competition exist simultaneously between clusters in the process of clustering. By using this principle of Cooperative Competition, the number of clusters can be found in the process of clustering. Experimental results on a synthetic and gene expression data are demonstrated. The results show that CCCA can choose the number of clusters automatically and get excellent performance with respect to other competing methods.