Natural versus artificial scene classification by ordering discrete fourier power spectra

Holistic representations of natural scenes is an effective and powerful source of information for semantic classification and analysis of arbitrary images. Recently, the frequency domain has been successfully exploited to holistically encode the content of natural scenes in order to obtain a robust representation for scene classification. In this paper, we present a new approach to naturalness classification of scenes using frequency domain. The proposed method is based on the ordering of the Discrete Fourier Power Spectra. Features extracted from this ordering are shown sufficient to build a robust holistic representation for Natural vs. Artificial scene classification. Experiments show that the proposed frequency domain method matches the accuracy of other state-of-the-art solutions. © 2008 Springer Berlin Heidelberg.

Cross-Lingual spoken language understanding from unaligned data using discriminative classification models and machine translation

This paper investigates several approaches to bootstrapping a new spoken language understanding (SLU) component in a target language given a large dataset of semantically-annotated utterances in some other source language. The aim is to reduce the cost associated with porting a spoken dialogue system from one language to another by minimising the amount of data required in the target language. Since word-level semantic annotations are costly, Semantic Tuple Classifiers (STCs) are used in conjunction with statistical machine translation models both of which are trained from unaligned data to further reduce development time. The paper presents experiments in which a French SLU component in the tourist information domain is bootstrapped from English data. Results show that training STCs on automatically translated data produced the best performance for predicting the utterance's dialogue act type, however individual slot/value pairs are best predicted by training STCs on the source language and using them to decode translated utterances. © 2010 ISCA.

Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?

Most HMM-based TTS systems use a hard voiced/unvoiced classification to produce a discontinuous F0 signal which is used for the generation of the source-excitation. When a mixed source excitation is used, this decision can be based on two different sources of information: the state-specific MSD-prior of the F0 models, and/or the frame-specific features generated by the aperiodicity model. This paper examines the meaning of these variables in the synthesis process, their interaction, and how they affect the perceived quality of the generated speech The results of several perceptual experiments show that when using mixed excitation, subjects consistently prefer samples with very few or no false unvoiced errors, whereas a reduction in the rate of false voiced errors does not produce any perceptual improvement. This suggests that rather than using any form of hard voiced/unvoiced classification, e.g., the MSD-prior, it is better for synthesis to use a continuous F0 signal and rely on the frame-level soft voiced/unvoiced decision of the aperiodicity model. © 2011 IEEE.

Constrained discriminative mapping transforms for unsupervised speaker adaptation

Discriminative mapping transforms (DMTs) is an approach to robustly adding discriminative training to unsupervised linear adaptation transforms. In unsupervised adaptation DMTs are more robust to unreliable transcriptions than directly estimating adaptation transforms in a discriminative fashion. They were previously proposed for use with MLLR transforms with the associated need to explicitly transform the model parameters. In this work the DMT is extended to CMLLR transforms. As these operate in the feature space, it is only necessary to apply a different linear transform at the front-end rather than modifying the model parameters. This is useful for rapidly changing speakers/environments. The performance of DMTs with CMLLR was evaluated on the WSJ 20k task. Experimental results show that DMTs based on constrained linear transforms yield 3% to 6% relative gain over MLE transforms in unsupervised speaker adaptation. © 2011 IEEE.

The infinite HMM for unsupervised PoS tagging

We extend previous work on fully unsupervised part-of-speech tagging. Using a non-parametric version of the HMM, called the infinite HMM (iHMM), we address the problem of choosing the number of hidden states in unsupervised Markov models for PoS tagging. We experiment with two non-parametric priors, the Dirichlet and Pitman-Yor processes, on the Wall Street Journal dataset using a parallelized implementation of an iHMM inference algorithm. We evaluate the results with a variety of clustering evaluation metrics and achieve equivalent or better performances than previously reported. Building on this promising result we evaluate the output of the unsupervised PoS tagger as a direct replacement for the output of a fully supervised PoS tagger for the task of shallow parsing and compare the two evaluations. © 2009 ACL and AFNLP.

A programme to carry out analysis of variance: two-way classification on Micro 2200

A brief description is given of a program to carry out analysis of variance two-way classification on MICRO 2200, for use in fishery data processing.

Semantic Discriminant mapping for classification and browsing of remote sensing textures and objects

We present a new approach based on Discriminant Analysis to map a high dimensional image feature space onto a subspace which has the following advantages: 1. each dimension corresponds to a semantic likelihood, 2. an efficient and simple multiclass classifier is proposed and 3. it is low dimensional. This mapping is learnt from a given set of labeled images with a class groundtruth. In the new space a classifier is naturally derived which performs as well as a linear SVM. We will show that projecting images in this new space provides a database browsing tool which is meaningful to the user. Results are presented on a remote sensing database with eight classes, made available online. The output semantic space is a low dimensional feature space which opens perspectives for other recognition tasks. © 2005 IEEE.

Classification and choice in product design

Life is full of difficult choices. Everyone has their own way of dealing with these, some effective, some not. The problem is particularly acute in engineering design because of the vast amount of information designers have to process. This paper deals with a subset of this set of problems: the subset of selecting materials and processes, and their links to the design of products. Even these, though, present many of the generic problems of choice, and the challenges in creating tools to assist the designer in making them. The key elements are those of classification, of indexing, of reaching decisions using incomplete data in many different formats, and of devising effective strategies for selection. This final element - that of selection strategies - poses particular challenges. Product design, as an example, is an intricate blend of the technical and (for want of a better word) the aesthetic. To meet these needs, a tool that allows selection by analysis, by analogy, by association and simply by 'browsing' is necessary. An example of such a tool, its successes and remaining challenges, will be described.

Unsupervised intra-lingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to estimate the transcription of the adaptation data. This paper first presents an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for such supplementary acoustic models. This is achieved by defining a mapping between HMM-based synthesis models and ASR-style models, via a two-pass decision tree construction process. Second, it is shown that this mapping also enables unsupervised adaptation of HMM-based speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data. Third, this paper demonstrates how this technique lends itself to the task of unsupervised cross-lingual adaptation of HMM-based speech synthesis models, and explains the advantages of such an approach. Finally, listener evaluations reveal that the proposed unsupervised adaptation methods deliver performance approaching that of supervised adaptation.

Perceptual learning, roving and the unsupervised bias

Perceptual learning improves perception through training. Perceptual learning improves with most stimulus types but fails when . certain stimulus types are mixed during training (roving). This result is surprising because classical supervised and unsupervised neural network models can cope easily with roving conditions. What makes humans so inferior compared to these models? As experimental and conceptual work has shown, human perceptual learning is neither supervised nor unsupervised but reward-based learning. Reward-based learning suffers from the so-called unsupervised bias, i.e., to prevent synaptic " drift" , the . average reward has to be exactly estimated. However, this is impossible when two or more stimulus types with different rewards are presented during training (and the reward is estimated by a running average). For this reason, we propose no learning occurs in roving conditions. However, roving hinders perceptual learning only for combinations of similar stimulus types but not for dissimilar ones. In this latter case, we propose that a critic can estimate the reward for each stimulus type separately. One implication of our analysis is that the critic cannot be located in the visual system. © 2011 Elsevier Ltd.

Bayesian classification of acoustical waveforms under environmental variability

We present in this paper a new multivariate probabilistic approach to Acoustic Pulse Recognition (APR) for tangible interface applications. This model uses Principle Component Analysis (PCA) in a probabilistic framework to classify tapping pulses with a high degree of variability. It was found that this model, achieves a higher robustness to pulse variability than simpler template matching methods, specifically when allowed to train on data containing high variability. © 2011 IEEE.