Rapid joint speaker and noise compensation for robust speech recognition

For speech recognition, mismatches between training and testing for speaker and noise are normally handled separately. The work presented in this paper aims at jointly applying speaker adaptation and model-based noise compensation by embedding speaker adaptation as part of the noise mismatch function. The proposed method gives a faster and more optimum adaptation compared to compensating for these two factors separately. It is also more consistent with respect to the basic assumptions of speaker and noise adaptation. Experimental results show significant and consistent gains from the proposed method. © 2011 IEEE.

Structured discriminative models for noise robust continuous speech recognition

Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features extracted from the observation sequence, and hypothesised word sequence. In previous work these discriminative models have been combined with features derived from generative models for noise-robust speech recognition for continuous digits. This paper extends this work to medium to large vocabulary tasks. The form of the score-space extracted using the generative models, and parameter tying of the discriminative model, are both discussed. Update formulae for both conditional maximum likelihood and minimum Bayes' risk training are described. Experimental results are presented on small and medium to large vocabulary noise-corrupted speech recognition tasks: AURORA 2 and 4. © 2011 IEEE.

Structured precision modelling with Cholesky basis superposition for speech recognition

Structured precision modelling is an important approach to improve the intra-frame correlation modelling of the standard HMM, where Gaussian mixture model with diagonal covariance are used. Previous work has all been focused on direct structured representation of the precision matrices. In this paper, a new framework is proposed, where the structure of the Cholesky square root of the precision matrix is investigated, referred to as Cholesky Basis Superposition (CBS). Each Cholesky matrix associated with a particular Gaussian distribution is represented as a linear combination of a set of Gaussian independent basis upper-triangular matrices. Efficient optimization methods are derived for both combination weights and basis matrices. Experiments on a Chinese dictation task showed that the proposed approach can significantly outperformed the direct structured precision modelling with similar number of parameters as well as full covariance modelling. © 2011 IEEE.

An evaluation of volumetric interest points

This paper presents the first performance evaluation of interest points on scalar volumetric data. Such data encodes 3D shape, a fundamental property of objects. The use of another such property, texture (i.e. 2D surface colouration), or appearance, for object detection, recognition and registration has been well studied; 3D shape less so. However, the increasing prevalence of depth sensors and the diminishing returns to be had from appearance alone have seen a surge in shape-based methods. In this work we investigate the performance of several detectors of interest points in volumetric data, in terms of repeatability, number and nature of interest points. Such methods form the first step in many shape-based applications. Our detailed comparison, with both quantitative and qualitative measures on synthetic and real 3D data, both point-based and volumetric, aids readers in selecting a method suitable for their application. © 2011 IEEE.

Coarse-level object recognition using interlevel products of complex wavelets

This paper introduces the Interlevel Product (ILP) which is a transform based upon the Dual-Tree Complex Wavelet. Coefficients of the ILP have complex values whose magnitudes indicate the amplitude of multilevel features, and whose phases indicate the nature of these features (e.g. ridges vs. edges). In particular, the phases of ILP coefficients are approximately invariant to small shifts in the original images. We accordingly introduce this transform as a solution to coarse scale template matching, where alignment concerns between decimation of a target and decimation of a larger search image can be mitigated, and computational efficiency can be maintained. Furthermore, template matching with ILP coefficients can provide several intuitive "near-matches" that may be of interest in image retrieval applications. © 2005 IEEE.