Joint uncertainty decoding (JUD) is an effective model-based noise compensation technique for conventional Gaussian mixture model (GMM) based speech recognition systems. In this paper, we apply JUD to subspace Gaussian mixture model (SGMM) based acoustic models. The total number of Gaussians in the SGMM acoustic model is usually much larger than for conventional GMMs, which limits the applicati...

Recent studies have shown that speech recognizers may benefit from data in languages other than the target language through efficient acoustic modelor feature-level adaptation. Crosslingual Tandem-Subspace Gaussian Mixture Models (SGMM) are successfully able to combine acoustic modeland featurelevel adaptation techniques. More specifically, we focus on under-resourced languages (Afrikaans in ou...

CD1 proteins are unique in their ability to present lipid Ags to T cells. Human CD1b shares significant amino acid homology with mouse CD1d1, which contains an unusual putative Ag-binding groove formed by two large hydrophobic pockets, A' and F'. We investigated the function of the amino acid residues that line the A' and F' pockets of CD1b by engineering 36 alanine-substitution mutants and ana...

Nonnative speech recognition is becoming more and more important as many speech applications are deployed world wide. Meanwhile, due to the large population of nonnative speakers, speaker adaptation remains the most practical way for providing high performance speech services. Subspace Gaussian Mixture Model (SGMM) has recently been shown to yield superior performance on various native speech r...

This paper describes experimental results of applying Subspace Gaussian Mixture Models (SGMMs) in two completely diverse acoustic scenarios: (a) for Large Vocabulary Continuous Speech Recognition (LVCSR) task over (well-resourced) English meeting data and, (b) for acoustic modeling of underresourced Afrikaans telephone data. In both cases, the performance of SGMM models is compared with a conve...

It is well-known that the performance of acoustic-to-articulatory inversion improves by smoothing the articulatory trajectories estimated using Gaussian mixture model (GMM) mapping (denoted by GMM + Smoothing). GMM + Smoothing also provides similar performance with GMM mapping using dynamic features, which integrates smoothing directly in the mapping criterion. Due to the separation between smo...

This paper investigates the problem of verifying the pronunciations of phonemes from continuous utterances collected from impaired children speakers engaged in a speech therapy session. A new pronunciation verification (PV) approach based on the subspace Gaussian mixture model (SGMM) is presented. A single SGMM is trained from test utterances collected from impaired and unimpaired speakers. PV ...

In this paper, we explore how different acoustic modeling techniques can benefit from data in languages other than the target language. We propose an algorithm to perform decision tree state clustering for the recently proposed Kullback-Leibler divergence based hidden Markov models (KL-HMM) and compare it to subspace Gaussian mixture modeling (SGMM). KLHMM can exploit multilingual information i...

This paper considers generalized method of moments (GMM) and sequential GMM (SGMM) estimation dynamic short panel data models. The efficient motivated from the quasi maximum likelihood (QML) can avoid use many instrument variables (IV) for estimation. It be asymptotically as estimators (MLE) when disturbances are normal, more than QML not normal. SGMM, which also incorporates IVs, generalizes m...

Large vocabulary continuous speech recognition is always a difficult task, and it is particularly so for low-resource languages. The scenario we focus on here is having only 1 hour of acoustic training data in the “target” language. This paper presents work on a data borrowing strategy combined with the recently proposed Subspace Gaussian Mixture Model (SGMM). We developed data borrowing strate...