This paper introduces a new optimization-based approach to Sparse Imputation/spectral denoising for robust Automatic Speech Recognition (ASR) applications. In particular, we propose an algorithm which couples frame-level optimization and strategic reconciliation of the predictions in a tight manner. We demonstrate that the proposed algorithm outperforms the current state-of-the-art two-step strategy of first optimizing and then averaging across windows, while maintaining the complexity advantages of efficient techniques like the Elastic Net. Our algorithm is also theoretically able to better exploit the properties of a collinear dictionary, which occurs with spectral exemplars from most speech corpora. Through experiments on the Aurora 2.0 noisy digits database, we demonstrate that this new technique achieves significant performance gains (7.67% on average over various SNR levels) over just simply averaging across large number of predictions.

Most supervised classification approaches try to learn patterns in inter class variabilities using training samples. However in the real world, their discriminative power is often diminished, because data is seldom free from irregularities within a class. Apriori modeling of these intra class variabilities poses a challenge even in underwater sidescan sonar images that we consider for object classification in this work. Sparse representation techniques prove particularly useful in this regard because of their data driven approach to model these variabilities. Results on the NSWC sidescan sonar database suggest that sparse representation classifier with zernike magnitude features is significantly robust in the presence of these non-idealities.

This paper presents novel variations of group sparse regularization techniques. We expand upon the Sparse Group LASSO formulation to incorporate different learning techniques for better sparsity enforcement within a group and demonstrate the effectiveness of the algorithms for spectral denoising with applications to robust Automatic Speech Recognition (ASR). In particular, we show that with a strategic selection of groupings greater robustness to noisy speech recognition can be achieved when compared to state-of-the-art techniques like the Fast Iterative Shrinkage Thresholding Algorithm (FISTA) implementation of the Sparse Group LASSO. Moreover, we demonstrate that group sparse regularization techniques can offer significant gains over efficient techniques like the Elastic Net. We also show that the proposed algorithms are effective in exploiting collinear dictionaries to deal with the inherent highly coherent nature of speech spectral segments. Experiments on the Aurora 2.0 continuous digit database and the Aurora 3.0 realistic noisy database demonstrate the performance improvement with the proposed methods, including showing that their execution time is comparable to FISTA, making our algorithms practical for application to a wide range of regularization problems.

Missing data techniques (MDTs) have been widely employed and shown to improve speech recognition results under noisy conditions. This paper presents a new technique which improves upon previously proposed sparse imputation techniques relying on the least absolute shrinkage and selection operator (LASSO). LASSO is widely employed in compressive sensing problems. However, the problem with LASSO is that it does not satisfy oracle properties in the event of a highly collinear dictionary, which happens with features extracted from most speech corpora. When we say that a variable selection procedure satisfies the oracle properties, we mean that it enjoys the same performance as though the underlying true model is known. Through experiments on the Aurora 2.0 noisy spoken digits database, we demonstrate that the Least Angle Regression implementation of the Elastic Net (LARS-EN) algorithm is able to better exploit the properties of a collinear dictionary, and thus is significantly more robust in terms of basis selection when compared to LASSO on the continuous digit recognition task with estimated mask. In addition, we investigate the effects and benefits of a good measure of sparsity on speech recognition rates. In particular, we demonstrate that a good measure of sparsity greatly improves speech recognition rates, and that the LARS modification of LASSO and LARS-EN can be terminated early to achieve improved recognition results, even though the estimation error is increased.

In this paper, we present a systems approach for channel mod-eling of an Automatic Speech Recognition (ASR) system. This can have implications in improving speech recognition com-ponents, such as through discriminative language modeling. We simulate the ASR corruption using a phrase-based machine translation system trained between the reference phoneme and output phoneme sequences of a real ASR. We demonstrate that local optimization on the quality of phoneme-to-phoneme map-pings does not directly translate to overall improvement of the entire model. However, we are still able to capitalize on contex-tual information of the phonemes which a simple acoustic dis-tance model is not able to accomplish. Hence we show that the use of longer context results in a significantly improved model of the ASR channel.