Feature statistics normalization techniques have been shown to be very successful in improving the noise robustness of a speech recognition system. In this paper, we propose an associative scheme in order to obtain a more accurate estimate of the statistical information in these techniques. By properly integrating codebook and utterance knowledge, the resulting associative cepstral mean subtrac...

This paper addresses the issue of text normalization, an important yet often overlooked problem in natural language processing. By text normalization, we mean converting ‘informally inputted’ text into the canonical form, by eliminating ‘noises’ in the text and detecting paragraph and sentence boundaries in the text. Previously, text normalization issues were often undertaken in an ad-hoc fashi...

In this paper we describe some characteristics of the acoustic modeling used in the Philips continuous-speech recognition system for the DARPA Hub-4 1997 evaluation, which are related to robustness issues. We aimed at a conceptually simple system: We trained two model sets on 70 hours of the Hub-4 training data, one for within-word and one for crossword decoding. These model sets were used for ...

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot exploit many levels of abstract representations. We introduce self-normalizin...

It is well-known that additive and channel noise cause shift and scaling in MFCC features. Empirical normalization techniques to estimate and compensate for the effects, such as cepstral mean subtraction and variance normalization, have been shown to be useful. However, these empirical estimate may not be optimal. In this paper, we approach the problem from two directions, 1) use a more robust ...

In this paper we describe some characteristics of the acoustic modeling used in the Philips continuous-speech recognition system for the DARPA Hub-4 1997 evaluation, which are related to robustness issues. We aimed at a conceptually simple system: We trained two model sets on 70 hours of the Hub4 training data, one for within-word and one for cross-word decoding. These model sets were used for ...

We consider properties of revisions to mean square optimal concurrent estimates of unobserved components, e.g., seasonal adjustments or trends, obtained by ARIMA model-based signal extraction methods like those used by SEATS. Concurrent estimates, i.e., the estimate for the most recent month (or quarter), are updated whenever future observations become available, and the difference between the ...

Abstract : In this paper we derive a new adaptive filtering algorithm. Starting from a general square−root formulation [1], we introduce a normalization transform to the updating scheme of the block−diagonal adaptive algorithm presented in [1]. This algorithm is efficiently implemented with a low complexity, the resulting algorithm is similar to the NLMS one. Simulations, in the context of mult...