In this paper we study various decorrelation methods for the features used in speech recognition and we compare the performance of each one by running several tests with a speech database. First of all we study the ...

The usual approach to automatic continuous speech recognition is what can be called the acoustic-phonetic modelling approach. In this approach, voice is considered to hold two different kinds of information acoustic and ...

A common intermediate language representation in neural machine translation can be used to extend bilingual systems by incremental training. We propose a new architecture based on introducing an interlingual loss as an ...

The introduction of a simple correction term in gradient algorithms for adaptive IIR filtering is shown to improve their convergence and robustness. The error surface, i.e. the mean-squared value of the output error as a ...

The inclusion of a pole-zero vector predictor in the backward loop of an AVPC coder[1] is approached . We hope to reach the same profit shown by the pole-zero predictor in the ADPCM-CCITT standard. By using a VLMS transversal ...

The aim of this paper is to investigate the benefit of combining both language and acoustic modelling for speaker diarization. Although conventional systems only use acoustic features, in some scenarios linguistic data ...

Neural Networks applied to Machine Translation need a finite vocabulary to express textual information as a sequence of discrete tokens. The currently dominant subword vocabularies exploit statistically-discovered common ...

This paper describes an unified messaging system which joins voice mail, fax and e-mail access. Its architecture consists in a group of independent servers, each offering an interface between the unified mailbox and an ...