Luciano Fissore

TL;DR: Current advances related to automatic speech recognition (ASR) and spoken language systems and deficiencies in dealing with variation naturally present in speech are outlined.

TL;DR: This paper presents a front-end consisting of an Artificial Neural Network architecture trained with multilingual corpora that produces discriminant features that can be used as observation vectors for language or task dependent recognizers.

TL;DR: In this paper, a dual-step, text-independent, language-independent speaker voice-print creation and speaker recognition method is presented, where a neural network-based technique is used in the first step and a Markov model-based approach is used for the second step.

TL;DR: A large-vocabulary isolated-word recognition system based on the hypothesize-and-test paradigm with a complexity reduction of about 73% can be achieved by using the two-pass approach with respect to the direct approach, while the recognition accuracy remains comparable.

TL;DR: In this paper, a method and a device for recognition of isolated words in large vocabularies are described, wherein recognition is performed through two sequential steps using neural networks and Markov models techniques, respectively, and the results of both techniques are adequately combined so as to improve recognition accuracy.