Lecture: Automatic Speech Recognition: From Statistical Decision Theory to Machine Learning and Neural Networks.

Will be taught by Professor Hermann Ney of the RWTH University (Germany). The seminar is aimed at undergraduate, master, and doctoral students with knowledge in pattern recognition and / or speech processing.

Quan?

27/04/2016 de 08:00 a 10:00 (Europe/Madrid / UTC200)

On?

UPC Campus Nord Building D5. MERIT Room D5-010

Afegiu l'esdeveniment al calendari

iCal

Abstract:

The last 40 years have seen a dramatic progress in machine learning and  statistical methods for speech and language processing like speech  recognition, handwriting recognition and machine translation. Most of the key statistical concepts had originally been developed for speech recognition. Examples of such key concepts are the Bayes decision rule for minimum error rate and probabilistic approaches to acoustic modelling (e.g.hidden Markov models) and language modelling. Recently the accuracy of speech recognition could be improved significantly by the use of artificial neural networks, such as deep feedforward multi-layer perceptrons and recurrent neural networks (incl. long short-term memory extension). We will discuss these approaches in detail and how they fit into the probabilistic approach.