Anúncios
Local do teste de repescagem
2 julho 2009, 17:58 • Isabel Maria Martins Trancoso
Sala V1.24
Data: 7 de Julho
Início: 9h00
Fim: 10h30
Horário de Dúvidas:
6ª feira, 3 de Julho: 9h-11h
2ª feira, 6 de Julho: 8h-9h
Palestra - Prof. Maxine Eskenazi
23 junho 2009, 07:55 • Isabel Maria Martins Trancoso
Language Technologies and CALL
14:00, Thursday, June 25th, 2009
Room VA2, building of Civil Engineering, IST-Alameda
Speaker
Maxine Eskenazi, Carnegie Mellon University, USA
Abstract
Language Technologies are still in their early stages of use as far as
Computer-assisted Language Learning (CALL) is concerned. But some
notable progress has been made and some systems have appeared. This
talk will discuss three applications that I have developed:
NativeAccent, Let's Go Lexical Entrainment, and REAP. We will look at
how each one uses language technologies. We will also discuss the
challenges that each system overcomes when it combines the need to
serve the language learner well with the present state of each
technology. We will also examine the learning science questions that
are raised when the interface between the technology and the student
is created.
Bio
Maxine S. Eskenazi received her Bachelor of Arts degree in Modern
Languages from Carnegie-Mellon University in 1973. She received her
DEA (Diplome d'Etudes Approfondies - equiv. Masters) in Linguistics
from the University of Paris VII in 1981 and her Doctorat de Troisieme
Cycle in Computer Science from the University of Paris XI in 1984. Her
thesis was on "Caracterisation acoustique des voyelles francaises en
vue de leur reconnaissance automatique" and her thesis advisor was
Jean-Sylvain Lienard. She has been President and Chief Technical
Officer of the Carnegie Speech™ Company (2001 - ). Carnegie Speech™ is
a CMU spinoff. She is presently Associate Teaching Professor in the
Language Technologies Institute of the School of Computer Science of
Carnegie Mellon University. From 1980 to 1994 she worked as a grad
student and then a tenured researcher at LIMSI-CNRS in Orsay, France.
Monografias
12 junho 2009, 16:58 • Isabel Maria Martins Trancoso
A apresentação das monografias terá lugar no anfiteatro AM.
11h00 - g03
11h30 - g04
12h00 - g08
14h00 - g06
14h30 - g09
15h00 - g02
15h30 - g15
16h00 - g11
16h30 - g10a
17h00 - g14
17h30 - g10b
18h00 - g07
18h30 - g05
Palestra - Prof. Alan Black
5 junho 2009, 13:46 • Isabel Maria Martins Trancoso
June 5th, 15h, Room Va4
This talk will look at the past, present and future of speech synthesis and how it relates to speech processing development in general. Specifically I will outline the advances in synthesis technology giving analogies to the developments in other speech and language processing fields (e.g. ASR and SMT) where knowledge-based techniques gave way to data-driven techniques, which in turn have pushed both machine learning technologies and later re-introduced techniques to include higher level knowledge in our data-driven approaches.
We will give overviews of diphone, unit selection, statistical parametric synthesis, voice morphing technologies and how synthesis can be optimized for the desired task. We will also address issues of evaluation, both in isolation and when embedded in real tasks. While widening our view of speech processing we will also present the publicly used Let's Go Spoken Dialog System (and its evaluation platform Let's Go Lab), our rapid language adaptation system (CMUSPICE) allowing construction of ASR and TTS support in new languages by non-speech experts and out hands-free real-time two-way speech to speech translation system showing how system integration can cause cross technology innovation.
Adiamento e matéria do 2º teste de Laboratório
14 maio 2009, 09:33 • Isabel Maria Martins Trancoso
Atendendo ao pedido para adiar a data do 2º teste, o mesmo fica marcado para dia 25 de Maio. Farei uma oral à Magda Santos no dia 18.
A matéria de codificação está no Capítulo 7. A matéria de síntese está em algumas secções dos capítulos 14 a 16.