GSLT: Speech Technology 1

Nordic Graduate School of Language Technology
Graduate School of Language Technology

Back to Speech Technology 1 home page

Closing Seminar
19/1 – 21/1, 2005

Directions: http://www.speech.kth.se/info/location.html

Each participant has to make their own hotel reservation. Mention the distributed reference number. Hotel Arcadia is close to KTH.

http://www.elite.se/eng/hotell/stockholm/arcadia/

Closing Seminar Program

Time	Author	Subject Preliminary Title	2-3 Reviewers	Adviser
Wednesday 19/1
13.00 Introduction
13.30	Erik Eriksson	Formants and their dynamics: Useful for speaker identification?	Ulla Bjursäter Björn Kristinsson Lisa Gustavsson	David House
14.00	Henrik Oxhammar Kristina Nilsson	Is this question a question? Final rise as an interrogative marker in Swedish	Gunilla Svanfeldt Lilja Øvrelid Atelach Alemu	David House
14.30	Coffee
15.00	Thomas Hansen	CALL: Linguistic reality and technological limitations - brains vs chips	Erik Eriksson Gunilla Svanfeldt	David House
15.30	Ulla Bjursäter	Speaking styles and phonetic variation	Erik Eriksson Preben Wik Ansis Ataols Berzins	David House
16.00	Lilja Øvrelid	Prosodic resolution of syntactic ambiguity	Karin Cavallin Gintaras Barisevicius Ebba Gustavii	David House
16.30	Karin Cavallin	Prosody in feedback Issues on feedback possibly appropriate for human-computer interaction	Thomas Hansen Ulla Bjursäter	David House
17.00-18.00	Phonetic practical exercise discussion
Thursday 20/1
09.00	Ansis Ataols Berzins	Distances between phonemes?	Thomas Hansen Magnus Sahlgren	Torbjørn Svendsen
09.30	Gintaras Barisevicius	Text-independent speaker verification	Johan Hall Ansis Ataols Berzins	Torbjørn Svendsen
10.00	Johan Hall	Can a syntactic language model be incorporated into an HMM-based ASR framework?	Marcus Uneson Ilya Oparin Atelach Alemu	Torbjørn Svendsen
10.30-11.00	Coffee
11.30	Lisa Gustavsson	Aspects on speech perception as the model for ASR	Henrik Oxhammar Karin Cavallin	Torbjørn Svendsen
12.00	Marcus Uneson	An Introduction to Dynamic Bayesian Networks for Automatic Speech Recognition	Ilya Oparin Gintaras Barisevicius Ebba Gustavii	Torbjørn Svendsen
12.30-14.00	Lunch
14.00	Ilya Oparin	Language modeling for ASR: Issues regarding building a Russian language model	Marcus Uneson Björn Kristinsson	Torbjørn Svendsen
14.30-16.00	Recognition practical exercise discussion, Coffee
16.00	Björn Kristinsson	Automatic Phonetisation for Icelandic	Geir Gunnarsson Johan Hall	Björn Granström
16.30	Geir Gunnarsson	Data-driven methods in speech synthesis	Eva Forsbom Fredrik Olsson Kristina Nilsson	Rolf Carlson
17.00-18.00	Synthesis practical exercise discussion
18.00--	An evening at the department
Friday 21/1
09.00	Gunilla Svanfeldt Preben Wik	Implementation issues regarding eye-gaze in synthetic faces	Pontus Wärnestål Henrik Oxhammar Fredrik Olsson	Björn Granström
09.30	Atelach Alemu Ebba Gustavii Eva Forsbom	Distribution and Acoustic Features of Extra Linguistic Sounds in the Waxholm Corpus	Lisa Gustavsson Lilja Øvrelid	Rolf Carlson
10.00	Anna Hjalmarsson	Adaptive Spoken Dialogue Systems	Pontus Wärnestål Eva Forsbom	Rolf Carlson
10.30-11.45	Coffee, Lab visit
11.45-13.00	Lunch
13.00	Fredrik Olsson Magnus Sahlgren	Content realisation in noisy environments	Anna Hjalmarsson Geir Gunnarsson Kristina Nilsson	Rolf Carlson
13.30	Pontus Wärnestål	Behaviors and Layers in Spoken Dialogue Systems	Anna Hjalmarsson Preben Wik Magnus Sahlgren	Rolf Carlson
14.00	Final remarks, Evaluation

Link to the Closing seminar January 2003 with links to papers

Link to the Closing seminar January 2002 with links to papers.

Back to Speech Technology 1 home page