GSLT: Speech Technology 1

Closing Seminar 14/1 – 16/1 2002

Department for Speech, Music and Hearing, KTH

Directions with map

Institutionen för tal, musik och hörsel
Drottning Kristinas väg 31
SE-100 44 STOCKHOLM
SWEDEN
Tfn: +46 (8) 790 7879

Monday 14/1/2002

13.00

Welcome

13.15

Practical assignment – Phonetic analysis

15.00

Coffee

15.30-17.00

Prosody and Emotions

 

Author

Title

Reviewer1

Reviewer2

15.30

Cecilia Hemming

Phonetic cues for phrase boundaries and discourse finality

Sara Rydin

Per-Anders Jande

16.00

Jarmo Välikangas

FIN-ToBI  Tones and Break Indices for Finnish

Janna Khegai

Sofia Gustafson-Capkova

16.30

Sofia Gustafson-Capkova

Emotions in speech - tagging and phonetic correlates

Sara Rydin

Loredana Cerrato

Tuesday 15/1/2002

09.00-10.30

Synthesis

 

Author

Title

Reviewer1

Reviewer2

09.00

Audur Thorunn Rognvaldsdottir

Speech Synthesis for Icelandic

 Klas Prytz

Jarmo Välikangas

09.30

Janna Khegai

Phonetic grammars for GF

Leif Grönqvist

Jonas Lindh

10.00

Jonas Lindh

Introductory Evaluation of the Swedish Realspeak System

Klas Prytz

Susanne Ekeklint

10.30-11.00

Coffee

11.00-12.30

Practical assignments – Synthesis and Telephone based Dialog Systems

12.30-14.00

Lunch

14.00-15.00

Multimodality

 

Author

Title

Reviewer1

Reviewer2

14.00

Loredana Cerrato

Issues related to the functions of visual displays in multimodal communication

Audur Thorunn Rognvaldsdottir

Cecilia Hemming

14.30

Mustapha Skhiri

Visual Cues in Speech Perception

Loredana Cerrato

Cecilia Hemming

15.00

Coffee

15.30 – 16.30

Recognition

15.30

Per Anders Jande

Linguistic Knowledge in High Level Automatic Speech Processing

Leif Grönqvist

Audur Thorunn Rognvaldsdottir

16.00

Sara Rydin

Text dependent and text independent speaker verification systems. Technology and applications

Mustapha Skiri

Jonas Lindh

16.30 – 18.00

Discussion

18.00 -

Something to eat…

Wednesday 15/1/2002

09.00 – 10.30

Recognition

 

Author

Title

Reviewer1

Reviewer2

09.00

Klas Prytz

Dynamic Time Warping

Janna Khegai

Per-Anders Jande

09.30

Leif Grönqvist

Similarities and differences between the statistical models for speech recognition and parts-of-speech tagging

Sofia Gustafson-Capkova

Fredrik Kronlid

 

Dialogue Systems

10.00

Author

Title

Reviewer1

Reviewer2

 

Fredrik Kronlid
Susanne Ekeklint

The need for robustness in dialog systems

Mustapha Skiri

Jarmo Valikangas

10.30 – 12.30

Coffee, Discussion and Evaluation

12.30 – 14.00

Lunch