Interspeech 2007 logo
August 27-31, 2007

Antwerp, Belgium
Antwerp Cathedral tower Antwerp main square Antwerp harbour in twilight
printer friendly version of this page

Interspeech 2007 Conference Schedule at a Glance

The program is now final!
Detailed session information can be found by clicking on the session name.

Note: All plenary sessions will take place in the Elisabeth Hall. All tutorials take place in Antwerp University, Rodestraat 14 (rooms R008, R012, R013, R124), see the Map.

Floor plans are available for the conference areas.

Session Code (Key)
First 2 Characters Third Character Last 2 Characters
Day Time Slot Session Type and Room
Tu - Tuesday
We - Wednesday
Th - Thursday
Fr - Friday
B - 10:00 – 12:00
C - 13:30 – 15:30
D - 16:00 – 18:00
O1 - Oral Session in the Elisabeth Hall
O2 - Oral Session in the Darwin Hall
O3 - Oral Session in the Marble Hall
P1x - Poster Session in the Foyer
P2x - Poster Session in the Alpaerts Room
P3x - Poster Session in the Keurvels Room
SS - Special Session in the Astrid Scala 1


Day 1: Tutorial Day, Monday, August 27

R008 R012 R013 R124
08:00
Registration for Morning Tutorials

09:00 Spoken Language Processing by Mind and Machine,
Roger K. Moore and Anne Cutler
The Modulation Spectrum and Its Application to Speech Science and Technology,
Les Atlas, Steven Greenberg and Hynek Hermansky
Voice Quality in Vocal Communication,
Christophe d’Alessandro
Processing Morphologically-Rich Languages,
Katrin Kirchhoff and Ruhi Sarikaya
12:30
Lunch / Registration for Afternoon Tutorials (from 13:00 on)

14:00 A Mathematical Theory of Speech Signals – Beyond the Linear Model,
Gernot Kubin and Erhard Rank
Voice Transformation,
Yannis Stylianou
Talking to Computers: from Speech Sounds to Human Computer Interaction,
Giuseppe Riccardi and Sebastian Varges
Machine Learning for Text and Speech Processing,
Antal van den Bosch and Walter Daelemans
17:30

Note: 30 min. coffee breaks at 10:30 and 15:30
Registration for the Main Conference is open in the Conference Center from 17:00 until 20:00
Special Session on "Presentation Skills" organized by the ISCA student council in Astrid Scala 1
from 18:00 until 20:00, see the ISCA students' website.


Day 2: Tuesday, August 28

ElisabethDarwinMarbleFoyerAlpaertsKeurvelsAstrid Scala 1
08:00
Conference Registration

10:00
Opening Ceremony

11:00 Plenary Session (Elisabeth Hall)
ISCA Medalist - Victor Zue: "On Organic Interfaces"
12:00
Lunch

13:30 TuC.O1
Discriminative and large margin techniques in acoustic modeling
TuC.O2
Speech production I
TuC.O3
Phonetic segmentation and classification I
TuC.P1a
Discourse, dialogue and conversation

TuC.P1b
Spoken dialogue systems I
TuC.P2a
Accent and language identification I

TuC.P2b
Education and training
TuC.P3a
Robust ASR I

TuC.P3b
Adaptation in ASR I
TuC.SS
Synthesis of singing challenge
15:30 Coffee Break
16:00 TuD.O1
Speaker verification & identification I
TuD.O2
Spoken data retrieval I
TuD.O3
Accent and language identification II
TuD.P1
Speech perception I
TuD.P2a
Prosody: prosodic structure

TuD.P2b
Prosodic modeling I
TuD.P3a
Speech analysis

TuD.P3b
Spectral analysis, formants and vocal tract models
TuD.SS
Speech and audio processing for intelligent environments
18:00
18:15
Welcome Reception in the Conference Center



Day 3: Wednesday, August 29

ElisabethDarwinMarbleFoyerAlpaertsKeurvelsAstrid Scala 1
08:00
Conference Registration

08:30 Plenary Session (Elisabeth Hall)
Sophie Scott: "The Neural Basis of Speech Perception – a view from functional imaging"
09:30 Coffee Break
10:00 WeB.O1
Language modelling I
WeB.O2
Prosody production and perception
WeB.O3
Multimodal speech recognition
WeB.P1a
Speech and other modalities

WeB.P1b
Multimodal / multimedia signal processing
WeB.P2
Speaker verification & identification II
WeB.P3
Speech enhancement
WeB.SS
Structure-based and template-based automatic speech recognition
12:00
Lunch

13:30 WeC.O1
Robust ASR against noise and reverberation
WeC.O2
Language resources and tools
WeC.O3
Single-channel speech enhancement
WeC.P1
Phonetics and phonology
WeC.P2
Robust ASR II
WeC.P3
Features for ASR
WeC.SS
Objective assessment of voice and speech quality
15:30 Coffee Break
16:00 WeD.O1
Speaker verification & identification III
WeD.O2
Discourse, dialogue and emotion expression
WeD.O3
Prosodic modeling II
WeD.P1
Resource acquisition and preparation; resource and system evaluation
WeD.P2
Speech production II
WeD.P3
ASR: new paradigms
WeD.SS
Speech and language technology for less-resourced languages
18:00
18:15 ISCA General Assembly (Elisabeth Hall)
19:30 Student Reception
Brasserie Horta

Reviewers Reception
City Hall


Day 4: Thursday, August 30

ElisabethDarwinMarbleFoyerAlpaertsKeurvelsAstrid Scala 1
08:00
Conference Registration

08:30 Plenary Session (Elisabeth Hall)
Alex Waibel: "Computer Supported Human-Human Multilingual Communication"
09:30 Coffee Break
10:00 ThB.O1
Adaptation in ASR II
ThB.O2
Speech perception II
ThB.O3
Spoken language understanding
ThB.P1a
Pitch extraction I

ThB.P1b
Speech coding and transmission
ThB.P2a
Topics in acoustic modeling

ThB.P2b
Confidence measures (and related topics)
ThB.P3a
Grapheme-to-
phoneme conversion


ThB.P3b
Lexical and prosodic modelling
ThB.SS
Speech recognition by automatic attribute transcription
12:00
Lunch

13:30 ThC.O1
Speaker diarization
ThC.O2
First and second language learning
ThC.O3
Speech synthesis I
ThC.P1a
Phonetic segmentation and classification II

ThC.P1b
Voice conversion and modification
ThC.P2
Speaker verification & identification IV
ThC.P3
Improved acoustic modeling for ASR
ThC.SS
Multilingualism in speech and language processing
15:30 Coffee Break
16:00 ThD.O1
Systems for LVCSR and rich transcription I
ThD.O2
Language learning and assessment
ThD.O3
Multimodal interaction: analysis and technology
ThD.P1a
Emotion

ThD.P1b
Speakers: expression, emotion and personality recognition
ThD.P2
First language, second language, cross-language
ThD.P3a
Language modelling II

ThD.P3b
Spoken data retrieval II
ThD.SS
Novel techniques for the NATO non-native air-traffic control and HIWIRE cockpit databases
18:00
19:00 Conference Banquet
Zuiderkroon


Day 5: Friday, August 31

ElisabethDarwinMarbleFoyerAlpaertsKeurvelsAstrid Scala 1
08:00
Conference Registration

08:30 Plenary Session (Elisabeth Hall)
Pierre-Yves Oudeyer: "Self-Organization in the Evolution of Shared Systems of Speech Sounds: a Computational Study"
09:30 Coffee Break
10:00 FrB.O1
Systems for spoken language translation I
FrB.O2
Articulatory features
FrB.O3
Wideband speech processing
FrB.P1a
Accessibility issues

FrB.P1b
New application areas
FrB.P2a
Story segmentation

FrB.P2b
Systems for LVCSR and rich transcription II
FrB.P3a
Prosody: production

FrB.P3b
Prosody: perception
FrB.SS
Machine learning for spoken dialogue systems
12:00
Lunch

13:30 FrC.O1
Spoken dialogue systems II
FrC.O2
Phonetics
FrC.O3
Pitch extraction II
FrC.P1a
Spoken language understanding and summarization

FrC.P1b
Systems for spoken language translation II
FrC.P2
Speech synthesis II
FrC.P3
Voice activity detection and sound classification
15:30 Closing Ceremony
16:30
17:30
Closing Drink - Belgian Beer Tasting

ISCA logo Universiteit Antwerpen logo Radboud University Nijmegen logo Katholieke Universiteit Leuven logo