Conference
Workshops
Accommodation
Visit Brighton

Brighton Pavilion

Conference

Programme Overview

Plenary Speakers

Special Sessions

Sponsors & Exhibitors

Scientific Committee

Organisers & Contact Us

Social Programme

Brighton Information

10^thAnnual Conference of the International Speech Communication Association

Interspeech 2009 Brighton

Conference Programme Overview

This is the final programme of the conference. If you have signed in to My Schedule, you can add papers to your own personalised list, ordered by time of presentation.

Also available are:

Programme at a glance (PDF).
Complete Abstracts Book (Note: 19MB PDF).
Complete printable list of papers and abstracts.
Search papers by author, title & abstract.

Session Coding System
Day	Session	Type	Index
Mon - Monday Tue - Tuesday Wed - Wednesday Thu - Thursday	Ses0 - 08:30 - 09:30 Ses1 - 10:00 - 12:00 Ses2 - 13:30 - 15:30 Ses3 - 16:00 - 18:00	K - Keynote O - Oral P - Poster S - Special	1 - 4

Sunday 6 September 2009
08:30	Tutorials Registration [Foyer, Brighton Centre]
09:15	Tutorial T-1 Analysis by synthesis of speech prosody, from data to models [East Wing 1]
09:15	Tutorial T-2 Dealing with High Dimensional Data with Dimensionality Reduction [East Wing 2]
09:15	Tutorial T-3 Language and Dialect Recognition [East Wing 3]
09:15	Tutorial T-4 Emerging Technologies for Silent Speech Interfaces [East Wing 4]
10:00	Interspeech 2009 public exhibition [Foyer, Brighton Centre]
10:45	Loebner Prize Competition [Rainbow room]
14:00	Conference Registration (to 18:00) [Foyer, Brighton Centre]
14:15	Tutorial T-5 In-Vehicle Speech Processing & Analysis [East Wing 1]
14:15	Tutorial T-6 Emotion Recognition in the Next Generation: an Overview and Recent Development [East Wing 2]
14:15	Tutorial T-7 Fundamentals and recent advances in HMM-based speech synthesis [East Wing 3]
14:15	Tutorial T-8 Statistical approaches to dialogue systems [East Wing 4]
14:15	The first Interspeech conversational systems challenge [Rainbow room]

Monday 7 September 2009
09:00	Conference Registration (to 17:00) [Foyer, Brighton Centre]
10:00	Opening Ceremony [Main Hall]
11:00	Keynote Speech [Main Hall]
	Mon-Ses1-K: Sadaoki Furui - Selected topics from 40 years of research on speech and speaker recognition [Main Hall]
12:00	Lunch break
13:30	Conference Session Mon-Ses2
	Mon-Ses2-O1: ASR: Features for Noise Robustness [Main Hall] Mon-Ses2-O2: Production: Articulatory modelling [East Wing 1] Mon-Ses2-O3: Systems for LVCSR and Rich Transcription [East Wing 2] Mon-Ses2-O4: Speech Analysis and Processing I [East Wing 3] Mon-Ses2-P1: Speech perception I [Hewison Hall] Mon-Ses2-P2: Accent and Language Recognition [Hewison Hall] Mon-Ses2-P3: ASR: Acoustic Model Training and Combination [Hewison Hall] Mon-Ses2-P4: Spoken dialogue systems [Hewison Hall] Mon-Ses2-S1: Special Session: INTERSPEECH 2009 Emotion Challenge [East Wing 4]
15:30	Tea break
16:00	Conference Session Mon-Ses3
	Mon-Ses3-O1: Automatic Speech Recognition: Language Models I [Main Hall] Mon-Ses3-O2: Phoneme-level Perception [East Wing 1] Mon-Ses3-O3: Statistical Parametric Synthesis I [East Wing 2] Mon-Ses3-O4: Systems for Spoken Language Translation [East Wing 3] Mon-Ses3-P1: Human Speech Production I [Hewison Hall] Mon-Ses3-P2: Prosody, Text Analysis, and Multilingual Models [Hewison Hall] Mon-Ses3-P3: Automatic Speech Recognition: Adaptation I [Hewison Hall] Mon-Ses3-P4: Applications in learning and other areas [Hewison Hall] Mon-Ses3-S1: Special Session: Silent Speech Interfaces [East Wing 4]
19:30	Welcome reception, Brighton Museum

Tuesday 8 September 2009
08:00	Conference Registration (to 17:00) [Foyer, Brighton Centre]
08:30	Keynote Speech [Main Hall]
	Tue-Ses0-K: Tom Griffiths - Connecting human and machine learning via probabilistic models of cognition [Main Hall]
09:30	Coffee break
10:00	Conference Session Tue-Ses1
	Tue-Ses1-O1: ASR: Discriminative Training [Main Hall] Tue-Ses1-O2: Language acquisition [East Wing 1] Tue-Ses1-O3: ASR: Lexical and Prosodic Models [East Wing 2] Tue-Ses1-O4: Unit-Selection Synthesis [East Wing 3] Tue-Ses1-P1: Human Speech Production II [Hewison Hall] Tue-Ses1-P2: Speech perception II [Hewison Hall] Tue-Ses1-P3: Speech and Audio Segmentation and Classification [Hewison Hall] Tue-Ses1-P4: Speaker Recognition and Diarisation [Hewison Hall] Tue-Ses1-S1: Special Session: Advanced Voice Function Assessment [East Wing 4]
12:00	Lunch break
13:30	ISCA Student Advisory Committee [East Wing 4]
13:30	Conference Session Tue-Ses2
	Tue-Ses2-O1: Automotive and Mobile applications [Main Hall] Tue-Ses2-O2: Prosody: production I [East Wing 1] Tue-Ses2-O3: ASR: Spoken Language Understanding [East Wing 2] Tue-Ses2-O4: Speaker Diarisation [East Wing 3] Tue-Ses2-P1: Speech Analysis and Processing II [Hewison Hall] Tue-Ses2-P2: Speech processing with audio or audiovisual input [Hewison Hall] Tue-Ses2-P3: ASR: Decoding and Confidence Measures [Hewison Hall] Tue-Ses2-P4: Robust Automatic Speech Recognition I [Hewison Hall]
15:30	Tea break
16:00	Conference Session Tue-Ses3
	Tue-Ses3-O3: Speaker verification & identification I [East Wing 2] Tue-Ses3-O4: Text Processing for Spoken Language Generation [East Wing 3] Tue-Ses3-P1: Single- and Multichannel Speech Enhancement [Hewison Hall] Tue-Ses3-P2: ASR: Acoustic Modelling [Hewison Hall] Tue-Ses3-P3: Assistive Speech Technology [Hewison Hall] Tue-Ses3-P4: Topics in Spoken Language Processing [Hewison Hall] Tue-Ses3-S1: Panel: Speech & Intelligence [Main Hall] Tue-Ses3-S2: Special Session: Measuring the Rhythm of Speech [East Wing 4]
18:00	ISCA General Assembly [Main Hall]
19:30	Reviewers' reception, Royal Pavilion
19:30	Student reception, Al Duomo Restaurant

Wednesday 9 September 2009
08:00	Conference Registration (to 17:00) [Foyer, Brighton Centre]
08:30	Keynote Speech [Main Hall]
	Wed-Ses0-K: Deb Roy - New Horizons in the Study of Language Development [Main Hall]
09:30	Coffee break
10:00	Conference Session Wed-Ses1
	Wed-Ses1-O1: Speaker verification & identification II [Main Hall] Wed-Ses1-O2: Emotion and Expression I [East Wing 1] Wed-Ses1-O3: Automatic Speech Recognition: Adaptation II [East Wing 2] Wed-Ses1-O4: Voice Transformation I [East Wing 3] Wed-Ses1-P1: Phonetics, Phonology, cross-language comparisons, pathology [Hewison Hall] Wed-Ses1-P2: Prosody perception and language acquisition [Hewison Hall] Wed-Ses1-P3: Statistical Parametric Synthesis II [Hewison Hall] Wed-Ses1-P4: Resources, annotation and evaluation [Hewison Hall] Wed-Ses1-S1: Special Session: Lessons and Challenges Deploying Voice Search [East Wing 4]
12:00	Lunch break
13:30	Conference Session Wed-Ses2
	Wed-Ses2-O1: Word-level perception [Main Hall] Wed-Ses2-O2: Applications in education and learning [East Wing 1] Wed-Ses2-O3: ASR: new paradigms I [East Wing 2] Wed-Ses2-O4: Single-Channel Speech Enhancement [East Wing 3] Wed-Ses2-P1: Emotion and Expression II [Hewison Hall] Wed-Ses2-P2: Expression, Emotion and Personality Recognition [Hewison Hall] Wed-Ses2-P3: Speech Synthesis Methods [Hewison Hall] Wed-Ses2-P4: LVCSR Systems and Spoken Term Detection [Hewison Hall] Wed-Ses2-S1: Special Session: Active Listening & Synchrony [East Wing 4]
15:30	Tea break
16:00	Conference Session Wed-Ses3
	Wed-Ses3-O1: Language Recognition [Main Hall] Wed-Ses3-O2: Phonetics & Phonology [East Wing 1] Wed-Ses3-O3: Speech activity detection [East Wing 2] Wed-Ses3-O4: Multimodal speech (e.g. audiovisual speech, gesture) [East Wing 3] Wed-Ses3-P1: Phonetics [Hewison Hall] Wed-Ses3-P2: Speaker verification & identification III [Hewison Hall] Wed-Ses3-P3: Robust Automatic Speech Recognition II [Hewison Hall] Wed-Ses3-P4: Prosody: Production II [Hewison Hall] Wed-Ses3-S1: Special Session: Machine Learning for Adaptivity in Spoken Dialogue Systems [East Wing 4]
19:30	Revelry at the Racecourse

Thursday 10 September 2009
08:00	Conference Registration (to 17:00) [Foyer, Brighton Centre]
08:30	Keynote Speech [Main Hall]
	Thu-Ses0-K: Mari Ostendorf - Transcribing Speech for Spoken Language Processing [Main Hall]
09:30	Coffee break
10:00	Conference Session Thu-Ses1
	Thu-Ses1-O1: Robust Automatic Speech Recognition III [Main Hall] Thu-Ses1-O2: Prosody: perception [East Wing 1] Thu-Ses1-O3: Segmentation and Classification [East Wing 2] Thu-Ses1-O4: Evaluation & standardisation of SL technology and systems [East Wing 3] Thu-Ses1-P1: Speech Coding [Hewison Hall] Thu-Ses1-P2: Voice Transformation II [Hewison Hall] Thu-Ses1-P3: Automatic Speech Recognition: Language Models II [Hewison Hall] Thu-Ses1-P4: Systems for Spoken Language Understanding [Hewison Hall] Thu-Ses1-S1: Special Session: New Approaches to Modeling Variability for Automatic Speech Recognition [East Wing 4]
12:00	Lunch break
13:30	Conference Session Thu-Ses2
	Thu-Ses2-O1: User Interactions in Spoken Dialog Systems [Main Hall] Thu-Ses2-O2: Production: Articulation and acoustics [East Wing 1] Thu-Ses2-O3: Features for Speech and Speaker Recognition [East Wing 2] Thu-Ses2-O4: Speech and multimodal resources & annotation [East Wing 3] Thu-Ses2-O5: Speech Analysis and Processing III [East Wing 4] Thu-Ses2-P1: Speaker and speech variability, Paralinguistic and nonlinguistic cues [Hewison Hall] Thu-Ses2-P2: ASR: Acoustic Model Features [Hewison Hall] Thu-Ses2-P3: ASR: Tonal Language, Cross-Lingual and Multilingual ASR [Hewison Hall] Thu-Ses2-P4: ASR: new paradigms II [Hewison Hall]
15:30	Tea break
16:00	Closing Ceremony [Main Hall]

_{© 2009
Mark Huckvale University College London}

_{Last modified: 11:05 03-Oct-2009.}