Panel | Debate | Keynote Discussion Panel: End-to-end Models - Friend or Foe of Speech Research | The Auditorium | 08:30 -- 09:30 | Roger Moore | |
Break | Wed-B1 | Wednesday morning break | The Auditorium | 09:30 -- 10:00 | | |
Oral | Wed-O1 | Analysis of Neural Speech Representations | The Auditorium | 10:00 -- 10:20 | Petr Motlicek | |
Oral | Wed-O2 | End-to-end ASR | Wicklow Hall 2 | 10:00 -- 10:20 | Abeer Alwan | Niko Moritz |
Oral | Wed-O3 | Speech Coding: Privacy | Liffey Hall 2 | 10:00 -- 10:20 | Gernot Kubin | Jennifer Williams |
Oral | Wed-O4 | Spoken Language Understanding, Summarization, and Information Retrieval | Liffey Hall 1 | 10:00 -- 10:20 | Nancy Chen | Sakriani Sakti |
Oral | Wed-O5 | Speech Synthesis: Representation Learning | Wicklow Hall 1 | 10:00 -- 10:20 | Rob Clark | Zhizheng Wu |
Oral | Wed-O6 | Pathological Speech Analysis 2 | EcoCem Room | 10:00 -- 10:20 | Alberto Abad | Nan Yan |
Poster | Wed-P1 | Speech Recognition: Architecture, Search, and Linguistic Components 3 | Forum Poster Area 1 | 10:00 -- 12:00 | David Harwath | |
Poster | Wed-P2 | Speaker and Language Identification 2 | Forum Poster Area 2 | 10:00 -- 12:00 | Jee-weon Jung | |
Poster | Wed-P3 | Speech Perception, Production, and Acquisition 1 | Forum Poster Area 3 | 10:00 -- 12:00 | Maeva Garnier | |
Special Session | Wed-S1 | Invariant and Robust Pre-trained Acoustic Models | Liffey Meeting Room 2 | 10:12 -- 10:26 | Ewan Dunbar | Emmanuel Dupoux |
Poster | Wed-P4 | Analysis of Speech and Audio Signals 3 | Forum Poster Area 1 | 11:00 -- 13:00 | Bogdan Vlasenko | |
Break | Wed-L | Wednesday lunch break | The Auditorium | 12:00 -- 13:30 | | |
Oral | Wed-O7 | Acoustic Model Adaptation for ASR | The Auditorium | 13:30 -- 13:50 | Mark Gales | Jinyu Li |
Oral | Wed-O8 | Speech Synthesis: Expressivity | Wicklow Hall 2 | 13:30 -- 14:10 | Catherine Lai | Berrak Sisman |
Oral | Wed-O9 | Multi-modal Systems | Liffey Hall 2 | 13:30 -- 13:50 | Naomi Harte | Chiori Hori |
Oral | Wed-O10 | Question Answering from Speech | Liffey Hall 1 | 13:30 -- 13:50 | Ingo Siegert | Gabriel Skantze |
Oral | Wed-O11 | Sociophonetics | Wicklow Hall 1 | 13:30 -- 14:10 | Keikichi Hirose | Bistra Andreeva |
Oral | Wed-O12 | Speaker and Language Diarization | EcoCem Room | 13:30 -- 13:50 | Jesus Villalba | Alfonso Ortega |
Poster | Wed-P5 | Speech Coding and Enhancement 3 | Forum Poster Area 2 | 13:30 -- 15:30 | Mohammad Vali | |
Poster | Wed-P6 | Spoken Language Translation, Information Retrieval, Summarization, Resources, and Evaluation 3 | Forum Poster Area 3 | 13:30 -- 15:30 | Santosh Kesiraju | |
Poster | Wed-P7 | Speech Emotion Recognition 2 | Forum Poster Area 4 | 13:30 -- 15:30 | Vidhyasaharan Sethu | |
Special Session | Wed-S2 | Multi-talker Methods in Speech Processing | Liffey Meeting Room 2 | 13:30 -- 15:30 | Marc Delcroix | Liang Lu |
Show and Tell | Wed-SaT | Show and Tell: Language learning and educational resources | Show and Tell Area | 13:30 -- 15:30 | | |
Break | Wed-B2 | Wednesday afternoon break | The Auditorium | 15:30 -- 16:00 | | |
Oral | Wed-O13 | Anti-Spoofing for Speaker Verification | The Auditorium | 16:00 -- 16:20 | Pavel Matejka | Nicholas Evans |
Oral | Wed-O14 | Speech Coding: Intelligibility | Wicklow Hall 2 | 16:00 -- 16:20 | Tim Fingscheidt | Jan Skoglund |
Oral | Wed-O15 | New Computational Strategies for ASR Training and Inference | Liffey Hall 2 | 16:00 -- 16:20 | Peter Mihajlik | Yanhua Long |
Oral | Wed-O16 | Health-Related Speech Analysis | Liffey Hall 1 | 16:00 -- 16:20 | Corinne Fredouille | Iona Gessinger |
Oral | Wed-O17 | Automatic Audio Classification and Audio Captioning | Wicklow Hall 1 | 16:00 -- 16:40 | Jean-François Bonastre | Mirco Ravanelli |
Oral | Wed-O18 | Resources for Spoken Language Processing | EcoCem Room | 16:00 -- 16:20 | Lori Lamel | Shi-wook Lee |
Poster | Wed-P8 | Speech Synthesis | Forum Poster Area 1 | 16:00 -- 18:00 | Sam Ribeiro | |
Poster | Wed-P9 | Speech Perception, Production, and Acquisition 2 | Forum Poster Area 2 | 16:00 -- 18:00 | Felicity Cox | |
Poster | Wed-P10 | Speech Recognition: Signal Processing, Acoustic Modeling, Robustness, Adaptation 4 | Forum Poster Area 3 | 16:00 -- 18:00 | Pawel Swietojanski | |
Special Session | Wed-S3 | MERLIon CCS Challenge: Multilingual Everyday Recordings - Language Identification On Code-Switched Child-Directed Speech | Liffey Meeting Room 2 | 16:00 -- 16:05 | Leibny Paola Garcia Perera | Hexin Liu |