25th International Conference on Text, Speech and Dialogue
TSD 2022, Brno, Czech Republic, September 6–9 2022
Topics | Committees | Important Dates | Contact info | Call for Papers
Conference Program
This is a preliminary conference program - please check the scheduled time of your talk.

Tuesday, September 6, 202216:00 - 18:00RegistrationLounge
Wednesday, September 7, 20228:00 - 9:00RegistrationLounge
9:00 - 9:20Opening SessionHall 5
9:20 - 10:20Eneko Agirre:
Few-shot Information Extraction is Here: Pre-train, Prompt and Entail - invited talk
Hall 5
10:20 - 10:35Coffee BreakLounge
10:35 - 11:50Parallel Sessions (2 x 3)Hall 5, Hall 4
11:50 - 13:00Lunch BreakRestaurant
13:00 - 14:00Poster SessionLounge
14:00 - 15:15Parallel Sessions (2 x 3)Hall 5, Hall 4
15:15 - 15:30Coffee BreakLounge
15:30 - 16:30Demo SessionHall 4
16:30 - 18:00Tutorial: Speech recognition on the edgeHall 4
16:30 - 17:30Program Committee MeetingHall 5
19:00 - 21:00Welcome ReceptionRestaurant
Thursday, September 8, 202209:00 - 10:15Parallel Sessions (2 x 3)Hall 5, Hall 4
10:15 - 10:30Coffee BreakLounge
10:30 - 11:45Parallel Sessions (2 x 3)Hall 5, Hall 4
11:45 - 13:00Lunch BreakRestaurant
13:00 - 23:00Trip and Conference Dinner
Friday, September 9, 20229:30 - 10:30Anna Rogers:
When does a machine "understand" what it "reads"? - invited talk
Hall 5
10:30 - 10:45Coffee BreakLounge
10:45 - 12:25Parallel Sessions (2 x 4)Hall 5, Hall 4
12:25 - 12:30Closing CeremonyHall 5
12:30 - 13:30Lunch BreakRestaurant

Wednesday, September 7, 2022
8:00Registration (Lounge)
9:00Opening Session (Hall 5)
9:20Eneko Agirre:
Few-shot Information Extraction is Here: Pre-train, Prompt and Entail - invited talk
(Hall 5)
chair: Ales Horak
10:20Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Text (Hall 5)
chair: Irina Illina
Section Speech (Hall 4)
chair: Jan Nouza
10:35#1115: Gabriel Amaral, Mārcis Pinnis, Inguna Skadiņa, Odinaldo Rodrigues, Elena Simperl:
Resolving Cross-lingual Entity Label Alignment for Machine Translation
#1163: Jan Lehečka, Josef V. Psutka, Josef Psutka:
Transformer-based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project
11:00#1123: Julia Brendel, Mihaela Vela:
Quality Assessment of Subtitles - Challenges and Strategies
#1113: Abner Hernandez, Philipp Klumpp, Badhan Das, Andreas Maier, Seung Hee Yang:
Autoblog 2021: The Importance of Language Models for Spontaneous Lecture Speech
11:25#1112: Yanis Labrak & Richard Dufour:
ANTILLES: A freNch linguisTIcaLLy Enriched part-of-Speech corpus
#1093: Sree Hari Krishnan Parthasarathi, Lu Zeng, Christin Jose, Joe Wang:
Wakeword Detection under Distribution Shifts
11:50Lunch Break (Restaurant)
13:00Poster Session (Lounge)
chair: Ales Horak
#1182: Lucia Nacinovic Prskalo, Marija Brkic Bakaric:
Identification of metaphorical collocations in different languages - similarities and differences
#1147: Botond Tarcsay, Jelena Vasic, Fernando Perez Tellez:
Use of Machine Learning Methods in the Assessment of Programming Assignments
#1109: George Wright and Matthew Purver:
A Self-Evaluating Architecture for Describing Data
#1133: Hiroshi Echizen'ya, Kenji Araki, Eduard Hovy:
OPTICS: Automatic MT Evaluation based on Optimal Transport by Integration of Contextual Representations and Static Word Embeddings
#1174: Elena Shushkevich, Mikhail Alexandrov, John Cardiff:
BERT-based Classifiers for Fake News Detection on Short and Long Texts with Noisy Data: a Comparative Analysis
#1118: Brett Drury and Samuel Morais Drury:
Lexical Bundle Variation in Business Actors' Public Communications
#1127: Lu Zeng, Sree Hari Krishnan Parthasarathi, Yuzong Liu, Alex Escott, Santosh Cheekatmalla, Nikko Strom, Shiv Vitaladevuni:
Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
#1096: Jan Nouza, Petr Červa, Jindřich Žďánský:
Lexicon-based vs. Lexicon-free ASR for Norwegian Parliament Speech Transcription
#1119: Liane Vogel, Lucie Flek:
Investigating Paraphrasing-based Data Augmentation for Task-Oriented Dialogue Systems
#1139: Jan Švec, Filip Polák, Aleš Bartoš, Michaela Zapletalová, Martin Víta:
Evaluation of Wav2Vec Speech Recognition for Speakers with Cognitive Disorders
#1181: Omama Hamad, Ali Hamdi, Khaled Shaban:
Empathy and Persona of English vs. Arabic Chatbots: A Survey and Future Directions
Parallel Sessions (2 x 3)
Section Text (Hall 5)
chair: Milos Jakubicek
Section Dialogue (Hall 4)
chair: Jan Švec
14:00#1097: Vojtěch Bartička, Ondřej Pražák, Miloslav Konopík, Jakub Sido:
Evaluating Attribution Methods for Explainable NLP with Transformers
#1135: Jan Švec, Adam Frémund, Martin Bulín, Jan Lehečka:
Transfer Learning of Transformers for Spoken Language Understanding
14:25#1136: Jakub Machura, Adam Frémund, Jan Švec:
Automatic Grammar Correction of Commas in~Czech Written Texts: Comparative Study
#1105: Kubilay Can Demir, Matthias May, Axel Schmid, Michael Uder, Katharina Breininger, Tobias Weise, Andreas Maier, Seung Hee Yang:
PoCaP Corpus: A Multimodal Dataset for Smart Operating Room Speech Assistant using Interventional Radiology Workflow Analysis
14:50#1116: Yanan Chen, Yang Liu:
A novel hybrid framework to enhance zero-shot classification
#1179: Tiziano Labruna, Bernardo Magnini:
Fine-Tuning BERT for Generative Dialogue Domain Adaptation
15:15Coffee Break (Lounge)
15:30Demo Session (Hall 4)
chair: Milos Jakubicek
#1185: Michal Měchura:
#1186: Daniel D. Hromada, Hyungjoong Kim:
Digital Primer v1 :: One Goal, Two Prototypes
#1187: Ondřej Matuška:
A tool for terminology extraction - OneClick Terms
#1188: Ondřej Matuška:
Corpora for language learning - SkELL
#1189: Jakub Machura:
Opravidlo.cz – New Online Proofreader of Czech Language
16:30Tutorial: Speech recognition on the edge (Hall 4)
16:30Program Committee Meeting (Hall 5)
19:00Welcome Reception (Restaurant)

Thursday, September 8, 2022
TimeParallel Sessions (2 x 3)
Section Text (Hall 5)
chair: Petr Sojka
Section Speech (Hall 4)
chair: Jindřich Matoušek
09:00#1108: Pavel Přibáň, Jakub Šmíd, Adam Mištera, Pavel Král:
Linear Transformations for Cross-lingual Sentiment
#1158: Franziska Braun, Andreas Erzigkeit, Hartmut Lehfeld, Thomas Hillemacher and Korbinian Riedhammer, Sebastian P. Bayerl:
Going Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments using Acoustic Features
09:25#1131: Sourabrata Mukherjee, Zdeněk Kasner, Ondrej Dusek:
Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising
#1095: Markéta Řezáčková, Jindřich Matoušek:
Text-to-Text Transfer Transformer Phrasing Model Using Enriched Text Input
09:50#1177: Omama Hamad, Ali Hamdi, Sayed Hamdi and Khaled Shaban:
Attention-based Model for Accurate Stance Detection
#1102: Jindřich Matoušek, Daniel Tihelka:
On Comparison of Phonetic Representations for Czech Neural Speech Synthesis
10:15Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Text (Hall 5)
chair: Petr Sojka
Section Dialogue/Text (Hall 4)
chair: Pavel Rychly
10:30#1170: Salar Mohtaj, Sebastian Möller:
On the Importance of Word Embedding in Automated Harmful Information Detection
#1098: Anna Fajfer, Mateusz Góra, Paweł Pardela, Artur Janicki:
Federated Learning in Heterogeneous Data Settings for Virtual Assistants – A Case Study
10:55#1164: Radoslav Sabol and Ales Horak:
New Language Identification and Sentiment Analysis Modules for Social Media Communication
#1178: Olga Vinogradova, Olga Lyashevskaya:
A review of practices for collecting and annotating texts in the learner corpus REALEC
11:20#1155: Julie Kallini, Christiane Fellbaum:
Computational Approaches for Understanding Semantic Constraints on Two-termed Coordination Structures
#1183: Prabhat Kumar Bharti, Asheesh Kumar, Tirthankar Ghosal, Mayank Agrawal, Asif Ekbal:
Can a Machine Generate a Meta-Review? How far are we?
11:45Lunch Break (Restaurant)
13:00Trip and Conference Dinner

Friday, September 9, 2022
9:30Anna Rogers:
When does a machine "understand" what it "reads"? - invited talk
(Hall 5)
chair: Pavel Rychly
10:30Coffee Break (Lounge)
Parallel Sessions (2 x 4)
Section Text (Hall 5)
chair: Pavel Rychly
Section Speech (Hall 4)
chair: Jan Lehecka
10:45#1111: Alexis Blandin, Farida Saïd, Jeanne Villaneau, Pierre-François Marteau:
DaFNeGE: Dataset of French Newsletters with Graph Representation and Embedding
#1117: C. D. Rios-Urrego, S. A. Moreno-Acevedo, E. Nöth, and J. R. Orozco-Arroyave:
End-to-End Parkinson's Disease Detection Using a Deep Convolutional Recurrent Network
11:10#1172: Ahmad Aghaebrahimian, Maria Anisimova, and Manuel Gil:
Ontology-Aware Biomedical Relation Extraction
#1122: Paula Andrea Pérez-Toro, Philipp Klumpp, Juan Camilo Vasquez-Correa, Maria Schuster, Elmar Nöth, Juan Rafael Orozco-Arroyave, Tomás Arias-Vergara:
50 Shades of Gray: Effect of the Color Scale for the Assessment of Speech Disorders
11:35#1107: Ali Davody, David Ifeoluwa Adelani, Thomas Kleinbauer, Dietrich Klakow:
TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models
#1104: Marie Kunešová, Markéta Řezáčková:
Detection of Prosodic Boundaries in Speech Using Wav2Vec 2.0
12:00#1140: Ashwin Geet D'Sa, Irina Illina, Dominique Fohr, Awais Akbar:
Exploration of Multi-Corpus Learning for Hate Speech Classification in Low Resource Scenarios
#1130: Sebastian P. Bayerl, Dominik Wagner, Tobias Bocklet, Elmar Nöth, Korbinian Riedhammer:
The Influence of Dataset Partitioning on Dysfluency Detection Systems
12:25Closing Ceremony (Hall 5)
12:30Lunch Break (Restaurant)

TSD 2021 | TSD 2020 | TSD 2019