23rd International Conference on Text, Speech and Dialogue
TSD 2020, Brno, Czech Republic, September 8–11 2020
Topics | Committees | Important Dates | Contact info | Call for Papers
Conference Program
All times are in Brno UTC+2 time.

Each standard session consist of:

  • an off-line part, when all materials for the session are published, and
  • an active conversation on-line part, where the participants discuss the session papers via questions to the authors.

During the off-line part, questions for the on-line part will be gathered via selected service. For details see the Presentation instructions.

Monday, September 7, 202014:00Virtual Social Eventsoffline
14:00Amazon Alexa Webinaroffline
16:00materials for Session 1offline
Tuesday, September 8, 20201:00materials for Session 2offline
9:00 - 9:05Opening SessionONLINE
9:05 - 10:00Paolo Rosso - invited talk
10:00 - 11:00Session 1 discussionONLINE
11:00 - 15:00Lunch and Time Zone Breakoffline
15:00 - 16:00Session 2 discussionONLINE
16:00materials for Session 3offline
Wednesday, September 9, 20201:00materials for Session 4offline
9:00 - 10:00Diana Maynard - invited talk
10:00 - 11:00Session 3 discussionONLINE
11:00 - 15:00Lunch and Time Zone Breakoffline
15:00 - 16:00Session 4 discussionONLINE
16:00materials for Session 5offline
16:00 - 17:00Program Committee MeetingONLINE
Thursday, September 10, 20201:00materials for Session 6offline
9:00 - 10:00Joakim Nivre - invited talk
10:00 - 11:00Session 5 discussionONLINE
11:00 - 15:00Lunch and Time Zone Breakoffline
15:00 - 16:00Session 6 discussionONLINE
16:00Closing CeremonyONLINE

Monday, September 7, 2020
14:00Virtual Social Events (offline)
14:00Amazon Alexa Webinar (offline)
Amazon Alexa Group:
Behind the scenes of building a socialbot
Amazon Alexa Group:
Creating AI driven voice experiences with Alexa Conversations
16:00materials for Session 1 (offline)

Tuesday, September 8, 2020
1:00materials for Session 2 (offline)
9:00Opening Session (ONLINE)
9:05Paolo Rosso - invited talk
chair: Ales Horak
10:00Session 1 discussion (ONLINE)
chair: Elmar Nöth
#1012: Jan-Oliver Wülfing, Chi-Tai Dang and Elisabeth André:
Synthesising Expressive Speech -- Which Synthesiser for VOCAs?
#1002: Gabriel F. Miller, Juan Camilo Vásquez-Correa and Elmar Nöth:
Assessing the Dysarthria Level of Parkinson's Disease Patients with GMM-UBM Supervectors Using Phonological Posteriors and Diadochokinetic Exercises
#1046: Jan Nouza, Petr Červa and Jindřich Žďánský:
Very Fast Keyword Spotting System with Real Time Factor below 0.01
#1038: Jesin James, Isabella Shields, Rebekah Berriman, Peter J. Keegan and Catherine I. Watson:
Developing Resources for Te Reo Māori Text To Speech Synthesis System
#1045: Jan Švec, Jan Lehečka, Luboš Šmídl and Pavel Ircing:
Automatic Correction of i/y Spelling in Czech ASR Output
#993: Sebastian P. Bayerl, Florian Hönig, Joëlle Reister, Korbinian Riedhammer:
Towards Automated Assessment of Stuttering and Stuttering Therapy
#1015: Tomáš Bořil and Jitka Veroňková:
Perceived Length of Czech High Vowels in Relation to Formant Frequencies Evaluated by Automatic Speech Recognition
#1071: Jindřich Matoušek and Michal Vraštil:
Context-Aware XGBoost for Glottal Closure Instant Detection in Speech Signal
#1085: J.V. Psutka, A. Pražák, J. Vaněk:
Complexity of the TDNN Acoustic model with respect to the HMM topology
11:00Lunch and Time Zone Break (offline)
15:00Session 2 discussion (ONLINE)
chair: Pavel Rychly
#1055: Nisrine Ait Khayi and Vasile Rus:
Graph Convolutional Networks for Student Answers Assessment
#1044: Benjamin Kane, Georgiy Platonov and Lenhart Schubert:
Registering Historical Context for Question Answering in a Blocks World Dialogue System
#999: Arman Kabiri and Paul Cook:
Evaluating a Multi-sense Definition Generation Model for Multiple Languages
#1026: Haukur Páll Jónsson, Haukur Barri Símonarson, Vésteinn Snæbjarnarson, Steinþór Steingrímsson and Hrafn Loftsson :
Experimenting with Different Machine Translation Models in Medium-Resource Settings
#1042: Murathan Kurfalı:
Labeling Explicit Discourse Relations using Pre-trained Language Models
#1029: Mario Ezra Aragón, A. Pastor López-Monroy, Luis C. González and Manuel Montes-y-Gómez:
Attention to Emotions: Detecting Mental Disorders in Social Media
#1084: Milton King and Paul Cook:
Authorship Verification with Personalized Language Models
#1035: Jayr Pereira, Natália Franco, Robson Fidalgo:
A Semantic Grammar for Augmentative and Alternative Communication Systems
#1074: Victor Zakharov and Irina Azarova:
Grammatical Parallelism of Russian Prepositional Localization and Temporal Constructions
16:00materials for Session 3 (offline)

Wednesday, September 9, 2020
1:00materials for Session 4 (offline)
9:00Diana Maynard - invited talk
chair: Ales Horak
10:00Session 3 discussion (ONLINE)
chair: Ondrej Bojar
#1058: Anirudh Dahiya, Manish Shrivastava and Dipti Misra Sharma:
Cross-Lingual Transfer for Hindi Discourse Relation Identification
#1030: Kavya Manohar, A. R. Jayan and Rajeev Rajan:
Quantitative Analysis of the Morphological Complexity of Malayalam Language
#1018: Jan Lehečka, Jan Švec, Pavel Ircing and Luboš Šmídl:
Adjusting BERT's Pooling Layer for Large-scale Multi-label Text Classification
#1021: Anton Alekseev and Sergey Nikolenko :
Recognizing Preferred Grammatical Gender in Russian Anonymous Online Confessions
#1047: Matúš Pikuliak and Marián Šimko:
Combining Cross-Lingual and Cross-Task Supervision for Zero-shot Learning
#989: Javier Sánchez-Junquera, Simone Paolo Ponzetto and Paolo Rosso:
A Twitter Political Corpus of the 2019 10N Spanish Election
#1024: Lucie Poláková and Jiří Mírovský:
Mining Local Discourse Annotation for Features of Global Discourse Structure
#1027: Dušica Terzić, Saša Marjanović, Dejan Stosic and Aleksandra Miletic:
Diversification of Serbian-French-English-Spanish Parallel Corpus ParCoLab with Spoken Language Data
#1059: Rudolf Rosa, Tomáš Musil and David Mareček:
Measuring Memorization Effect in Word-Level Neural Networks Probing
11:00Lunch and Time Zone Break (offline)
15:00Session 4 discussion (ONLINE)
chair: Jimmy Kunzmann
#997: Cristian David Rios-Urrego, Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave and Elmar Nöth:
Transfer Learning to Detect Parkinson's Disease from Speech in Different Languages Using Convolutional Neural Networks with Layer Freezing
#1070: Markéta Jůzová and Daniel Tihelka:
Speaker-Dependent BiLSTM-Based Phrasing
#1023: Jordan Hosier, Jordan Kalfen, Nikhita Sharma and Vijay K. Gurbani:
A Systematic Study of Open Source and Commercial Text-to-Speech (TTS) Engines
#1000: Patricia Argüello-Vélez, Tomás Arias-Vergara, María Claudia González-Rátiva, Juan Rafael Orozco-Arroyave, Elmar Noeth, Maria Schuster:
Acoustic Characteristics of VOT in Plosive Consonants Produced by Parkinson's Patients
#1054: Balázs Tarján, György Szaszák, Tibor Fegyó and Péter Mihajlik:
On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech
#985: Jiří Málek and Jindřich Žďánský:
Voice-Activity and Overlapped Speech Detection Using x-Vectors
#1073: Zdeněk Hanzlíček and Jakub Vít:
LSTM-Based Speech Segmentation Trained on Different Foreign Languages
#986: Stéphane Level, Irina Illina and Dominique Fohr:
Introduction of Semantic Model to Help Speech Recognition
#1014: Marie Hévrová, Tomáš Bořil, Barbara Köpke:
Phonetic Attrition in Vowels' Quality in L1 Speech of Late Czech-French Bilinguals
16:00materials for Session 5 (offline)
16:00Program Committee Meeting (ONLINE)

Thursday, September 10, 2020
1:00materials for Session 6 (offline)
9:00Joakim Nivre - invited talk
chair: Ales Horak
10:00Session 5 discussion (ONLINE)
chair: Pavel Rychly
#1009: Marcin Sowański and Artur Janicki:
Leyzer: A Dataset for Multilingual Virtual Assistants
#991: Jennifer Ureta, Celina Iris Brito, Jilyan Bianca Dy, Kyle-Althea Santos, Winfred Villaluna and Ethel Ong:
At Home with Alexa: A Tale of Two Conversational Agents
#1077: Chiara Leoni, Ilaria Torre and Gianni Vercelli:
ConversIAmo: Improving Italian Question Answering Exploiting IBM Watson Services
#1003: Adrian Radej and Artur Janicki:
Modification of Pitch Parameters in Speech Coding for Information Hiding
#1005: Vaishali Pal, Manish Shrivastava and Laurent Besacier:
ConfNet2Seq: Full Length Answer Generation from Spoken Questions
#1061: Elizabeth Jasmi George:
Verb Focused Answering from CORD-19
#1048: Prateek Saxena and Soma Paul:
EPIE Dataset: A Corpus for Possible Idiomatic Expressions
#1072: Marek Medveď, Radoslav Sabol and Aleš Horák:
Employing Sentence Context in Czech Answer Selection
#1080: Kateřina Macková, Milan Straka:
Reading Comprehension in Czech via Machine Translation and Cross-lingual Transfer
11:00Lunch and Time Zone Break (offline)
15:00Session 6 discussion (ONLINE)
chair: Petr Sojka
#1022: Pavel Hlubík, Martin Španěl, Marek Boháč and Lenka Weingartová:
Inserting Punctuation to ASR Output in a Real-Time Production Environment
#983: Mercedes Vetráb and Gábor Gosztolya:
Investigating the Corpus Independence of the Bag-of-Audio-Words Approach
#1060: Matej Ulčar, Marko Robnik-Šikonja:
FinEst BERT and CroSloEngual BERT: Less is More in Multilingual Models
#1075: Petra Barančíková and Ondřej Bojar:
Costra 1.1: An Inquiry into Geometric Properties of Sentence Spaces
#1078: Jonáš Vidra and Zdeněk Žabokrtský:
Next Step in Online Querying and Visualization of Word-Formation Networks
#1001: Mossad Helali, Thomas Kleinbauer and Dietrich Klakow:
Assessing Unintended Memorization in Neural Discriminative Sequence Models
#1082: Jan Bodnár, Zdeněk Žabokrtský, Magda Ševčíková:
Semi-supervised Induction of Morpheme Boundaries in Czech using a Word-formation Network
#1040: Tamás Ficsor and Gábor Berend:
Interpreting Word Embeddings Using a Distribution Agnostic Approach Employing Hellinger Distance
#1064: Aleena Thomas, David Ifeoluwa Adelani, Ali Davody, Aditya Mogadala and Dietrich Klakow:
Investigating the Impact of Pre-trained Word Embeddings on Memorization in Neural Networks
16:00Closing Ceremony (ONLINE)

TSD 2019 | TSD 2018 | TSD 2017