21st International Conference on Text, Speech and Dialogue
TSD 2018, Brno, Czech Republic, September 11–14 2018
 
Topics | Committees | Important Dates | Contact info | Call for Papers
Conference Program Schema

The conference will be held in Hotel Continental, Brno (see the Conference Location page).

Overview
DateTimeActionRoom
Monday, September 10, 201816:00 - 18:00RegistrationLounge
Tuesday, September 11, 20188:00 - 9:00RegistrationLounge
9:00 - 9:20Opening SessionHall II
9:20 - 9:50Elmar Nöth:
Speech and Language Based Human Decisions - What is next?
Hall II
9:50 - 10:50Kenneth Ward Church:
Minsky, Chomsky & Deep Nets - invited talk
Hall II
10:50 - 11:15Coffee BreakLounge
11:15 - 12:05Parallel Sessions (2 x 2)Hall II, Hall III
12:05 - 13:30Lunch BreakRestaurant
13:30 - 15:00Poster SessionLounge
15:00 - 15:50Parallel Sessions (2 x 2)Hall II, Hall III
15:50 - 16:20Coffee BreakLounge
16:20 - 17:45Demo SessionComputer Room
19:00 - 21:00Welcome ReceptionRestaurant
Wednesday, September 12, 20189:00 - 10:00Piek Vossen and Selene Baez and Lenka Bajcetić and Bram Kraaijeveld:
Leolani: a Reference Machine with a Theory of Mind for Social Communication - invited talk
Hall II
10:00 - 10:30Coffee BreakLounge
10:30 - 11:00Łukasz Kobylinski and Michał Wasiluk and Grzegorz Wojdyga:
Improving Part-of-Speech Tagging by Meta-Learning - Best Paper talk
Hall II
11:00 - 11:50Parallel Sessions (2 x 2)Hall II, Hall III
11:50 - 13:15Lunch BreakRestaurant
13:15 - 14:30Poster SessionLounge
14:30 - 15:45Parallel Sessions (2 x 3)Hall II, Hall III
16:00 - 18:00Program Committee MeetingComputer Room
18:00 - 20:00Guided Tour to Brno (info at Registration)
Thursday, September 13, 201809:00 - 09:50Parallel Sessions (2 x 2)Hall II, Hall III
09:50 - 10:20Coffee BreakLounge
10:20 - 11:35Parallel Sessions (2 x 3)Hall II, Hall III
11:35 - 13:00Lunch BreakRestaurant
13:00 - 24:00Trip and Conference Dinner
Friday, September 14, 20189:30 - 10:30Isabel Trancoso and Joana Correia and Francisco Teixeira and Bhiksha Raj and Alberto Abad:
Speech Analytics for Medical Applications - invited talk
Hall II
10:30 - 11:00Coffee BreakLounge
11:00 - 11:30Asadullah and Tanel Alumae:
Data Augmentation and Teacher-Student Training for LF-MMI Based Robust Speech Recognition - Best Student Paper talk
Hall II
11:30 - 12:20Parallel Sessions (2 x 2)Hall II, Hall III
12:20 - 12:30Closing CeremonyHall II
12:30 - 13:30Lunch BreakRestaurant










Tuesday, September 11, 2018
Time
8:00Registration (Lounge)
9:00Opening Session (Hall II)
9:20Elmar Nöth:
Speech and Language Based Human Decisions - What is next? (Hall II)
chair: Karel Pala
9:50Kenneth Ward Church:
Minsky, Chomsky & Deep Nets - invited talk
(Hall II)
chair: Karel Pala
10:50Coffee Break (Lounge)
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Natalia Loukachevitch
Section Speech (Hall III)
chair: Tino Haderlein
11:15Jaroslava Hlaváčová:
Prefixal Morphemes of Czech Verbs
Jiří Přibil and Anna Přibilová and Jindřich Matoušek:
Automatic Evaluation of Synthetic Speech Quality by a System Based on Statistical Analysis
11:40Jakub Waszczuk and Witold Kieras and Marcin Wolinski:
Morphosyntactic Disambiguation and Segmentation for Historical Polish with Graph-Based Conditional Random Fields
Martin Matura and Markéta Jůzová:
Using Anomaly Detection for Fine Tuning of Formal Prosodic Structures in Speech Synthesis
12:05Lunch Break (Restaurant)
13:30Poster Session (Lounge)
chair: Aleš Horák
Alexei Dobrov and Anastasia Dobrova and Pavel Grokhovskiy and Maria Smirnova and Nikolay Soms:
Idioms Modeling in a Computer Ontology as a Morphosyntactic Disambiguation Strategy
Bálint Sass:
A Lattice Based Algebraic Model for Verb Centered Constructions
Gennady Shtekh and Polina Kazakova* and Nikita Nikitinsky:
Adjusting Machine Translation Datasets for Document-Level Cross-Language Information Retrieval: Methodology
Jiří Málek and Jindřich Ždánský and Petr Červa:
Robust Recognition of Conversational Telephone Speech via Multi-Condition Training and Data Augmentation
Aleksandra Vatian and Natalia Dobrenko and Anastasia Makarenko and Niyaz Nigmatullin and Nikolay Vedernikov and Artem Vasilev and Andrey Stankevich and Natalia Gusarova and Anatoly Shalyto:
Adaptation of Algorithms for Medical Information Retrieval for Working on Russian-Language Text Content
Jan Lehečka and Aleš Pražák:
Online LDA-Based Language Model Adaptation
Ágnes Kalivoda and Noémi Vadász and Balázs Indig:
Manócska: A Unified Verb Frame Database for Hungarian
Zbyněk Zajíc and Daniel Soutner and Marek Hrúz and Luděk Müller and Vlasta Radová:
Recurrent Neural Network Based Speaker Change Detection from Text Transcription Applied in Telephone Speaker Diarization System
Lukás Svoboda and Tomás Brychcí­n:
Czech Dataset for Semantic Textual Similarity
Ben Fishman and Itshak Lapidot and Irit Opher:
Prosodic Features' Criterion For Hebrew
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Jaroslava Hlaváčová
Section Dialogue (Hall III)
chair: Lubomir Ivanov
15:00Aidar Khusainov and Dzhavdet Suleymanov and Rinat Gilmullin and Ajrat Gatiatullin:
Building the Tatar-Russian NMT System Based on Re-Translation of Multilingual Data
Tino Haderlein and Anne Schützenberger and Michael Doellinger and Elmar Nöth:
Subtext Word Accuracy and Prosodic Features for Automatic Intelligibility Assessment
15:25N.L. Rusnachenko and Natalia Loukachevitch:
Sentiment Attitudes and Their Extraction from Analytical Texts
Thierry Desot and Stefania Raimondo and Anastasia Mishakova and François Portet and Michel Vacher:
Towards a French Smart-Home Voice Command Corpus: Design and NLU Experiments
15:50Coffee Break (Lounge)
16:20Demo Session (Computer Room)
chair: Aleš Horák
Thejeswi Nagendra Kamatchi, Jelena Mitrović, Siegfried Handschuh:
Automated Legal Research for German Law
Aleksei Dobrov, Anastasia Dobrova, Pavel Grokhovskiy, Maria Smirnova, Nikolay Soms:
Computer model of the Tibetan language morphology
Basile Audard, Elena Manishina, Joao Pedro Campello:
SMACC - text analyzer for legal assistance
Magdalena Wiercioch:
Text Embeddings Based on Synonyms
Kira Droganova, Eva Fučíková, Anša Vernerová:
An interface between the Czech valency lexicon PDT-Vallex and corpus manager KonText
Hien T. Ha and Marek Medveď and Zuzana Nevěřilová and Aleš Horák:
Recognition of OCR Invoice Metadata Block Types
Witold Kieraś, Łukasz Kobyliński, Maciej Ogrodniczuk, Zbigniew Gawłowicz, Michał Wasiluk:
Korpusomat: a quick way to create searchable, annotated corpora
Vít Baisa, Tomáš Svoboda, Jan Michelfeit, Miloš Jakubíček, Vojtěch Kovář, Ondřej Matuška:
Sketch Engine: all-new user experience and richer API
17:45
19:00Welcome Reception (Restaurant)
21:00










Wednesday, September 12, 2018
Time
9:00Piek Vossen and Selene Baez and Lenka Bajcetić and Bram Kraaijeveld:
Leolani: a Reference Machine with a Theory of Mind for Social Communication - invited talk
(Hall II)
chair: Aleš Horák
10:00Coffee Break (Lounge)
10:30Łukasz Kobylinski and Michał Wasiluk and Grzegorz Wojdyga:
Improving Part-of-Speech Tagging by Meta-Learning - Best Paper talk
(Hall II)
chair: Piek Vossen
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Pavel Rychlý
Section Speech (Hall III)
chair: Simon Dobrišek
11:00Dominik Macháček and Jonáš Vidra and Ondřej Bojar:
Morphological and Language-Agnostic Word Segmentation for NMT used as gold-standard data for evaluating the segmentation methods
Markéta Jůzová and Daniel Tihelka and Jan Volín:
On the Extension of the Formal Prosody Model for TTS
11:25Jakub Harašta and Jaromír Šavelka and František Kasl and Adéla Kotková and Pavel Loutocký and Jakub Míšek and Daniela Procházková and Helena Pullmannová and Petr Semenišín and Tamara Šejnová and Nikola Šimková and Michal Vosinek and Lucie Zavadilová and Jan Zibner:
Annotated Corpus of Czech Case Law for Reference Recognition Tasks
Zdeněk Hanzlíček and Jakub Vít and Daniel Tihelka:
WaveNet-Based Speech Synthesis Applied to Czech
11:50Lunch Break (Restaurant)
13:15Poster Session (Lounge)
chair: Pavel Rychlý
Aleksander Wawer and Justyna Sarzyńska:
Do We Need Word Sense Disambiguation for LCM Tagging?
Daniel Tihelka, Zdeněk Hanzlíček and Markéta Jůzová and Jakub Vít and Jindřich Matoušek and Martin Grůber:
Current State of Text-to-Speech System ARTIC: A Decade of Research on the Field of Speech Technologies
Samia Ben Ismail and Sirine Boukedi and Kais Haddar:
Generation of Arabic Broken Plural within LKB
Michal Trzos, Martin Dostál, Petra Macháčková, and Jana Eitlerová:
Voice Control in a Real Flight Deck Environment
Behzad Naderalvojoud and Behrang Qasemizadeh and Laura Kallmeyer and Ebru Akcapinar Sezer:
A Cross-Lingual Approach for Building Multilingual Sentiment Lexicons
Radek Šafařík and Lukáš Matějů and Lenka Weingartová:
The Influence of Errors in Phonetic Annotations on Performance of Speech Recognition System
Hien T. Ha and Marek Medveď and Zuzana Nevěřilová and Aleš Horák:
Recognition of OCR Invoice Metadata Block Types
Gyoergy Kovács:
Classification of Formal and Informal Dialogues Based on Emotion Recognition Features
Hassina Bouressace and Janos Csirik:
Recognition of the Logical Structure of Arabic Newspaper Pages
Ignatius Ezeani and Mark Hepple and Ikechukwu Onyenwe and Chioma Enemuo:
Multi-task Projected Embedding for Igbo
Parallel Sessions (2 x 3)
Section Text (Hall II)
chair: Petr Sojka
Section Speech (Hall III)
chair: Jimmy Kunzmann
14:30Lauma Pretkalnina and Laura Rituma and Baiba Saulite:
Deriving Enhanced Universal Dependencies from a Hybrid Dependency-Constituency Treebank
Niraj Shrestha and Marie-Francine Moens:
Semantic Role Labeling of Speech Transcripts without Sentence Boundaries
14:55Natalia Loukachevitch and Ekaterina Parkhomenko:
Evaluating Distributional Features for Multiword Expression Recognition
Jan Zelinka:
Deep Learning and Online Speech Activity Detection for Czech Radio Broadcasting
15:20N. Garcia-Ospina and T. Arias-Vergara and J. C. Vásquez-Correa and J. R. Orozco-Arroyave and M. Cernak and E. Nöth:
Phonological i-Vectors to Detect Parkinson's Disease
16:00Program Committee Meeting (Computer Room)
18:00Guided Tour to Brno (info at Registration)
20:00










Thursday, September 13, 2018
TimeParallel Sessions (2 x 2)
Section Text (Hall II)
chair: Petr Sojka
Section Text (Hall III)
chair: Aidar Khusainov
09:00Roua Torjmen and Kais Haddar:
Morphological Aanalyzer for the Tunisian Dialect
Miloslav Konopík and Ondřej Pražák:
LDA in Character-LSTM-CRF Named Entity Recognition
09:25Zuzana Pelikánová and Zuzana Nevěřilová:
Corpus Annotation Pipeline for Non-standard Texts
Ajay Gupta and Devendra Verma and Sachin Pawar and Sangameshwar Patil and Swapnil Hingmire and Girish K. Palshikar and Pushpak Bhattacharya:
Identifying Participant Mentions and Resolving their Coreferences in Legal Court Judgements
09:50Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Text (Hall II)
chair: Miloslav Konopík
Section Dialogue/Speech (Hall III)
chair: Daniel Tihelka
10:20Lubomir Ivanov and Amanda Aebig and Stephen Meerman:
Lexical Stress-Based Authorship Attribution with Accurate Pronunciation Patterns Selection
AlBara Khalifa and Tsuneo Kato and Seiichi Yamamoto:
The Retention Effect of Learning Grammatical Patterns Implicitly Using Joining-in-Type Robot-Assisted Language-Learning System
10:45Afifah Waseem:
CoRTE: A Corpus of Recognizing Textual Entailment Data Annotated for Coreference and Bridging Relations
Adam Chýlek and Jan Švec and Luboš Šmídl:
Learning to Interrupt the User at the Right Time in Incremental Dialogue Systems
11:10Dage Särg and Kadri Muischnek and Kaili Müürisep:
Annotated Clause Boundaries' Influence on Parsing Results
Juan Camillo Vásquez-Correa and Nicanor Garcia-Ospina and Juan Rafael Orozco-Arroyave and Milos Cernak and Elmar Nöth:
Phonological Posteriors and GRU Recurrent Units to Assess Speech Impairments of Patients with Parkinson's Disease
11:35Lunch Break (Restaurant)
13:00Trip and Conference Dinner
24:00










Friday, September 14, 2018
Time
9:30Isabel Trancoso and Joana Correia and Francisco Teixeira and Bhiksha Raj and Alberto Abad:
Speech Analytics for Medical Applications - invited talk
(Hall II)
chair: Elmar Nöth
10:30Coffee Break (Lounge)
11:00Asadullah and Tanel Alumae:
Data Augmentation and Teacher-Student Training for LF-MMI Based Robust Speech Recognition - Best Student Paper talk
(Hall II)
chair: Isabel Trancoso
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Karel Pala
Section Speech (Hall III)
chair: Juan Rafael Orozco-Arroyave
11:30Anutosh Maitra and Shubhashis Sengupta and Abhisek Mukhopadhyay and Deepak Gupta and Rajkumar Pujari and Pushpak Bhattacharya and Asif Ekbal and Tom Geo Jain:
Semantic Question Matching in Data Constrained Environment
Josef Michálek and Jan Vaněk:
A Survey of Recent DNN Architectures on the TIMIT Phone Recognition Task
11:55Fangzhou Zhai and Yue Fan and Tejaswani Verma and Rupali Sinha and Dietrich Klakow:
A Dataset and a Novel Neural Approach for Optical Gregg Shorthand Recognition
Markéta Jůzová and Jan Volín:
F0 Post-Stress Rise Trends Consideration in Unit Selection TTS
12:20Closing Ceremony (Hall II)
12:30Lunch Break (Restaurant)
13:30










.
TSD 2017 | TSD 2016 | TSD 2015