19th International Conference on Text, Speech and Dialogue
TSD 2016, Brno, Czech Republic, September 12–16 2016
Topics | Committees | Important Dates | Contact info | Call for Papers
Conference Program

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

Monday, September 12, 201613:00 - 14:00RegistrationLounge
14:00 - 18:00Community-based Building of Language Resources Workshop
14:00 - 14:30Björn Gambäck:
Harvesting big text data for under-resourced languages - invited talk
Computer Room
14:30 - 16:00CBBLR Workshop Session IComputer Room
16:00 - 16:30Coffee BreakLounge
16:30 - 18:00CBBLR Workshop Session IIComputer Room
Tuesday, September 13, 20168:00 - 9:00RegistrationLounge
9:00 - 9:20Opening SessionHall II
9:20 - 10:20Ido Dagan:
Natural Language Knowledge Graphs - invited talk
Hall II
10:20 - 10:45Coffee BreakLounge
10:45 - 12:00Parallel Sessions (2 x 3)Hall II, Hall III
12:00 - 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 14, 20169:00 - 10:00Hinrich Schütze:
Embeddings! For which objects? For which objectives? - invited talk
Hall II
10:00 - 10:30Coffee BreakLounge
10:30 - 11:45Parallel Sessions (2 x 3)Hall II, Hall III
11:45 - 13:15Lunch BreakRestaurant
13:15 - 14:30Poster SessionLounge
14:30 - 15:20Parallel Sessions (2 x 2)Hall II, Hall III
15:20 - 15:50Coffee BreakLounge
15:50 - 16:40Parallel Sessions (2 x 2)Hall II, Hall III
16:45 - 18:00Program Committee MeetingComputer Room
18:00 - 20:00Guided Tour to Brno (info at Registration)
Thursday, September 15, 201609:00 - 10:15Parallel Sessions (2 x 3)Hall II, Hall III
10:15 - 10:45Coffee BreakLounge
10:45 - 11:35Parallel Sessions (2 x 2)Hall II, Hall III
11:35 - 13:00Lunch BreakRestaurant
13:00 - 24:00Trip and Conference Dinner
Friday, September 16, 20169:30 - 10:30Elmar Nöth:
Remote Monitoring of Neurodegeneration through Speech - invited talk
Hall II
10:30 - 11:00Coffee BreakLounge
11:00 - 11:50Parallel Sessions (2 x 2)Hall II, Hall III
11:50 - 12:00Closing CeremonyHall II
12:00 - 13:00Lunch BreakRestaurant
13:00 - 13:00ENeL COST Action MeetingComputer Room
15:15 - 16:00Coffee BreakLounge
16:00 - 16:00ENeL COST Action MeetingComputer Room
18:00 - 20:00Steering Group Meeting
Saturday, September 17, 20169:00 - 9:00ENeL COST Action MeetingComputer Room
10:30 - 11:00Coffee BreakLounge
11:00 - 11:00ENeL COST Action MeetingComputer Room
12:30 - 14:00Lunch BreakRestaurant
14:00 - 14:00ENeL COST Action MeetingComputer Room
15:30 - 16:00Coffee BreakLounge
16:00 - 17:00ELEXIS proposal meeting (ELEXIS partners)Computer Room

Monday, September 12, 2016
13:00Registration (Lounge)
14:00-18:00Community-based Building of Language Resources Workshop
14:00Björn Gambäck:
Harvesting big text data for under-resourced languages - invited talk
(Computer Room)
chair: Karel Pala
14:30CBBLR Workshop Session I (Computer Room)
chair: Karel Pala
Tatiana Litvinova, Olga Litvinova:
Russian Deception Bank: A Corpus for Automated Deception Detection in Text
Hamza Frihia and Halima Bahi:
Embedded Learning Segmentation Approach for Arabic Speech Recognition
Filip Gralinski, Rafał Jaworski, Łukasz Borchmann, Piotr Wierzchon:
Vive la Petite Différence!
Arun Baby, Anju Leela Thomas, Nishanthi N L, TTS Consortium:
Resources for Indian languages
Claudio Russo:
Towards It-CMC: a Fine-Grained POS Tagset for Italian Linguistic Analysis
16:00Coffee Break (Lounge)
16:30CBBLR Workshop Session II (Computer Room)
chair: Björn Gambäck
Pavel Rychlý and Vít Suchomel:
Annotated Amharic Corpora
Arun Baby and Nishanthi N. L. and Anju Leela Thomas and Hema A. Murthy:
A Unified Parser for Developing Indian Language Text to Speech Synthesizers
Ikechukwu E. Onyenwe and Mark Hepple:
Predicting Morphologically-Complex Unknown Words in Igbo
Gizem Sogancioglu, Bilge Koroglu, Onur Agin:
Multi-label Topic Classification of Turkish Sentences Using Cascaded Approach for Dialog Management System
Silvie Cinková:
WordSim353 for Czech

Tuesday, September 13, 2016
8:00Registration (Lounge)
9:00Opening Session (Hall II)
9:20Ido Dagan:
Natural Language Knowledge Graphs - invited talk
(Hall II)
chair: Karel Pala
10:20Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Text (Hall II)
chair: Karel Pala
Section Speech (Hall III)
chair: France Mihelič
10:45Jana Straková and Milan Straka and Jan Hajič:
Neural Networks for Featureless Named Entity Recognition in Czech
Mittul Singh and Clayton Greenberg and Dietrich Klakow:
The Custom Decay Language Model for Long Range Dependencies
11:10Jan Kocoń and Michał Marcińczuk:
Generating of Events Dictionaries from Polish WordNet for the Recognition of Events in Polish Documents
Petr Mizera and Jiří Fiala and Aleš Brich and Petr Pollak:
KALDI Recipes for the Czech Speech Recognition Under Various Conditions
11:35Rohit Gupta and Constantin Orasan and Qun Liu and Ruslan Mitkov:
A Dynamic Programming Approach to Improving Translation Memory Matching and Retrieval Using Paraphrases
Kim Berninger and Jannis Hoppe and Benjamin Milde:
Classification of Speaker Intoxication Using a Bidirectional Recurrent Neural Network
12:00Lunch Break (Restaurant)
13:30Poster Session (Lounge)
chair: Aleš Horák
Enaitz Ezpeleta and Urko Zurutuza and José María Gómez Hidalgo:
Short Messages Spam Filtering Using Sentiment Analysis
Ahmad Aghaebrahimian and Filip Jurčíček:
Constraint-Based Open-Domain Question Answering Using Knowledge Graph Search
Peter Bednár:
Cross-Language Dependency Parsing Using Part-Of-Speech Patterns
Jiří Přibil and Anna Přibilová and Jindřich Matoušek:
Evaluation of TTS Personification by GMM-Based Speaker Gender and Age Classifier
Sofía N. Galicia-Haro and Alexander F. Gelbukh:
Assessing Context for Extraction of Near Synonyms from Product Reviews in Spanish
Sergey Salishev and Andrey Barabanov and Daniil Kocharov and Pavel Skrelin and Mikhail Moiseev:
Voice Activity Detector (VAD) Based on Long-Term Mel Frequency Band Features
Miroslav Smatana and Ján Paralič and Peter Butka:
Topic Modeling over Text Streams from Social Media
Tino Haderlein and Michael Doellinger and Anne Schützenberger and Elmar Noeth:
Influence of Reverberation on Automatic Evaluation of Intelligibility with Prosodic Features
Jakub Kanis:
Digging Language Model - Maximum Entropy Phrase Extraction
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Karel Pala
Section Dialogue (Hall III)
chair: Simon Dobrišek
15:00Tomáš Jelínek:
Combining Dependency Parsers Using Error Rates
Martin Gropp, Anna Schmidt, Thomas Kleinbauer, Dietrich Klakow:
Platon: Dialog Management and Rapid Prototyping for Multilingual Multi-User Dialog Systems
15:25Vojtěch Kovář, Jakub Machura, Kristýna Zemková and Michal Rott:
Evaluation and Improvements in Punctuation Detection for Czech
Tatiana Sokoreva, Tatiana Shevchenko:
Starting a Conversation: Indexical Rhythmical Features Across Age and Gender (a Corpus Study)
15:50Coffee Break (Lounge)
16:20Demo Session (Computer Room)
chair: Aleš Horák
Ondřej Matuška:
Sketch Engine Overview
Adam Rambousek:
Lexicographic Software with the DEB platform
Milan Straka and Jana Straková and Jan Hajič:
Complete Analysis from Unstructured Text to Dependency Tree with UDPipe and NameTag
Tatiana Litvinova, Olga Litvinova, Olga Zagorovskaya, Ekaterina Ryzhkova:
Text Corpus for Gender Attribution Studies
Michal Měchura:
Lexonomy: a cloud-based dictionary writing system
Miloš Jakubíček:
Multiword thesaurus
Seyed Mostafa Assi, Saeedeh Ghandi:
Persian Linguistic Database (PLDB) and its historical corpus
19:00Welcome Reception (Restaurant)

Wednesday, September 14, 2016
9:00Hinrich Schütze:
Embeddings! For which objects? For which objectives? - invited talk
(Hall II)
chair: Petr Sojka
10:00Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Text (Hall II)
chair: Constantin Orasan
Section Dialogue (Hall III)
chair: Tino Haderlein
10:30Arantxa Otegi and Nerea Ezeiza and Iakes Goenaga and Gorka Labaka:
A Modular Chain of NLP Tools for Basque
Frédéric Aman and Véronique Aubergé and Michel Vacher:
Influence of Expressive Speech on ASR Performances: Application to Elderly Assistance in Smart Home
10:55Jaroslava Hlaváčová:
Homonymy and Polysemy in the Czech Morphological Dictionary
Ángel Callejas-Rodríguez and Esaú Villatoro-Tello and Ivan Meza and Gabriela Ramírez-de-la-Rosa:
From Dialogue Corpora to Dialogue Systems: Generating a Chatbot with Teenager Personality for Preventing Cyber-Pedophilia
11:20Zuzana Nevěřilová:
Annotation of Czech Texts with Language Mixing
Marek Boháč and Lukáš Matějů and Michal Rott and Radek Šafařík:
Automatic Syllabification and Syllable Timing of Automatically Recognized Speech - for Czech
11:45Lunch Break (Restaurant)
13:15Poster Session (Lounge)
chair: Pavel Rychlý
Tom Kocmi and Ondřej Bojar:
SubGram: Extending Skip-gram Word Representation with Substrings
Ignatius Ezeani and Mark Hepple and Ikechukwu Onyenwe:
Automatic Restoration of Diacritics for Igbo Language
Miroslav Blšták and Viera Rozinajová:
Automatic Question Generation Based on Analysis of Sentence Structure
Markéta Jůzová and Daniel Tihelka:
Difficulties with Wh-Questions in Czech TTS System
Lieke Verheijen and Wessel Stoop:
Collecting Facebook Posts and WhatsApp Chats
Lucie Skorkovská:
Relevant Documents Selection for Blind Relevance Feedback in Speech Information Retrieval
Marek Medveď and Aleš Horák:
AQA: Automatic Question Answering System for Czech
Meysam Asgari and Allison Sliter and Jan Van Santen:
Automatic Scoring of a Sentence Repetition Task from Voice Recordings
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Petr Sojka
Section Speech (Hall III)
chair: Jiří Přibil
14:30Mladen Karan and Jan Šnajder:
FAQIR - A Frequently Asked Questions Retrieval Test Collection
Aleksey Prudnikov, Maxim Korenevsky:
Training Maxout Neural Networks for Speech Recognition Tasks
14:55Michał Marcińczuk and Marcin Oleksy and Jan Wieczorek:
Preliminary Study on Automatic Recognition of Spatial Expressions in Polish Texts
Anna Bulusheva and Alexander Zatvornitskiy and Maxim Korenevsky:
An Efficient Method for Vocabulary Addition to WFST Graphs
15:20Coffee Break (Lounge)
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Eva Hajičová
Section Speech (Hall III)
chair: Elmar Nöth
15:50Natalia Loukachevitch and Aleksei Alekseev:
Gathering Information about Word Similarity from Neighbor Sentences
Tomáš Bořil and Radek Skarnitzl:
Tools rPraat and mPraat
16:15Alexei Dobrov and Anastasia Dobrova and Pavel Grokhovskiy and Nikolay Soms and Victor Zakharov:
Morphosyntactic Analyzer for the Tibetan Language: Aspects of Structural Ambiguity
Anna Popková, Filip Povolný, Pavel Matějka, Ondřej Glembek, František Grézl, and Jan ``Honza'' Černocký:
Investigation of Bottle-Neck Features for Emotion Recognition
16:45Program Committee Meeting (Computer Room)
18:00Guided Tour to Brno (info at Registration)

Thursday, September 15, 2016
TimeParallel Sessions (2 x 3)
Section Speech (Hall II)
chair: Daniel Tihelka
Section Text/Speech (Hall III)
chair: Jaroslava Hlaváčová
09:00Žiga Golob and Jerneja Žganec Gros and Vitomir Štruc and France Mihelič and Simon Dobrišek:
A Composition Algorithm of Compact Finite-State Super Transducers for Grapheme-to-Phoneme Conversion
Eckhard Bick, Marcos Zampieri:
Grammatical Annotation of Historical Portuguese: Generating a Corpus-Based Diachronic Dictionary
09:25Elkyn Alexander Belalcázar-Bolaños and Juan Rafael Orozco-Arroyave and Jesús Francisco Vargas-Bonilla and Tino Haderlein and Elmar Noeth:
Glottal Flow Patterns Analyses for Parkinson's Disease Detection: Acoustic and Nonlinear Approaches
Ondřej Bojar and Ondřej Dušek and Tom Kocmi and Jindřich Libovický and Michal Novák and Martin Popel and Roman Sudarikov and Dušan Variš:
CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered
09:50Jakub Vít and Jindřich Matoušek:
Unit-Selection Speech Synthesis Adjustments for Audiobook-based Voices
Zdeněk Hanzlíček:
Correction of Prosodic Phrases in Large Speech Corpora
10:15Coffee Break (Lounge)
Parallel Sessions (2 x 2)
Section Dialogue (Hall II)
chair: Zdeněk Hanzlíček
Section Text (Hall III)
chair: Lubomir Ivanov
10:45Axel Horndasch and Caroline Kaufhold and Elmar Nöth:
How to Add Word Classes to the Kaldi Speech Recognition Toolkit
Elena Tutubalina:
A Sentiment-Aware Topic Model for Extracting Failures from Product Reviews
11:10Reiko Kuwa and Xiaoyun Wang and Tsuneo Kato and Seiichi Yamamoto:
Classification of Utterance Acceptability Based on BLEU Scores for Dialogue-based CALL Systems
Michal Rott, Petr Červa:
Speech-to-Text Summarization Using Automatic Phrase Extraction from Recognized Text
11:35Lunch Break (Restaurant)
13:00Trip and Conference Dinner

Friday, September 16, 2016
9:30Elmar Nöth:
Remote Monitoring of Neurodegeneration through Speech - invited talk
(Hall II)
chair: Jindřich Matoušek
10:30Coffee Break (Lounge)
Parallel Sessions (2 x 2)
Section Text (Hall II)
chair: Michał Marcińczuk
Section Speech (Hall III)
chair: Elmar Nöth
11:00Jan Švec and Jan Rygl:
Building Corpora for Stylometric Research
Jindřich Matoušek and Daniel Tihelka:
On the Influence of the Number of Anomalous and Normal Examples in Anomaly-Based Annotation Errors Detection
11:25Lubomir Ivanov:
Using Alliteration in Authorship Attribution of Historical Texts
Stephen Ash and David Lin:
Grapheme to Phoneme Translation Using Conditional Random Fields with Re-ranking
11:50Closing Ceremony (Hall II)
12:00Lunch Break (Restaurant)
13:00ENeL COST Action Meeting (Computer Room)
13:00Introduction (Ilan Kernerman & Egon Stemle)
13:15Corpus metadata harmonization (Ismail El Maarouf & Roser Saurí)
13:45Converting dictionaries to grammars for NLP (Voula Giouli)
14:15Kamusi Pre:D – Lexicon-based source-side pre-disambiguation for MT and other text processing applications (Martin Benjamin)
14:45An Online System for Lexical Monitoring and Neologism Detection in Bulgarian (Ivelina Stoyanova, Svetlozara Leseva, Svetla Koeva)
15:15Coffee Break (Lounge)
16:00ENeL COST Action Meeting (Computer Room)
16:00NLP and lexicography at TALN group, UPF Barcelona (Luis Espinosa Anke)
16:30ELEXIS introduction & discussion (Simon Krek & participants)
18:00Steering Group Meeting

Saturday, September 17, 2016
9:00ENeL COST Action Meeting (Computer Room)
9:00Applying lexical resources for semantic processing (Bolette Sandford Pedersen)
9:30Lexicography from scratch (Miloš Jakubiček)
10:00BabelNet and gamification (Roberto Navigli)
10:30Coffee Break (Lounge)
11:00ENeL COST Action Meeting (Computer Room)
11:00Interoperability of language data in lexicographic frameworks and knowledge systems (Thierry Declerck)
11:30(Linguistic) Linked Open Data (John McCrae)
12:00Old Dictionaries in New Clothes: Retrodigitization, Standards and the Infrastructural Turn (Toma Tasovac)
12:30Lunch Break (Restaurant)
14:00ENeL COST Action Meeting (Computer Room)
14:00Cross-Lingual Automated Common Senses (Ilan Kernerman)
14:30Resources, tools and services (Bob Boelhouwer (INT), Thomas Troelsgård (DSL), Svetla Koeva (IBL), Tamas Varadi (NYTUD), Monica Monachini (ILC), Vera Hildenbrandt (UT))
15:30Coffee Break (Lounge)
16:00ELEXIS proposal meeting (ELEXIS partners) (Computer Room)

TSD 2015 | TSD 2014 | TSD 2013