PROGRAMME
The timetable shown below is the final version of the conference programme. In case there are some changes to the programme based upon particular requests of the conference participants or due to other unforeseen reasons, the participants will be informed on site via a notice board.
Sunday, September 1
whole day |
Arrivals |
17:00 – 19:30 |
Registration (open on all conference days) |
Monday, September 2
09:00 – 09:15 |
Official Opening of the 16th TSD 2013
Hynek Hermansky (TSD 2013 Programme Committee Chair)
|
09:15 – 10:05 |
Invited Talk — Main Lecture Hall
H. Hermansky: Long, Deep and Wide Artificial Neural Nets for Dealing with Unexpected Noise in Machine Recognition of Speech
|
10:10 – 11:00 |
Invited Talk — Main Lecture Hall
T. Lager: Statecharts and SCXML for Dialogue Management
|
11:00 – 11:30 |
Coffee Break |
11:30 – 12:20 |
Section Text 1 — Lecture Hall 1
R. Grundkiewicz: Automatic Extraction of Polish Language Errors from Text Edition History |
R. Brown: Selecting and Weighting N-Grams to Identify 1100 Languages |
|
Section Dialogue — Lecture Hall 2
A. Dingli: Building a Hybrid: Chatterbot - Dialog System |
M. Konkol: CRF-based Czech Named Entity Recognizer and Consolidation of Czech NER Research |
|
12:30 – 14:00 |
Lunch |
14:00 – 16:05 |
Section Text 2 — Lecture Hall 1
J. Straková: A New State-Of-The-Art Czech Named Entity Recognizer |
N. Mikelic Preradovic: Semi-automatic Verb Valence Frame Assignment Through VerbNet Classification |
N. Mikelic Preradovic: Motion Event in Croatian, English, German and Italian Concerning Path Prefixes and Prepositions |
S. Orasmaa: Automatic Verb Subcategorisation Acquisition for Estonian |
J. Mitrović: Ontology of Rhetorical Figures for Serbian |
|
Section Speech Recognition 1 — Lecture Hall 2
A. Stepikhov: Resolving Ambiguities in Sentence Boundary Detection in Russian Spontaneous Speech |
L. Orosanu: Comparison and Analysis of Several Phonetic Decoding Approaches |
J. Švec: On the Use of Phoneme Lattices in Spoken Language Understanding |
P. Campr: Online Speaker Adaptation of an Acoustic Model using Face Recognition |
M. Sazhok: Lexical Stress-based Morphological Decomposition and its Application for Ukrainian Speech Recognition |
|
16:05 – 16:30 |
Coffee Break |
16:30 – 18:00 |
Poster Session: Text — Main Lecture Hall
|
19:00 – ... |
Welcome Reception |
Tuesday, September 3
09:00 – 10:00 |
Invited Talk — Main Lecture Hall
R. Steinberger: Multilingual Media Monitoring and Text Analysis Challenges for Highly Inflected Languages
|
10:00 – 10:30 |
Coffee Break |
10:30 – 12:10 |
Section Speech Recognition 2 — Lecture Hall 1
M. Kuchařová: On the Quantitative and Qualitative Speech Changes of the Czech Radio Broadcasts News within Years 1969 - 2005 |
J. Pálfy: Algorithms for Dysfluency Detection in Symbolic Sequences using Suffix Arrays |
J. Lehečka: Improving Speech Recognition by Detecting Foreign Inclusions and Generating Pronunciations |
A. Beke: A Logistic Regression Approach for the Improvement of Keyword Spotting based on Phonological Phrasing |
|
Section Speech Synthesis 1 — Lecture Hall 2
J. Přibil: Experiment with Evaluation of Quality of the Synthetic Speech by the GMM Classifier |
Z. Hanzlíček: Experiments on Reducing Footprint of Unit Selection TTS System |
L. Latacz: Speaker-specific Pronunciation for Speech Synthesis |
J. Vít: Concatenation Artifact Detection Trained from Listeners Evaluations |
|
12:30 – 14:00 |
Lunch |
14:00 – 16:05 |
Section Text 3 — Lecture Hall 1
N. Karanikolas: Structuring a Multimedia Tri-dialectal Dictionary |
O. Polacek: Efficiency of Multi-tap Text Entry Method on Interactive Television |
Z. Agic: Three Syntactic Formalisms for Data-Driven Dependency Parsing of Croatian |
J. Chaloupka: Downdating Lexicon and Language Model for Automatic Transcription of Czech Historical Spoken Documents |
I. Nagy: English Noun Compound Detection With Wikipedia-Based Methods |
|
Section Neural Networks — Lecture Hall 2
Y. Shi: K-component Adaptive Recurrent Neural Network Language Models |
T. Grósz: A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition |
L. David: A Machine Learning Based Approach for Vocabulary Selection for Speech Transcription |
G. Kovács: The Joint Optimization of Spectro-Temporal Features and Neural Net Classifiers |
D. Soutner: Application of LSTM Neural Networks in Language Modelling |
|
16:30 – ... |
Excursion to the Pilsner-Urquell Brewery — beer tasting, traditional Czech nosh-up in the brewery pub
|
Wednesday, September 4
09:00 – 10:00 |
Invited Talk — Main Lecture Hall
R. Cole: Spoken Dialogs with Children for Science Learning and Literacy
|
10:00 – 11:00 |
Invited Talk — Main Lecture Hall
V. Zakharov: Russian Corpora: Comparison and Usage
|
11:00 – 11:30 |
Coffee Break |
11:30 – 12:20 |
Section Machine Translation — Lecture Hall 1
A. Han: Automatic Machine Translation Evaluation with Part-Of-Speech Information |
D. Zeman: Scratching the Surface of Possible Translations |
|
Section Speech Synthesis 2 — Lecture Hall 2
M. Legát: Configuring TTS Evaluation Method Based on Unit Cost Outlier Detection |
M. Rusko: Expressive speech synthesis for urgent warning messages generation in Romani and Slovak |
|
12:30 – 14:00 |
Lunch |
14:00 – 15:15 |
Section Parsing — Lecture Hall 1
T. Jelínek: Improving Dependency Parsing by Filtering Linguistic "Noise" |
A. Radziszewski: Using Low-cost Annotation to Train a Reliable Czech Shallow Parser |
J. Matoušek: SVM-Based Detection of Misannotated Words in Read Speech Corpora |
|
Section Speech Synthesis 3 — Lecture Hall 2
M. Pobar: A Comparison of Two Approaches to Bilingual HMM-based Speech Synthesis |
D. Tihelka: Robust Methodology for TTS Enhancement Evaluation |
|
15:15 – 15:45 |
Coffee Break |
15:45 – 17:30 |
Poster Session: Speech — Main Lecture Hall
|
19:00 – ... |
Closing Ceremony
|
Thursday, September 5
09:00 – 20:00 |
Conference Trip to Cheb, SOOS Natural Preserve, and Skalná |
whole day |
Departures (of those who miss the beautiful conference trip) |