09:00 Registration of participants

10:00 Opening & Welcome

10:10 Keynote speaker (EURASIP Seminar): Satoshi Nakamura (Nara Institute of Science and Technology, Japan) – TOWARDS REAL-TIME MULTILINGUAL MULTIMODAL SPEECH-TO-SPEECH TRANSLATION

11:10 Coffee/Tea break

11:40 Session “MULTILINGUAL SPOKEN LANGUAGE TECHNOLOGIES” (4 papers)

11:40 QUERY-BY-EXAMPLE SPOKEN TERM DETECTION EVALUATION ON LOW-RESOURCE LANGUAGES
Xavier Anguera Miro (Telefonica Research Lab, Spain), Luis Javier Rodriguez Fuentes (University of the Basque Country, Spain), Igor Szöke (Brno University of Technology, Czech Republic), Andi Buzo (University Politehnica of Bucharest, Romania), Florian Metze (Carnegie Mellon University, USA), Mikel Penagarikano (University of the Basque Country, Spain)

12:00 FEATURES FOR FACTORED LANGUAGE MODELS FOR CODE-SWITCHING SPEECH
Heike Adel (Karlsruhe Institute of Technology, Germany), Katrin Kirchhoff (University of Washington, USA), Dominic Telaar (Karlsruhe Institute of Technology, Germany), Ngoc Thang Vu (Karlsruhe Institute of Technology, Germany), Tim Schlippe (Karlsruhe Institute of Technology, Germany), Tanja Schultz (Karlsruhe Institute of Technology, Germany)

12:20 ADAPTATING MULTILINGUAL NEURAL NETWORK HIERARCHY TO A NEW LANGUAGE
Frantisek Grezl (Brno University of Technology, Czech Republic), Martin Karafiat (Brno University of Technology, Czech Republic)

12:40 RECENT PROGRESS IN DEVELOPING GRAPHEME-BASED SPEECH RECOGNITION FOR INDONESIAN ETHNIC LANGUAGES: JAVANESE, SUNDANESE, BALINESE AND BATAKS
Sakriani Sakti (Nara Institute of Science and Technology, Japan), Satoshi Nakamura (Nara Institute of Science and Technology, Japan)

13:00 Lunch break

14:00 Session “AUTOMATIC SPEECH RECOGNITION I” (5 papers)

14:00 SPEECH ALIGNMENT AND RECOGNITION EXPERIMENTS FOR LUXEMBOURGISH
Martine Adda-Decker (CNRS-Paris 3/Sorbonne Nouvelle), Lori Lamel (LIMSI-CNRS, France), Gilles Adda (LIMSI-CNRS, France)

14:20 ON USING INTRINSIC SPECTRAL ANALYSIS FOR LOW-RESOURCE LANGUAGES
Reza Sahraeian (KULeuven University, Belgium), Dirk Van Compernolle (KULeuven University, Belgium), Febe de Wet (Meraka Institute, CSIR, South Africa)

14:40 SEMI-SUPERVISED G2P BOOTSTRAPPING AND ITS APPLICATION TO ASR FOR A VERY UNDER-RESOURCED LANGUAGE: IBAN
Sarah Samson Juan (Laboratoire d'Informatique de Grenoble LIG, France), Laurent Besacier (Laboratoire d'Informatique de Grenoble, France), Solange Rossato (Laboratoire d'Informatique de Grenoble, France)

15:00 TOWARDS AUTOMATIC SPEECH RECOGNITION WITHOUT PRONUNCIATION DICTIONARY, TRANSCRIBED SPEECH AND TEXT RESOURCES IN THE TARGET LANGUAGE USING CROSS-LINGUAL WORD-TO-PHONEME ALIGNMENT
Felix Stahlberg (Karlsruhe Institute of Technology, Germany), Tim Schlippe (Karlsruhe Institute of Technology, Germany), Stephan Vogel (Qatar Computing Research Institute, Qatar), Tanja Schultz (Karlsruhe Institute of Technology, Germany)

15:20 RESCORING N-BEST LISTS FOR RUSSIAN SPEECH RECOGNITION USING FACTORED LANGUAGE MODELS
Irina Kipyatkova (St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia), Vasilisa Verkhodanova (St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia), Alexey Karpov (St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences / University ITMO, Russia)

15:40 Coffee/Tea break

16:00 Session “TEXT-TO-SPEECH SYNTHESIS” (4 papers)

16:00 ON MIRANDESE LANGUAGE RESOURCES FOR TEXT-TO-SPEECH
José Pedro Ferreira (Instituto de Linguística Teórica e Computacional, Portugal), Cristiano Chesi (Microsoft Language Development Center, Portugal), Hyongsil Cho (Microsoft Language Development Center, Portugal), Daan Baldewijns (Microsoft Language Development Center, Portugal), Daniela Braga (Microsoft Language Development Center, Portugal), Miguel Sales Dias (Microsoft Language Development Center, Portugal)

16:20 HMM-BASED SPEECH SYNTHESISER FOR THE URDU LANGUAGE
Zeeshan Ahmed (University College Dublin, Ireland), Joao Cabral (Trinity College Dublin, Ireland)

16:40 INTONATION ISSUES IN HMM-BASED SPEECH SYNTHESIS FOR VIETNAMESE
Thi Thu Trang Nguyen (Hanoi University of Science and Technology, Vietnam), Do Dat Tran (MICA-CNRS, Vietnam), Rilliard Albert (LIMSI-CNRS, France), Christophe D'Alessandro (LIMSI-CNRS, France), Thi Ngoc Yen Pham (MICA-CNRS, Vietnam)

17:00 HIGH QUALITY SPEECH SYNTHESIS USING A SMALL SPEECH DATASET
Pavel Chistikov (St. Petersburg National Research University of Information Technologies, Mechanics and Optics, Russia), Andrey Talanov (Speech Technology Center Ltd., Russia)

17:20 Break

18:00 Welcome reception (Dinner on the boat – Neva river cruise with an English spe4aking guide, starts at Universitetskaya Embankment, duration is approximately 2 hours)

Thursday, 15 May 2014

09:20 Keynote speaker: Mark Gales (University of Cambridge, United Kingdom) - SPEECH RECOGNITION AND KEYWORD SPOTTING FOR LOW RESOURCE LANGUAGES: BABEL PROJECT RESEARCH AT CUED

10:20 Coffee/Tea break

10:40 Session “AUTOMATIC SPEECH RECOGNITION II” (6 papers)

10:40 CROSS-WORD SUB-WORD UNITS FOR LOW-RESOURCE KEYWORD SPOTTING
William Hartmann (LIMSI-CNRS, France), Lori Lamel (LIMSI-CNRS, France), Jean-Luc Gauvain (LIMSI-CNRS, France)

11:00 RECENT IMPROVEMENTS IN ESTONIAN LVCSR
Tanel Alumäe (Tallinn University of Technology, Estonia)

11:20 UNSUPERVISED ACOUSTIC MODEL TRAINING USING MULTIPLE SEED ASR SYSTEMS
Horia Cucu (University Politehnica of Bucharest, Romania), Andi Buzo (University Politehnica of Bucharest, Romania), Corneliu Burileanu (University Politehnica of Bucharest, Romania)

11:40 A BILINGUAL STUDY ON THE PREDICTION OF MORPH-BASED IMPROVEMENT
Balázs Tarján (Budapest University of Technology and Economics, Hungary), Tibor Fegyó (AITIA International Inc., Hungary), Péter Mihajlik (THINKTech Research Center Nonprofit LLC, Hungary)

12:00 COMBINING GRAPHEME-TO-PHONEME CONVERTER OUTPUTS FOR ENHANCED PRONUNCIATION GENERATION IN LOW-RESOURCE SCENARIOS
Tim Schlippe (Karlsruhe Institute of Technology, Germany), Wolf Quaschningk (Karlsruhe Institute of Technology, Germany), Tanja Schultz (Karlsruhe Institute of Technology, Germany)

12:20 DEVELOPMENT OF A KOREAN SPEECH RECOGNITION SYSTEM WITH LITTLE ANNOTATED DATA
Antoine Laurent (LIMSI-CNRS, France), Lori Lamel (LIMSI-CNRS, France)

12:40 Lunch break

13:40 Session “AUTOMATIC SPEECH RECOGNITION III” (6 papers)

13:40 TOWARDS THE AUTOMATIC PROCESSING OF YONGNING NA (SINO-TIBETAN): DEVELOPING A ‘LIGHT’ ACOUSTIC MODEL OF THE TARGET LANGUAGE AND TESTING ‘HEAVYWEIGHT’ MODELS FROM FIVE NATIONAL LANGUAGES
Thi Ngoc Diep Do (MICA, Hanoi University of Technology, Vietnam), Alexis Michaud (LACITO, CNRS, France), Eric Castelli (MICA, Hanoi University of Technology, Vietnam)

14:00 EXPLORING PRONUNCIATION VARIANTS FOR ROMANIAN SPEECH-TO-TEXT TRANSCRIPTION
Ioana Vasilescu (LIMSI-CNRS, France), Bianca Vieru (VOCAPIA Research, France), Lori Lamel (LIMSI-CNRS, France)

14:20 CROSS-LANGUAGE MAPPING FOR SMALL-VOCABULARY ASR IN UNDER-RESOURCED LANGUAGES: INVESTIGATING THE IMPACT OF SOURCE LANGUAGE CHOICE
Anjana Vakil (University of Saarland, Germany), Alexis Palmer (University of Saarland, Germany)

14:40 SPEECH-TO-TEXT DEVELOPMENT FOR SLOVAK, A LOW-RESOURCED LANGUAGE
Cong-Thanh Do (LIMSI-CNRS, France), Lori Lamel (LIMSI-CNRS, France), Jean-Luc Gauvain (LIMSI-CNRS, France)

15:00 SEQUENCE MEMOIZER BASED LANGUAGE MODEL FOR RUSSIAN SPEECH RECOGNITION
Daria Vazhenina (The University of Aizu, Japan), Konstantin Markov (The University of Aizu, Japan)

15:20 CODE-SWITCHING SPEECH RECOGNITION FOR CLOSELY RELATED LANGUAGES
Tetyana Lyudovyk (International Research/Training Center for Information Technologies and Systems, Ukraine), Valeriy Pylypenko (International Research/Training Center for Information Technologies and Systems, Ukraine)

15:40 Coffee/Tea break

16:00 Session “SPEECH AND LANGUAGE RESOURCES I” (4 papers)

16:00 THE NCHLT SPEECH CORPUS OF THE SOUTH AFRICAN LANGUAGES
Etienne Barnard (North-West University, South Africa), Marelie Davel (North-West University, South Africa), Charl van Heerden (North-West University, South Africa), Febe de Wet (Meraka Institute, CSIR, South Africa), Jaco Badenhorst (Meraka Institute, CSIR, South Africa)

16:20 COMMUNITY-BASED RESOURCE BUILDING AND DATA COLLECTION
Kristiina Jokinen (University of Helsinki, Finland), Graham Wilcock (University of Helsinki, Finland)

16:40 AUTOMATIC DETECTION OF ANGLICISMS FOR THE PRONUNCIATION DICTIONARY GENERATION: A CASE STUDY ON OUR GERMAN IT CORPUS
Sebastian Leidig (Karlsruhe Institute of Technology, Germany), Tim Schlippe (Karlsruhe Institute of Technology, Germany), Tanja Schultz (Karlsruhe Institute of Technology, Germany)

17:00 A ROBUST DIACRITICS RESTORATION SYSTEM USING UNRELIABLE RAW TEXT DATA
Lucian Petrica (University Politehnica of Bucharest, Romania), Horia Cucu (University Politehnica of Bucharest, Romania), Andi Buzo (University Politehnica of Bucharest, Romania), Corneliu Burileanu (University Politehnica of Bucharest, Romania)

17:20 Break

18:30 Banquet accompanied by live piano music and romances (Restaurant “Literary Cafe” – Nevsky prospect 18, 2nd floor, duration is approximately 3 hours): http://eng.litcafe.su

Friday, 16 May 2014

09:20 Session “SPEECH SIGNAL PROCESSING” (3 papers)

09:20 “STC SPOOFING” DATABASE FOR TEXT-DEPENDENT SPEAKER RECOGNITION EVALUATION
Konstantin Simonchik (Speech Technology Center Ltd., Russia), Vadim Shchemelinin (St. Petersburg National Research University of Information Technologies, Mechanics and Optics, Russia)

09:40 MODELING CODE-SWITCHING SPEECH ON UNDER-RESOUCED LANGUAGES FOR LANGUAGE IDENTIFICATION
Koena Ronny Mabokela (University of Limpopo, South Africa), Madimetja Jonas Manamela (University of Limpopo, South Africa), Mabu Manaileng (University of Limpopo, South Africa)

10:00 TOWARDS LOW-RESOURCE PROSODIC BOUNDARY DETECTION
Bogdan Ludusan (LSCP - EHESS/ENS/CNRS, France), Emmanuel Dupoux (LSCP - EHESS/ENS/CNRS, France)

10:20 Coffee/Tea break

10:40 Session “SPEECH AND LANGUAGE RESOURCES II” (6 papers)

10:40 SPEECH DATA COLLECTION IN AN UNDER-RESOURCED LANGUAGE WITHIN A MULTILINGUAL CONTEXT
Raymond Molapo (Meraka Institute, CSIR, South Africa), Febe de Wet (Meraka Institute, CSIR, South Africa), Etienne Barnard (North-West University, South Africa)

11:00 THE DEVELOPMENT OF NEW CORPORA FOR UNDER-RESOURCED LANGUAGES USING DATA AVAILABLE FOR WELL-RESOURCED ONES
Pavel Skrelin (St. Petersburg State University, Russia), Nina Volskaya (St. Petersburg State University, Russia), Karina Evgrafova (St. Petersburg State University, Russia), Riikka Ullakonoja (University of Jyväskylä, Finland)

11:20 WEB LEXICOGRAPHY FOR AND BY NON-TECH PEOPLE
Dmitri Dmitriev (Institute of Linguistic Research of the Russian Academy of Sciences, Russia)

11:40 PHONETIC TOOL FOR THE TUNISIAN ARABIC
Abir Masmoudi (LIUM, Tunisia), Yannick Estève (LIUM - Université du Maine, France), Mariem Ellouze (MIRACL Laboratory, Tunisia), Fethi Bougares (LIUM, Tunisia), Lamia Hadrich Belguith (MIRACL Laboratory, Tunisia)

12:00 GRAPHEME TO PHONEME CONVERSION: AN ARABIC DIALECT CASE
Salima Harrat (Ecole Normale Supérieure Bouzaréah, Algeria), Karima Meftouh (Badji Mokhtar University, Algeria), Mourad Abbas (CRSTDLA, Algeria), Kamel Smaili (LORIA , Nancy, France)

12:20 SOUNDS AND SYMBOLS: AN OVERVIEW OF DIFFERENT TYPES OF METHODS DEALING WITH LETTERS-TO-SOUNDS RELATIONSHIPS IN A WIDE RANGE OF LANGUAGES IN AUTOMATIC SPEECH RECOGNITION
Maria Goudi (Laboratoire Informatique d'Avignon, Université d'Avignon, France), Pascal Nocera (Laboratoire Informatique d'Avignon, Université d'Avignon, France)

12:40 Lunch break

13:30 Bus excursion with an English speaking guide in and around St. Petersburg city (starts at the workshop venue, duration is 3.5-4 hours)