3rd INTERNATIONAL CONFERENCE ON STATISTICAL LANGUAGE AND SPEECH PROCESSING

SLSP 2015

Budapest, Hungary

November 24-26, 2015

Organised by:

Laboratory of Speech Acoustics
Department of Telecommunications and Telematics
Budapest University of Technology and Economics
http://alpha.tmit.bme.hu/speech/

Research Group on Mathematical Linguistics (GRLMC)
Rovira i Virgili University

http://grammars.grlmc.com/SLSP2015/

**********************************************************************************

PROGRAM

Tuesday, November 24

08:15 - 08:45 Registration

08:45 - 09:00 Opening

09:00 - 09:50 Xavier Carreras: Low-rank Matrix Learning for Compositional Objects, Strings and Trees - Invited Lecture

09:50 - 10:20 Coffee Break

10:20 - 11:35

Khan Baykaner, Mark Huckvale, Iya Whiteley, Oleg Ryumin and Svetlana Andreeva: The Prediction of Fatigue Using Speech as a Biosignal

Tamás Gábor Csapó, Géza Németh and Milos Cernak: Residual-based Excitation with Continuous F0 Modeling in HMM-based Speech Synthesis

Marc Evrard, Albert Rilliard and Christophe d'Alessandro: Evaluation of the Impact of Corpus Phonetic Alignment on the HMM-Based Speech Synthesis Quality

11:35 - 11:50 Break

11:50 - 12:40

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Camille Dutrey, Fabian Santiago and Martine Adda-Decker: Combining Continuous Word Representation and Prosodic Features for ASR Error Prediction

Mark Huckvale and Aimee Webb: A Comparison of Human and Machine Estimation of Speaker Age

12:40 - 14:10 Lunch

14:10 - 15:25

Luis Chiruzzo and Dina Wonsever: Supertagging for a Statistical HPSG Parser for Spanish

Mathilde Dargnat, Katarina Bartkova and Denis Jouvet: Discourse Particles in French: Prosodic Parameters Extraction and Analysis

Julia Efremova, Alejandro Montes García, Jianpeng Zhang and Toon Calders: Effects of Evolutionary Linguistics in Text Classification

15:25 - 15:40 Break

15:40 - 16:55

Fatemeh Ghiyafeh Davoodi and Yllias Chali: Semi-Extractive Multi-Document Summarization via Submodular Functions

Pavel Král, Ladislav Lenc and Christophe Cerisara: Semantic Features for Dialogue Act Recognition

André Mansikkaniemi and Mikko Kurimo: Unsupervised and User Feedback Based Lexicon Adaptation for Foreign Names and Acronyms

Wednesday, November 25

09:00 - 09:50 Sebastian Riedel: Towards Two-way Interaction with Reading Machines - Invited Lecture

09:50 - 10:20 Coffee Break

10:20 - 11:35

Denis Jouvet and Katarina Bartkova: Acoustical Frame Rate and Pronunciation Variant Statistics

Tatiana Kachkovskaia: The Influence of Boundary Depth on Phrase-final Lengthening in Russian

Ferenc Kazinczi, Krisztina Mészáros and Klára Vicsi: Automatic Detection of Voice Disorders

11:35 - 11:50 Break and Group Photo

11:50 - 12:40

Rasa Lileikyte, Lori Lamel and Jean-Luc Gauvain: Conversational Telephone Speech Recognition for Lithuanian

Erfan Loweimi, Mortaza Doulaty, Jon Barker and Thomas Hain: Long-term Statistical Feature Extraction from Speech Signal and its Application in Emotion Recognition

12:40 - 14:10 Lunch

14:10 - 15:25

Lorenzo Ferrone, Fabio Massimo Zanzotto and Xavier Carreras: Decoding Distributed Tree Structures

Luiza Orosanu and Denis Jouvet: Combining Lexical and Prosodic Features for Automatic Detection of Sentence Modality in French

Konstantinos Pechlivanis and Stasinos Konstantopoulos: Corpus Based Methods for Learning Models of Metaphor in Modern Greek

15:25 - 15:40 Break

15:40 - 16:30

Lina Maria Rojas-Barahona and Christophe Cerisara: Weakly Supervised Discriminative Training of Linear Models for Natural Language Processing

Daniel Soutner and Ludek Müller: On Continuous Space Word Representations as Input of LSTM Language Model

16:30 - 18:30 Touristic visit

Thursday, November 26

09:00 - 09:50 Steve Young: Open-domain Statistical Spoken Dialogue Systems - Invited Lecture

09:50 - 10:20 Coffee Break

10:20 - 11:35

Bogdan Ludusan, Antonio Origlia and Emmanuel Dupoux: Rhythm-Based Syllabic Stress Learning without Labelled Data

Raheel Qader, Gwénolé Lecorvé, Damien Lolive and Pascale Sébillot: Probabilistic Speaker Pronunciation Adaptation for Spontaneous Speech Synthesis Using Linguistic Features

Sarah Samson Juan, Laurent Besacier, Benjamin Lecouteux and Tien-Ping Tan: Merging of Native and Non-native Speech for Low-resource Accented ASR

11:35 - 11:50 Break

11:50 - 12:40

Jan Zelinka, Jan Vanek and Ludek Müller: Neural-Network-based Spectrum Processing for Speech Recognition and Speaker Verification

Xiaoyi Wu, Yuji Matsumoto, Kevin Duh and Hiroyuki Shindo: An Improved Hierarchical Word Sequence Language Model Using Word Association

12:40 - 12:55 Closing