October 15-16, 2018, Mons, Belgium
Co-organized by:
NUMEDIART Institute, University of Mons
LANGUAGE Institute, University of Mons
Institute for Research Development, Training and Advice (IRDTA), Brussels/London
Website: http://slsp2018.irdta.eu/
Program:
Monday, October 15
09:00 – 09:30 Registration
09:30 – 09:40 Opening
09:40 – 10:30 Thomas Hain. Crossing Domains in Automatic Speech Recognition – Invited lecture
10:30 – 11:00 Break
11:00 – 12:15
Amal Houidhek, Vincent Colotte, Zied Mnasri and Denis Jouvet. DNN-based Speech Synthesis for Arabic: Modelling and Evaluation
Antoine Perquin, Gwénolé Lecorvé, Damien Lolive and Laurent Amsaleg. Phone-level Embeddings for Unit Selection Speech Synthesis
Raheel Qader, Gwénolé Lecorvé, Damien Lolive and Pascale Sébillot. Disfluency Insertion for Spontaneous TTS: Formalization and Proof of Concept
12:15 – 13:45 Lunch
13:45 – 14:35 Simon King. Does ‘End-to-End’ Speech Synthesis Make any Sense? – Invited lecture
14:35 – 14:50 Break
14:50 – 16:05
George Christodoulides. Forced Alignment of the Phonologie du Français Contemporain Corpus
Ruei Hung Alex Lee and Jyh-Shing Roger Jang. A Syllable Structure Approach to Spoken Language Recognition
Gueorgui Pironkov, Sean Wood, Stéphane Dupont and Thierry Dutoit. Investigating a Hybrid Learning Approach for Robust Automatic Speech Recognition
16:05 – 16:20 Break
16:20 – 17:30 Poster session I
17:30 – 19:30 Touristic visit
Tuesday, October 16
09:00 – 09:50 Isabel Trancoso. Analysing Speech for Clinical Applications – Invited lecture
09:50 – 10:20 Break
10:20 – 11:35
Jan Vanek, Josef Michalek, Jan Zelinka and Josef Psutka. A Comparison of Adaptation Techniques and Recurrent Neural Network Architectures
Andris Varavs and Askars Salimbajevs. Restoring Punctuation and Capitalization Using Transformer Models
David Awad, Caroline Sabty, Mohamed Elmahdy and Slim Abdennadher. Arabic Name Entity Recognition Using Deep Learning
11:35 – 11:50 Break and Group photo
11:50 – 13:05
Pratik Doshi and Wlodek Zadrozny. Movie Genre Detection Using Topological Data Analysis and Simple Discourse Features
Daniel Grießhaber, Thang Vu and Johannes Maucher. Low-resource Text Classification Using Domain-adversarial Learning
Manny Rayner, Johanna Gerlach, Pierrette Bouillon, Nikolaos Tsourakis and Hervé Spechbach. Handling Ellipsis in a Spoken Medical Phraselator
13:05 – 14:35 Lunch
14:35 – 15:50
Laura García-Sardiña, Manex Serras and Arantza Del Pozo. Knowledge Transfer for Active Learning in Textual Anonymisation
Fernando Gomes and Juan Manuel Adán-Coello. Studying the Effects of Text Preprocessing and Ensemble Methods on Sentiment Analysis of Brazilian Portuguese Tweets
Daniel Lichtblau and Catalin Stoean. Text Documents Encoding through Images for Authorship Attribution
15:50 – 16:05 Break
16:05 – 17:05 Poster session II
17:05 – 17:15 Closing
