Posted inLinguistique en Belgique

6th International Conference on Statistical Language and Speech Processing

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