SLSP 2017 Program


Invited lectures: 45 minutes for presentation + 5 minutes for questions
Contributed talks: 23 minutes for presentation + 2 minutes for questions
Posters: 10 minutes for presentation


Monday, October 23

09:00 - 09:30Registration
09:30 - 09:40Opening
09:40 - 10:30Haizhou Li: Recent Advances in Singing Synthesis - Invited lecture
10:30 - 11:00Coffee break
11:00 - 12:15 Mercedes García Martínez, Loïc Barrault and Fethi Bougares. Neural Machine Translation by Generating Multiple Linguistic Factors

Denis Jouvet, Katarina Bartkova, Mathilde Dargnat and Lou Lee. Analysis and Automatic Classification of Some Discourse Particles on a Large Set of French Spoken Corpora

Javad Nouri and Roman Yangarber.Toward Learning Morphology of Natural Language as a Finite-state Grammar
12:15 - 13:45Lunch
13:45 - 15:00 Ferdinand Fuhrmann, Anna Maly, Christina Leitner and Franz Graf. Three Experiments on the Application of Automatic Speech Recognition in Industrial Environments

Sahar Ghannay, Yannick Estève and Nathalie Camelin. Enriching Confusion Networks for Post-processing

Alp Öktem, Mireia Farrús and Leo Wanner. Attentional Parallel RNNs for Generating Punctuation in Transcribed Speech

15:00 - 15:15Break
15:15 - 16:30 Céline Manenti, Thomas Pellegrini and Julien Pinquier. Unsupervised Speech Unit Discovery using k-means and Neural Networks

Gueorgui Pironkov, Stéphane Dupont, Sean Wood and Thierry Dutoit. Noise and Speech Estimation as Auxiliary Tasks for Robust Speech Recognition

Radek Šafarík and Jan Nouza. Unified Approach to Development of ASR Systems for East Slavic Languages

Tuesday, October 24

09:00 - 09:50Bhiksha Raj Ramakrishnan: An Introduction to Neural Networks - Invited lecture
09:50 - 10:20Coffee break
10:20 - 11:35 Sadeen Alharbi, Madina Hasan and Anthony A.J. Simons. Detecting Stuttering Events in Transcripts of Children's Speech

Kevin El Haddad, Ilaria Torre, Emer Gilmartin, Huseyin Cakmak, Stéphane Dupont, Thierry Dutoit and Nick Campbell. Introducing AmuS: The Amused Speech Database

Abdelwahab Heba, Thomas Pellegrini, Tom Jorquera, Régine André-Obrecht and Jean-Pierre Lorré. Lexical Emphasis Detection in Spoken French using F-BANKs and Neural Networks

11:35 - 11:50Break and Group photo
11:50 - 13:05 Michal Novák, Katerina Rysová, Magdaléna Rysová and Jirí Mírovský. Incorporating Coreference to Automatic Evaluation of Coherence in Essays

Etienne Papegnies, Vincent Labatut, Richard Dufour and Georges Linarès. Graph-based Features for Automatic Online Abuse Detection

Mathias Quillot, Cassandre Ollivier, Richard Dufour and Vincent Labatut. Exploring Temporal Analysis of Tweet Contents from Cultural Events

13:05 - 14:35Lunch
14:35 - 15:25Poster presentations

Sunil Kumar Kopparapu and C. Anantaram. Reusing General Purpose ASR for Domain Specific Speech Recognition Using Posteriors

Seongmin Mun, Guillaume Desagulier and Kyungwon Lee. How Can We Capture Multiword Expressions?

Roelant Ossewaarde, Roel Jonkers, Fedor Jalvingh and Roelien Bastiaanse. Automated Detection of Unfilled Pauses in Speech of Healthy and Brain-damaged Individuals

Amit Sangroya, C. Anantaram, Mrinal Rawat and Sunil Kumar Kopparapu. A Bio-inspired Mechanism to Improve Accuracy of ASR Output Sentences

Patrice A. Yemmene and Ron C. Chiang. Automatic Speech Recognition for Ngiemboon Language in Mobile and Cloud Computing
16:00 - 18:00Touristic visit

Wednesday, October 25

09:00 - 09:50Paolo Rosso: Author Profiling in Social Media: The Impact of Emotions in Discourse Analysis - Invited lecture
09:50 - 10:20Coffee break
10:20 - 11:35 Manny Rayner, Nikolaos Tsourakis and Johanna Gerlach. Lightweight Spoken Utterance Classification with CFG, tf-idf and Dynamic Programming

Máté Ákos Tündik, Balázs Tarján and György Szaszák. Low Latency MaxEnt- and RNN-based Word Sequence Models for Punctuation Restoration of Closed Caption Data

Jan Vanek, Daniel Soutner, Josef Psutka and Jan Zelinka. A Regularization Post Layer: An Additional Way how to Make Deep Neural Networks Robust

11:35 - 11:50Break
11:50 - 13:05 Gil Rocha and Henrique Lopes Cardoso. Towards a Relation-based Argument Model for Argumentation Mining

Jose Patino, Héctor Delgado and Nicholas Evans. Speaker Change Detection using Binary Key Modelling with Contextual Information

Marie Tahon, Gwénolé Lecorvé, Damien Lolive and Raheel Qader. Perception of Expressivity in TTS: Linguistics, Phonetics or Prosody?

13:05 - 13:15Closing
13:15 - Lunch