Search

Your search keyword '"Jonathan Chevelu"' showing total 10 results
Start Over Author "Jonathan Chevelu" Topic business
10 results on '"Jonathan Chevelu"'

1. Neural-Driven Search-Based Paraphrase Generation

Author

Damien Lolive, Jonathan Chevelu, Betty Fabre, Tanguy Urvoy, Expressiveness in Human Centered Data/Media (EXPRESSION), MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Orange Labs, and Université de Rennes (UR)

Subjects
Perplexity, Syntax (programming languages), Computer science, business.industry, computer.software_genre, Paraphrase, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Set (abstract data type), Tree (data structure), Semantic similarity, Search problem, Artificial intelligence, business, computer, Natural language processing, Sentence, ComputingMilieux_MISCELLANEOUS
Abstract

We study a search-based paraphrase generation scheme where candidate paraphrases are generated by iterated transformations from the original sentence and evaluated in terms of syntax quality, semantic distance, and lexical distance. The semantic distance is derived from BERT, and the lexical quality is based on GPT2 perplexity. To solve this multi-objective search problem, we propose two algorithms: Monte-Carlo Tree Search For Paraphrase Generation (MCPG) and Pareto Tree Search (PTS). We provide an extensive set of experiments on 5 datasets with a rigorous reproduction and validation for several state-of-the-art paraphrase generation algorithms. These experiments show that, although being non explicitly supervised, our algorithms perform well against these baselines.

Published
2021

2. Mama/Papa, Is this Text for Me?

Author

Delphine Battistelli, Jonathan Chevelu, Rashedur Rahman, Aline Étienne, Gwénolé Lecorvé, Nicolas Béchet, Expressiveness in Human Centered Data/Media (EXPRESSION), MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Modèles, Dynamiques, Corpus (MoDyCo), Université Paris Nanterre (UPN)-Centre National de la Recherche Scientifique (CNRS), ANR-19-CE38-0014,TextoKids,Accès au contenu informationnel de textes par les enfants(2019), ANR-16-CE23-0019,TREMoLo,Transformation de registres par extraction de motifs langagiers(2016), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), IRT SystemX, and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique)

Subjects
050101 languages & linguistics, Computer science, business.industry, 05 social sciences, Context (language use), 010501 environmental sciences, computer.software_genre, 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Recurrent neural network, ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, 0501 psychology and cognitive sciences, The Internet, Artificial intelligence, business, Baseline (configuration management), computer, Sentence, Natural language processing, ComputingMilieux_MISCELLANEOUS, 0105 earth and related environmental sciences
Abstract

International audience; Children have less linguistic skills than adults, which makes it more difficult for them to understand some texts, for instance when browsing the Internet. In this context, we present a novel method which predicts the minimal age from which a text can be understood. This method analyses each sentence of a text using a recurrent neural network, and then aggregates this information to provide the text-level prediction. Different approaches are proposed and compared to baseline models, at sentence and text levels. Experiments are carried out on a corpus of 1, 500 texts and 160K sentences. Our best model, based on LSTMs, outperforms state-of-the-art results and achieves mean absolute errors of 1.86 and 2.28, at sentence and text levels, respectively.

Published
2020

3. Corpus design for expressive speech: impact of the utterance length

Author

Meysam Shamsi, Nelly Barbot, Damien Lolive, Jonathan Chevelu, Expressiveness in Human Centered Data/Media (EXPRESSION), Université de Bretagne Sud (UBS)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Université de Rennes (UR), MEDIA ET INTERACTIONS (IRISA-D6), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Centre National de la Recherche Scientifique (CNRS), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes)

Subjects
Optimization problem, Computer science, media_common.quotation_subject, Concatenation, Speech synthesis, 02 engineering and technology, computer.software_genre, Task (project management), 0202 electrical engineering, electronic engineering, information engineering, Selection (linguistics), Quality (business), [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], media_common, business.industry, 020206 networking & telecommunications, voice corpus design, utterance length, Constraint (information theory), ComputingMethodologies_PATTERNRECOGNITION, 020201 artificial intelligence & image processing, Artificial intelligence, business, Text to speech, computer, Utterance, Natural language processing
Abstract

International audience; Voice corpus plays a crucial role in the quality of the synthetic speech generation, specially under a length constraint. Creating a new voice is costly and the recording script selection for an expressive TTS task is generally considered as an optimization problem in order to achieve a rich and parsimonious corpus. In order to vocalize a given book using a TTS system, we investigate four script selection approaches. Based on preliminary observations, we simply propose to select shortest utterances of the book and compare the achievements of this method with state of the art ones for two books, with different utterance lengths and styles, using two kinds of concatenation based TTS systems. The study of the TTS costs indicates that selecting the shortest utterances could result in better synthetic quality, which is confirmed by a perceptual test. By investigating usual criteria for corpus design in literature like unit coverage or distribution similarity of units, it turns out that they are not pertinent metrics in the framework of this study.

Published
2020

4. How to compare TTS systems: a new subjective evaluation methodology focused on differences

Author

Damien Lolive, David Guennec, Jonathan Chevelu, Sébastien Le Maguer, Expressiveness in Human Centered Data/Media (EXPRESSION), Université de Bretagne Sud (UBS)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Saarland University [Saarbrücken], CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), and Lolive, Damien

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, subjective evaluation, Computer science, Process (engineering), Speech recognition, Speech synthesis, Sample (statistics), 02 engineering and technology, computer.software_genre, Machine learning, Field (computer science), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Domain (software engineering), 030507 speech-language pathology & audiology, 03 medical and health sciences, speech synthesis, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Measure (data warehouse), business.industry, 020206 networking & telecommunications, Speech processing, [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD], [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], Artificial intelligence, [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], 0305 other medical science, Focus (optics), business, computer
Abstract

International audience; Subjective evaluation is a crucial problem in the speech processing community and especially for the speech synthesis field, no matter what system is used. Indeed, when trying to assess the effectiveness of a proposed method, researchers usually conduct subjective evaluations by randomly choosing a small set of samples, from the same domain, taken from a baseline system and the proposed one. When selecting them randomly, statistically, samples with almost no differences are evaluated and the global measure is smoothed which may lead to judge the improvement not significant.To solve this methodological flaw, we propose to compare speech synthesis systems on thousands of generated samples from various domains and to focus subjective evaluations on the most relevant ones by computing a normalized alignment cost between sample pairs. This process has been successfully applied both in the HTS statistical framework and in the corpusbased approach. We have conducted two perceptive experiments by generating more than 27,000 samples for each system under comparison. A comparison between tests involving most different samples and randomly chosen samples shows clearly that the proposed approach

Published
2015

5. Large Linguistic Corpus Reduction with SCP algorithms

Author

Olivier Boëffard, Nelly Barbot, Arnaud Delhay, Jonathan Chevelu, Expressiveness in Human Centered Data/Media (EXPRESSION), Université de Bretagne Sud (UBS)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)

Subjects
Text corpus, Linguistics and Language, Computer science, ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing/I.2.7.5: Speech recognition and synthesis, Context (language use), Machine learning, computer.software_genre, Language and Linguistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], symbols.namesake, Artificial Intelligence, Greedy algorithm, business.industry, Set cover problem, Linguistics, Computer Science Applications, Rule of thumb, Lagrangian relaxation, Metric (mathematics), symbols, Artificial intelligence, business, Heuristics, computer, Algorithm, Natural language processing
Abstract

Linguistic corpus design is a critical concern for building rich annotated corpora useful in different domains of applications. For example, speech technologies such as ASR (Automatic Speech Recognition) or TTS (Text-to-Speech) need a huge amount of speech data to train data-driven models or to produce synthetic speech. Collecting data is always related to costs (recording speech, verifying annotations, etc.), and as a rule of thumb, the more data you gather, the more costly your application will be. Within this context, we present in this article solutions to reduce the amount of linguistic text content while maintaining a sufficient level of linguistic richness required by a model or an application. This problem can be formalized as a Set Covering Problem (SCP) and we evaluate two algorithmic heuristics applied to design large text corpora in English and French for covering phonological information or POS labels. The first considered algorithm is a standard greedy solution with an agglomerative/spitting strategy and we propose a second algorithm based on Lagrangian relaxation. The latter approach provides a lower bound to the cost of each covering solution. This lower bound can be used as a metric to evaluate the quality of a reduced corpus whatever the algorithm applied. Experiments show that a suboptimal algorithm like a greedy algorithm achieves good results; the cost of its solutions is not so far from the lower bound (about 4.35% for 3-phoneme coverings). Usually, constraints in SCP are binary; we proposed here a generalization where the constraints on each covering feature can be multi-valued.

Published
2015

6. Do not build your TTS training corpus randomly

Author

Damien Lolive, Jonathan Chevelu, Lolive, Damien, Expressiveness in Human Centered Data/Media (EXPRESSION), Université de Bretagne Sud (UBS)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)

Subjects
Text corpus, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Subjective evaluation, Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Speech recognition, media_common.quotation_subject, Speech synthesis, 02 engineering and technology, computer.software_genre, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 030507 speech-language pathology & audiology, 03 medical and health sciences, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Quality (business), [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], media_common, Corpus reduction, business.industry, Speech corpus, Pragmatics, [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD], Focus (linguistics), Test (assessment), Corpus-based Unit Selection TTS, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 020201 artificial intelligence & image processing, Artificial intelligence, [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], 0305 other medical science, business, computer, Natural language processing
Abstract

International audience; TTS voice building generally relies on a script extracted from a big text corpus while optimizing the coverage of linguistic and phonological events supposedly related to voice acoustic quality. Previous works have shown differences on objective measures between smartly reduced and random corpora, but not when subjective evaluations are performed. For us, those results do not come from corpus reduction utility but from evaluations that smooth differences. In this article, we highlight those differences in a subjective test, by clustering test corpora according to a distance between signals so as to focus on different synthesized stimuli. The results show that covering appropriate features has a real impact on the perceived quality.

Published
2015

7. Introduction of a new paraphrase generation tool based on Monte-Carlo sampling

Author

Jonathan Chevelu, Yves Lepage, Thomas Lavergne, and Thierry Moudenc

Subjects
Machine translation, Computer science, business.industry, Monte Carlo method, Sampling (statistics), Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing), Function (mathematics), Viterbi algorithm, Machine learning, computer.software_genre, Paraphrase, Task (project management), Constraint (information theory), symbols.namesake, symbols, Artificial intelligence, business, computer
Abstract

We propose a new specifically designed method for paraphrase generation based on Monte-Carlo sampling and show how this algorithm is suitable for its task. Moreover, the basic algorithm presented here leaves a lot of opportunities for future improvement. In particular, our algorithm does not constraint the scoring function in opposite to Viterbi based decoders. It is now possible to use some global features in paraphrase scoring functions. This algorithm opens new outlooks for paraphrase generation and other natural language processing applications like statistical machine translation.

Published
2009

8. Driving Hierarchy Construction via Supervised Learning: Application to Osteo-Articular Medical Images Database

Author

K. Yousfi, C. Ambroise, Jean-Pierre Cocquerez, and Jonathan Chevelu

Subjects
Hierarchy, Contextual image classification, Computer science, business.industry, Supervised learning, Image segmentation, Machine learning, computer.software_genre, Semantic similarity, Segmentation, Artificial intelligence, business, Classifier (UML), computer
Abstract

Most similarity or dissimilarity measures used in merging and splitting segmentation methods include in almost all cases a single radiometrical information, integrate rarely geometrical information and ignore the high level knowledge on the image. Consequently, the region hierarchies issued from these approaches may suffer from a structural instability and deficiency in the semantic of the regions due to the image content, its high variability and the complexity of the meaningful regions which compose this image. In this paper, we propose to enhance the "semantic" content of the hierarchy by means of an additional term called "contextual cost". This term integrates the high level knowledge on the image which is derived from a classifier after a supervised learning on the semantic classes composing the image. Its purpose is to better guide the merging process towards the construction of meaningful regions.

Published
2006

9. Supervised Learning for Guiding Hierarchy Construction: Application to Osteo-Articular Medical Images Database

Author

C. Ambroise, Jonathan Chevelu, K. Yousfi, and Jean-Pierre Cocquerez

Subjects
Hierarchy, Computer science, business.industry, Supervised learning, Segmentation, Image segmentation, Artificial intelligence, Machine learning, computer.software_genre, business, computer, Classifier (UML)
Abstract

Most merging and splitting segmentation methods aim to construct a hierarchical structure from an image by minimizing or maximizing a homogeneity measure. This latter generally includes radiometrical information, but rarely includes geometrical information and ignore the high level information on the image content. Moreover, the hierarchies issued from these approaches may suffer from a structural instability and deficiency in the "semantic" of the regions related to the image content and to the energy or the criterion which does not contain any high level prior knowledge. In this paper, we propose to improve the semantic content of the hierarchy by adding a new term called "contextual cost". This term integrates the prior knowledge on the image, derived from a classifier after a supervised learning on the semantic classes composing the image. Its purpose is to better drive the merging process in the construction of meaningful regions by penalizing spurious fusions.

Published
2006

Catalog

Books, media, physical & digital resources
See catalog results