Search Results for author: Martine Adda-Decker

Found 25 papers, 1 papers with code

Extracting Linguistic Knowledge from Speech: A Study of Stop Realization in 5 Romance Languages

no code implementations LREC 2022 Yaru Wu, Mathilde Hutin, Ioana Vasilescu, Lori Lamel, Martine Adda-Decker

This paper builds upon recent work in leveraging the corpora and tools originally used to develop speech technologies for corpus-based linguistic studies.

speech-recognition Speech Recognition

L\'enition et fortition des occlusives en coda finale dans deux langues romanes : le fran\ccais et le roumain (Lenition and fortition of word-final stops in two Romance languages: French and Romanian)

no code implementations JEPTALNRECITAL 2020 Mathilde Hutin, Ad{\`e}le Jatteau, Ioana Vasilescu, Lori Lamel, Martine Adda-Decker

D{\`e}s lors, il est int{\'e}ressant de se pencher sur des ph{\'e}nom{\`e}nes phonologiques largement attest{\'e}s dans les langues en diachronie comme en synchronie pour {\'e}tablir leur {\'e}mergence ou non dans des langues qui n{'}y sont pas encore sujettes.

Lenition and Fortition of Stop Codas in Romanian

no code implementations LREC 2020 Mathilde Hutin, Oana Niculescu, Ioana Vasilescu, Lori Lamel, Martine Adda-Decker

The present paper aims at providing a first study of lenition- and fortition-type phenomena in coda position in Romanian, a language that can be considered as less-resourced.

Alignement de s\'equences phon\'etiques pour une analyse phonologique des erreurs de transcription automatique (Phonetic sequences alignment for a phonemic analysis of automatic speech transcription errors )

no code implementations JEPTALNRECITAL 2016 Camille Dutrey, Martine Adda-Decker, Naomi Yamaguchi

La transcription automatique de la parole obtient aujourd{'}hui des performances {\'e}lev{\'e}es avec des taux d{'}erreur qui tombent facilement en dessous de 10{\%} pour une parole journalistique.

Production des voyelles parl\'ees et chant\'ees dans le Cantu in Paghjella (Production of spoken and sung vowels in Cantu in Paghjella)

no code implementations JEPTALNRECITAL 2016 Claire Pillot-Loiseau, Patrick Chawah, Ang{\'e}lique Amelot, Gr{\'e}goire Bachman, Catherine Herrgott, Martine Adda-Decker, Lise Crevier-Buchman

Quelles sont les caract{\'e}ristiques acoustiques et articulatoires des voyelles parl{\'e}es et chant{\'e}es du Cantu in Paghjella (polyphonie corse {\`a} trois voix), en fonction du chanteur, de la voyelle et de la fr{\'e}quence fondamentale ?

Sur les traces acoustiques de /ʃ/ et /\cc/ en allemand L2 (Acoustic tracing of /S/ and /\cc/ in German L2)

no code implementations JEPTALNRECITAL 2016 Jane Wottawa, Martine Adda-Decker

Les apprenants fran{\c{c}}ais de l{'}allemand ont des difficult{\'e}s {\`a} produire la fricative palatale sourde allemande /{\c{c}}/ (Ich-Laut) et ont tendance {\`a} la remplacer par la fricative post-alv{\'e}olaire /S/.

French Learners Audio Corpus of German Speech (FLACGS)

no code implementations LREC 2016 Jane Wottawa, Martine Adda-Decker

The French Learners Audio Corpus of German Speech (FLACGS) was created to compare German speech production of German native speakers (GG) and French learners of German (FG) across three speech production tasks of increasing production complexity: repetition, reading and picture description.

ETER : a new metric for the evaluation of hierarchical named entity recognition

no code implementations LREC 2014 Mohamed Ben Jannet, Martine Adda-Decker, Olivier Galibert, Juliette Kahn, Sophie Rosset

We then introduce a new metric, the Entity Tree Error Rate (ETER), to evaluate hierarchical and structured named entity detection, classification and decomposition.

Entity Extraction using GAN General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.