41 |
Duration- vs. Style-Dependent Vowel Variation: a Multiparametric Investigation
|
|
|
|
In: ICPHS Proceedings ; 18th International Congress of Phonetic Sciences (ICPhS'15) ; https://hal.archives-ouvertes.fr/hal-01251372 ; 18th International Congress of Phonetic Sciences (ICPhS'15), Aug 2015, Glasgow, United Kingdom. pp.5 ; http://www.icphs2015.info/ (2015)
|
|
BASE
|
|
Show details
|
|
42 |
Voicing Variations in French Obstruents: Distribution and Acoustic Quantification
|
|
|
|
In: 18th International Congress of Phonetic Sciences (ICPhS'15) ; https://hal.archives-ouvertes.fr/hal-01251373 ; 18th International Congress of Phonetic Sciences (ICPhS'15), Aug 2015, Glasgow, United Kingdom. pp.5 (2015)
|
|
BASE
|
|
Show details
|
|
43 |
Automatic language identity tagging on word and sentence-level in multilingual text sources: a case-study on Luxembourgish
|
|
|
|
In: International Conference on Language Resources and Evaluation ; https://hal.archives-ouvertes.fr/hal-01843401 ; International Conference on Language Resources and Evaluation, May 2014, Reykjavik, Iceland (2014)
|
|
BASE
|
|
Show details
|
|
44 |
Automatic Language Identity Tagging on Word and Sentence-Level in Multilingual Text Sources: a Case-Study on Luxembourgish
|
|
|
|
In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14) ; Ninth International Conference on Language Resources and Evaluation (LREC'14) ; https://hal.archives-ouvertes.fr/hal-01134776 ; Ninth International Conference on Language Resources and Evaluation (LREC'14), European Language Resources Association (ELRA), May 2014, Reykjavik, Iceland. pp.3300-3304 ; http://lrec2014.lrec-conf.org/en/ (2014)
|
|
BASE
|
|
Show details
|
|
45 |
Modélisation acoustico-phonétique de langues peu dotées : Études phonétiques et travaux de reconnaissance automatique en luxembourgois
|
|
|
|
In: Journées d'Etude sur la Parole ; https://hal.archives-ouvertes.fr/hal-01843399 ; Journées d'Etude sur la Parole, Jan 2014, Le Mans, France (2014)
|
|
BASE
|
|
Show details
|
|
46 |
Traitements automatiques de l’oral et de l’écrit
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-01420863 ; France. 141, pp.4-8, 2014 (2014)
|
|
BASE
|
|
Show details
|
|
47 |
How to assess the quality of automatic transcriptions for the extraction of named entities? ; Comment évaluer la qualité des transcriptions automatiques pour la détection d’entités nommées ?
|
|
|
|
In: Actes des XXXe Journées d'Études sur la Parole (JEP'14) ; XXXe Journées d'Études sur la Parole (JEP'14) ; https://hal.archives-ouvertes.fr/hal-01134868 ; XXXe Journées d'Études sur la Parole (JEP'14), Jun 2014, Le Mans, France. pp.430-437 ; http://www-lium.univ-lemans.fr/jep2014/ (2014)
|
|
Abstract:
International audience ; The standard metric used to evaluate the performance of Automatic Speech Recognition (ASR) systems is the Word Error Rate (WER). This well known metric is very useful when ASR systems are used in isolation, but nowadays these systems are often combined with other natural language processing (NLP) systems to perform tasks like speech translation, man-machine dialogue, or information retrieval from speech. That situation exacerbates the need expressed by the speech processing community for a new evaluation metric which can estimate the quality of automatic transcription taking into account their applicative context. We propose an alternative evaluation metric to the WER in the context of Named Entity detection in spoken documents. Our proposed metric makes use of posterior probability to estimate the risk of error that ASR errors can induce to the Named Entity detection system applied downstream. ; La métrique standard pour l’évaluation des performances des systèmes de reconnaisance automatique de la parole est le taux d’erreur mot (Word Error Rate). Cette métrique est très efficace quand il s’agit d’évaluer les systèmes de transcription seules, mais de nos jours les systèmes RAP sont très souvent combinés avec d’autres briques technologiques de Traitement Automatique des Langues telles que la traduction de la parole, le dialogue homme-machine, ou l’extraction d’informations. Cette situation exacerbe le besoin exprimé par la communauté pour une métrique qui permet d’estimer la qualité des transcriptions automatiques en tenant compte du contexte applicatif. Nous proposons une métrique alternative au WER qui permet d’évaluer la qualité des transcriptions automatiques dans un contexte d’extraction d’entités nommées à partir de la parole. Notre métrique utilise des probabilités a posteriori pour estimer le risque d’erreur induit par les erreurs de transcription sur un système de détection d’entités nommées appliqué en aval.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [SHS.LANGUE]Humanities and Social Sciences/Linguistics; Automatic Speech Recognition; ETER; Evaluation; Extraction d’Entités Nommées; Metrics; Métrique; Named Entities Recognition; Reconnaissance de la Parole; WER
|
|
URL: https://hal.archives-ouvertes.fr/hal-01134868
|
|
BASE
|
|
Hide details
|
|
48 |
Human Annotation of ASR Error Regions: is "gravity" a Sharable Concept for Human Annotators?
|
|
|
|
In: Ninth International Conference on Language Resources and Evaluation (LREC'14) ; https://hal.archives-ouvertes.fr/hal-01134802 ; Ninth International Conference on Language Resources and Evaluation (LREC'14), May 2014, Reykjavik, Iceland. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pp.3050-3056, 2014 ; http://lrec2014.lrec-conf.org/en/ (2014)
|
|
BASE
|
|
Show details
|
|
49 |
A CRF-Based Approach to Automatic Disfluency Detection in a French Call-Centre Corpus
|
|
|
|
In: Proceedings of the 15th Annual Conference of the International Speech Communication Association (Interspeech'14) ; 15th Annual Conference of the International Speech Communication Association (Interspeech'14) ; https://hal.archives-ouvertes.fr/hal-01134812 ; 15th Annual Conference of the International Speech Communication Association (Interspeech'14), International Speech Communication Association (ISCA), Sep 2014, Singapour, Singapore. pp.2897-2901 ; http://www.interspeech2014.org/public.php?page=home.html (2014)
|
|
BASE
|
|
Show details
|
|
50 |
ETER: a New Metric for the Evaluation of Hierarchical Named Entity Recognition
|
|
|
|
In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14) ; Ninth International Conference on Language Resources and Evaluation (LREC'14) ; https://hal.archives-ouvertes.fr/hal-01134713 ; Ninth International Conference on Language Resources and Evaluation (LREC'14), European Language Resources Association (ELRA), May 2014, Reykjavik, Iceland. pp.3987-3994 ; http://lrec2014.lrec-conf.org/en/ (2014)
|
|
BASE
|
|
Show details
|
|
51 |
Reconnaissance automatique de la parole
|
|
|
|
In: ISSN: 0222-9838 ; EISSN: 1783-1601 ; L'information grammaticale ; https://hal.archives-ouvertes.fr/hal-01135037 ; L'information grammaticale, Peeters Publishers, 2014, TRAITEMENTS AUTOMATIQUES DE L’ORAL ET DE L’ÉCRIT (1) Panorama des recherches et des technologies actuelles, 141, pp.10 (2014)
|
|
BASE
|
|
Show details
|
|
52 |
Speech Alignment and Recognition Experiments for Luxembourgish
|
|
|
|
In: Proceedings of the 4th International Workshop on Spoken Language Technologies for Underresourced Languages ; 4th International Workshop on Spoken Language Technologies for Underresourced Languages ; https://hal.archives-ouvertes.fr/hal-01134824 ; 4th International Workshop on Spoken Language Technologies for Underresourced Languages, May 2014, Saint-Petersbourg, Russia. pp.53-60 ; http://www.mica.edu.vn/sltu2014/ (2014)
|
|
BASE
|
|
Show details
|
|
53 |
A First LVCSR System for Luxembourgish, a Low-Resourced European Language
|
|
|
|
In: Human Language Technology Challenges for Computer Science and Linguistics ; https://hal.archives-ouvertes.fr/hal-01135103 ; Zygmunt Vetulani; Joseph Mariani. Human Language Technology Challenges for Computer Science and Linguistics, 8387, Springer International Publishing, pp.479-490, 2014, 5th Language and Technology Conference, LTC 2011, Poznań, Poland, November 25--27, 2011, Revised Selected Papers, 978-3-319-08957-7. ⟨10.1007/978-3-319-08958-4_39⟩ (2014)
|
|
BASE
|
|
Show details
|
|
54 |
How are word-final schwas different in the North and South of France?
|
|
|
|
In: 14th Annual Conference of the International Speech Communication Association (Interspeech'13) ; https://hal.archives-ouvertes.fr/hal-01134916 ; 14th Annual Conference of the International Speech Communication Association (Interspeech'13), Aug 2013, Lyon, France. Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech'13), pp.305-309, 2014 ; http://www.interspeech2013.org/ (2013)
|
|
BASE
|
|
Show details
|
|
55 |
Recent evolution of non-standard consonantal variants in French broadcast news
|
|
|
|
In: Interspeech ; https://halshs.archives-ouvertes.fr/halshs-00856290 ; Interspeech, Aug 2013, Lyon, France. pp.412-416 (2013)
|
|
BASE
|
|
Show details
|
|
56 |
Recent Evolution of Non Standard Consonantal Variants in French Broadcast News
|
|
|
|
In: Annual Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-01843431 ; Annual Conference of the International Speech Communication Association , International Speech Communication Association, F. Bimbot, C. Cerisara, C. Fougeron, G. Gravier, L. Lamel, F. Pellegrino, P. Perrier, Jan 2013, Lyon, France (2013)
|
|
BASE
|
|
Show details
|
|
57 |
What we can learn from ASR errors about low-resourced languages: a case- study of Luxembourgish and Austrian
|
|
|
|
In: Errors by Humans and Machines in Multimedia, Multimodal, Multilingual Data Processing ; https://hal.archives-ouvertes.fr/hal-01843440 ; Errors by Humans and Machines in Multimedia, Multimodal, Multilingual Data Processing, Jan 2013, Ermenonville, France (2013)
|
|
BASE
|
|
Show details
|
|
58 |
Embosi: automatic alignment with segments and words and phonological mining
|
|
|
|
In: International Conference on Bantu Languages ; https://hal.archives-ouvertes.fr/hal-01843438 ; International Conference on Bantu Languages, Jan 2013, Paris, France (2013)
|
|
BASE
|
|
Show details
|
|
59 |
What we can learn from asr errors about low-resourced languages: a case-study of luxembourgish and austrian
|
|
|
|
In: Errors by Humans and Machines in Multimedia, Multimodal, Multilingual Data Processing (ERRARE 2013) ; https://halshs.archives-ouvertes.fr/halshs-01424902 ; Errors by Humans and Machines in Multimedia, Multimodal, Multilingual Data Processing (ERRARE 2013), Nov 2013, Ermenonville, France (2013)
|
|
BASE
|
|
Show details
|
|
60 |
Embosi : automatic alignment with segments and words and phonological mining
|
|
|
|
In: International Conference on Bantu Languages (BANTU 2013) ; https://halshs.archives-ouvertes.fr/halshs-01424894 ; International Conference on Bantu Languages (BANTU 2013), Jun 2013, Paris France (2013)
|
|
BASE
|
|
Show details
|
|
|
|