41 |
Analysis of phone confusion matrices in a manually annotated French-German learner corpus
|
|
|
|
In: Proceedings SLaTE 2015, Workshop on Speech and Language Technology in Education ; Workshop on Speech and Language Technology in Education ; https://hal.inria.fr/hal-01184186 ; Workshop on Speech and Language Technology in Education, Sep 2015, Leipzig, Germany (2015)
|
|
BASE
|
|
Show details
|
|
42 |
Terminal portable de communication et affichage de la reconnaissance vocale. Enjeux et rapports à l'écrit. Étude préliminaire auprès d'adultes déficients auditifs
|
|
|
|
In: Ideki 2015 - 3ème colloque international "Didactiques, Métiers de l’Humain, Intelligence collective : construction de savoirs et de dispositifs didactiques" ; https://hal.inria.fr/hal-01239910 ; Ideki 2015 - 3ème colloque international "Didactiques, Métiers de l’Humain, Intelligence collective : construction de savoirs et de dispositifs didactiques", Dec 2015, Colmar, France. pp.1-15 (2015)
|
|
BASE
|
|
Show details
|
|
43 |
Acoustical Frame Rate and Pronunciation Variant Statistics
|
|
|
|
In: Proceedings SLSP'2015, 3rd International Conference on Statistical Language and Speech Processing ; International Conference on Statistical Language and Speech Processing ; https://hal.inria.fr/hal-01184195 ; International Conference on Statistical Language and Speech Processing, Nov 2015, Budapest, Hungary (2015)
|
|
BASE
|
|
Show details
|
|
44 |
Impact of frame rate on automatic speech-text alignment for corpus-based phonetic studies
|
|
|
|
In: Proceedings ICPhS 2015 ; ICPhS'2015 - 18th International Congress of Phonetic Sciences ; https://hal.inria.fr/hal-01183637 ; ICPhS'2015 - 18th International Congress of Phonetic Sciences, Aug 2015, Glasgow, United Kingdom (2015)
|
|
BASE
|
|
Show details
|
|
45 |
Detection of sentence modality on French automatic speech-to-text transcriptions
|
|
|
|
In: Proceedings ICNLSP'2015, International Conference on Natural Language and Speech Processing ; International Conference on Natural Language and Speech Processing ; https://hal.inria.fr/hal-01184193 ; International Conference on Natural Language and Speech Processing, Oct 2015, Alger, Algeria (2015)
|
|
BASE
|
|
Show details
|
|
46 |
Reconnaissance de la parole pour l’aide à la communication pour les sourds et malentendants ; Speech recognition as a communication aid for deaf and hearing impaired people
|
|
|
|
BASE
|
|
Show details
|
|
47 |
About Combining Forward and Backward-Based Decoders for Selecting Data for Unsupervised Training of Acoustic Models
|
|
|
|
In: INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-01090483 ; INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, Sep 2014, Singapour, Singapore (2014)
|
|
BASE
|
|
Show details
|
|
48 |
Combining words and syllables for speech transcription ; Combinaison de mots et de syllabes pour transcrire la parole
|
|
|
|
In: XXXème édition des Journées d'Etudes sur la Parole ; https://hal.inria.fr/hal-01080351 ; XXXème édition des Journées d'Etudes sur la Parole, Jun 2014, Le Mans, France (2014)
|
|
BASE
|
|
Show details
|
|
49 |
Hybrid language models for speech transcription
|
|
|
|
In: INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-01090478 ; INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, Sep 2014, Singapour, Singapore (2014)
|
|
BASE
|
|
Show details
|
|
50 |
Links between Manual Punctuation Marks and Automatically Detected Prosodic Structures
|
|
|
|
In: Speech Prosody 2014 ; https://hal.archives-ouvertes.fr/hal-00998031 ; Speech Prosody 2014, May 2014, Dublin, Ireland (2014)
|
|
BASE
|
|
Show details
|
|
51 |
Designing a Bilingual Speech Corpus for French and German Language Learners: a Two-Step Process
|
|
|
|
In: LREC - 9th Language Resources and Evaluation Conference ; https://hal.inria.fr/hal-00979026 ; LREC - 9th Language Resources and Evaluation Conference, The European Language Resources Association, May 2014, Reykjavik, Iceland (2014)
|
|
BASE
|
|
Show details
|
|
52 |
Constitution d'un Corpus de Français Langue Etrangère destiné aux Apprenants Allemands
|
|
|
|
In: ISSN: 2261-2424 ; SHS Web of Conferences ; https://hal.inria.fr/hal-01080630 ; SHS Web of Conferences, EDP Sciences, 2014, 4e Congrès Mondial de Linguistique Française, 8, pp.14. ⟨10.1051/shsconf/20140801186⟩ ; www.webofconferences.org (2014)
|
|
BASE
|
|
Show details
|
|
53 |
Explicit trajectories and speaker class modeling for child and adult speech recognition ; Modélisation de trajectoires et de classes de locuteurs pour la reconnaissance de voix d'enfants et d'adultes
|
|
|
|
In: XXXème édition des Journées d'Etudes sur la Parole ; https://hal.inria.fr/hal-01080343 ; XXXème édition des Journées d'Etudes sur la Parole, Jun 2014, Le Mans, France (2014)
|
|
Abstract:
International audience ; When the speech data is produced by speakers of different age and gender, the acoustic variability of any given phonetic unit becomes large, which degrades speech recognition performance. One way to go beyond conventional Hidden Markov Model is to explicitly include speaker class information in the modeling. Speaker classes can be obtained automatically, and they are used for building speaker class-specific acoustic models. This paper introduces a structuring of the Gaussian components of the GMM densities with respect to the speaker classes. In a first approach, this structuring of the Gaussian components is completed with speaker class-dependent mixture weights, and in a second approach, with transition matrices, which add dependencies between Gaussian components of mixture densities (as in stranded GMMs). The two approaches bring substantial performance improvements when recognizing adult and child speech. Using class-structured components plus mixture transition matrices reduces by more than one third the word error rate on the TIDIGIT corpus. ; RÉSUMÉ Lorsque l'on considère de la parole produite par des enfants et des adultes, la variabilité acous-tique de chaque unité phonétique devient grande, ce qui dégrade les performances de recon-naissance. Un moyen d'aller au-delà des modèles de Markov traditionnels, est de prendre en considération des classes de locuteurs. Les classes de locuteurs peuvent être obtenues automa-tiquement. Elles servent à fabriquer des modèles acoustiques spécifiques de chaque classe. Ce papier propose une structuration des composantes des densités multigaussiennes (GMMs) en re-lation avec des classes de locuteurs. Dans une première approche, cette structuration des densités est complétée par des pondérations des composantes gaussiennes dépendantes des classes de locuteurs, et dans une deuxième approche, par des matrices de transition entre les composantes gaussiennes des densités (comme dans les stranded GMMs). Ces deux approches apportent des gains substantiels pour la reconnaissance de voix d'enfants et d'adultes. La structuration des composantes gaussiennes complétée par des matrices de transition entre composantes réduit de plus d'un tiers le taux d'erreur mot sur le corpus TIDIGIT.
|
|
Keyword:
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing; classification non supervisée; modèles de classes de locuteurs; modèles stochastiques de trajectoire; Reconnaissance de la parole; speaker class modeling; Speech recognition; stochastic trajectory modeling; unsupervised clustering
|
|
URL: https://hal.inria.fr/hal-01080343/document https://hal.inria.fr/hal-01080343 https://hal.inria.fr/hal-01080343/file/jep2014-agorin-V5-FR-V.01.pdf
|
|
BASE
|
|
Hide details
|
|
54 |
Component Structuring and Trajectory Modeling for Speech Recognition
|
|
|
|
In: Interspeech ; https://hal.inria.fr/hal-01063653 ; Interspeech, Sep 2014, Singapoore, Singapore (2014)
|
|
BASE
|
|
Show details
|
|
55 |
A Machine Learning Based Approach for Vocabulary Selection for Speech Transcription
|
|
|
|
In: TSD - 16th International Conference on Text, Speech and Dialogue - 2013 ; https://hal.inria.fr/hal-00834302 ; TSD - 16th International Conference on Text, Speech and Dialogue - 2013, Sep 2013, Pilsen, Czech Republic. pp.60-67 ; http://link.springer.com/chapter/10.1007%2F978-3-642-40585-3_9 (2013)
|
|
BASE
|
|
Show details
|
|
56 |
Analysis and Combination of Forward and Backward based Decoders for Improved Speech Transcription
|
|
|
|
In: TSD - 16th International Conference on Text, Speech and Dialogue - 2013 ; https://hal.inria.fr/hal-00834296 ; TSD - 16th International Conference on Text, Speech and Dialogue - 2013, Sep 2013, Pilsen, Czech Republic. pp.84-91 ; http://link.springer.com/chapter/10.1007%2F978-3-642-40585-3_12 (2013)
|
|
BASE
|
|
Show details
|
|
57 |
Comparison and Analysis of Several Phonetic Decoding Approaches
|
|
|
|
In: TSD - 16th International Conference on Text, Speech and Dialogue - 2013 ; https://hal.inria.fr/hal-00834313 ; TSD - 16th International Conference on Text, Speech and Dialogue - 2013, Sep 2013, Pilsen, Czech Republic. pp.161-168 ; http://link.springer.com/chapter/10.1007%2F978-3-642-40585-3_21 (2013)
|
|
BASE
|
|
Show details
|
|
58 |
Comparison of approaches for an efficient phonetic decoding
|
|
|
|
In: InterSpeech - 14th Annual Conference of the International Speech Communication Association - 2013 ; https://hal.inria.fr/hal-00834284 ; InterSpeech - 14th Annual Conference of the International Speech Communication Association - 2013, Aug 2013, Lyon, France (2013)
|
|
BASE
|
|
Show details
|
|
59 |
Efficient constrained parametrization of GMM with class-based mixture weights for Automatic Speech Recognition
|
|
|
|
In: LTC'13 - 6th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics ; https://hal.inria.fr/hal-00923202 ; LTC'13 - 6th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, Dec 2013, Poznań, Poland (2013)
|
|
BASE
|
|
Show details
|
|
60 |
Automatic Detection of the Prosodic Structures of Speech Utterances
|
|
|
|
In: SPECOM - 15th International Conference on Speech and Computer - 2013 ; https://hal.inria.fr/hal-00834318 ; SPECOM - 15th International Conference on Speech and Computer - 2013, Sep 2013, Pilsen, Czech Republic. pp.1-8 ; http://link.springer.com/chapter/10.1007%2F978-3-319-01931-4_1 (2013)
|
|
BASE
|
|
Show details
|
|
|
|