81 |
The reception of Eugen Wüster’s work and the development of terminology
|
|
|
|
BASE
|
|
Show details
|
|
82 |
Normalisation and the translation of phraseology in the COVALT Corpus
|
|
Marco, Josep. - : Les Presses de l'Université de Montréal, 2012
|
|
BASE
|
|
Show details
|
|
83 |
Toponymes maghrébins. De l'enracinement à l'internationalisation.
|
|
|
|
In: ISSN: 1273-6449 ; Cahiers de sociolinguistique ; https://hal.univ-rennes2.fr/hal-01586160 ; Cahiers de sociolinguistique, PUR - Presse Universitaire de Rennes, 2011, Noms propres, dynamiques identitaires et sociolinguistiques, pp.117-143 ; https://www.cairn.info/revue-cahiers-de-sociolinguistique-2006-1-page-117.htm (2011)
|
|
BASE
|
|
Show details
|
|
84 |
Description formelle et diagnostic automatique des erreurs en langue étrangère : quelques perspectives pour les outils d'ELAO
|
|
|
|
In: Sciences du langage et nouvelles technologies (ASL'09) ; https://hal-inalco.archives-ouvertes.fr/hal-01375634 ; Thierry Ponchon; Isabelle Labord-Milla. Sciences du langage et nouvelles technologies (ASL'09), Lambert-Lucas, pp.107-115, 2011, Sciences du langage et nouvelles technologies (ASL'09) (2011)
|
|
BASE
|
|
Show details
|
|
85 |
Size-based termination: Semantics and generalizations ; Terminaison à base de tailles: Sémantique et généralisations
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-01746182 ; Other [cs.OH]. Université Henri Poincaré - Nancy 1, 2011. English. ⟨NNT : 2011NAN10034⟩ (2011)
|
|
BASE
|
|
Show details
|
|
86 |
Practice, Description and Theory Come Together – Normalization or Interference in Italian Technical Translation?
|
|
|
|
BASE
|
|
Show details
|
|
87 |
Description formelle et diagnostic automatique des erreurs en langue étrangère : quelques perspectives pour les outils d'ELAO
|
|
|
|
In: Sciences du langage et nouvelles technologies (ASL'09) ; https://hal-inalco.archives-ouvertes.fr/hal-01375634 ; Thierry Ponchon; Isabelle Labord-Milla. Sciences du langage et nouvelles technologies (ASL'09), Lambert-Lucas, pp.107-115, 2011, Sciences du langage et nouvelles technologies (ASL'09) (2011)
|
|
BASE
|
|
Show details
|
|
88 |
Developing a System Resilience Approach to the Improvement of Patient Safety in NHS Hospitals
|
|
|
|
BASE
|
|
Show details
|
|
89 |
L'approche de la diversité linguistique en sociolinguistique (Dynamiques de la langue française ; 1/5)
|
|
|
|
In: http://www.uoh.fr/ (2011)
|
|
BASE
|
|
Show details
|
|
90 |
Dynamiques de la langue française au 21ième siècle : une introduction à la sociolinguistique
|
|
|
|
In: http://www.uoh.fr/ (2011)
|
|
BASE
|
|
Show details
|
|
91 |
Variations et normes d'une langue (Dynamiques de la langue française ; 3/5)
|
|
|
|
In: http://www.uoh.fr/ (2011)
|
|
BASE
|
|
Show details
|
|
92 |
Terminaison à base de tailles : sémantique et généralisations ; Size-based termination: Semantics and generalizations
|
|
|
|
BASE
|
|
Show details
|
|
93 |
OntoGene (Team 65): preliminary analysis of participation in BioCreative III
|
|
|
|
In: Rinaldi, Fabio; Schneider, Gerold; Clematide, Simon; Jegen, Silvan; et al (2010). OntoGene (Team 65): preliminary analysis of participation in BioCreative III. In: BioCreative III workshop, Bethesda, Maryland, 13 September 2010 - 15 September 2010. (2010)
|
|
BASE
|
|
Show details
|
|
94 |
Normalisation and the Translation of Phraseology in the COVALT Corpus
|
|
Marco, Josep. - : Les Presses de l'Université de Montréal, 2009. : Érudit, 2009
|
|
BASE
|
|
Show details
|
|
95 |
Speaker normalisation for large vocabulary multiparty conversational speech recognition
|
|
|
|
Abstract:
One of the main problems faced by automatic speech recognition is the variability of the testing conditions. This is due both to the acoustic conditions (different transmission channels, recording devices, noises etc.) and to the variability of speech across different speakers (i.e. due to different accents, coarticulation of phonemes and different vocal tract characteristics). Vocal tract length normalisation (VTLN) aims at normalising the acoustic signal, making it independent from the vocal tract length. This is done by a speaker specific warping of the frequency axis parameterised through a warping factor. In this thesis the application of VTLN to multiparty conversational speech was investigated focusing on the meeting domain. This is a challenging task showing a great variability of the speech acoustics both across different speakers and across time for a given speaker. VTL, the distance between the lips and the glottis, varies over time. We observed that the warping factors estimated using Maximum Likelihood seem to be context dependent: appearing to be influenced by the current conversational partner and being correlated with the behaviour of formant positions and the pitch. This is because VTL also influences the frequency of vibration of the vocal cords and thus the pitch. In this thesis we also investigated pitch-adaptive acoustic features with the goal of further improving the speaker normalisation provided by VTLN. We explored the use of acoustic features obtained using a pitch-adaptive analysis in combination with conventional features such as Mel frequency cepstral coefficients. These spectral representations were combined both at the acoustic feature level using heteroscedastic linear discriminant analysis (HLDA), and at the system level using ROVER. We evaluated this approach on a challenging large vocabulary speech recognition task: multiparty meeting transcription. We found that VTLN benefits the most from pitch-adaptive features. Our experiments also suggested that combining conventional and pitch-adaptive acoustic features using HLDA results in a consistent, significant decrease in the word error rate across all the tasks. Combining at the system level using ROVER resulted in a further significant improvement. Further experiments compared the use of pitch adaptive spectral representation with the adoption of a smoothed spectrogram for the extraction of cepstral coefficients. It was found that pitch adaptive spectral analysis, providing a representation which is less affected by pitch artefacts (especially for high pitched speakers), delivers features with an improved speaker independence. Furthermore this has also shown to be advantageous when HLDA is applied. The combination of a pitch adaptive spectral representation and VTLN based speaker normalisation in the context of LVCSR for multiparty conversational speech led to more speaker independent acoustic models improving the overall recognition performances.
|
|
Keyword:
automatic speech recognition; meetings; Vocal tract length normalisation; warping factors
|
|
URL: http://hdl.handle.net/1842/3983
|
|
BASE
|
|
Hide details
|
|
96 |
Automatic emotion recognition: an investigation of acoustic and prosodic parameters
|
|
|
|
BASE
|
|
Show details
|
|
97 |
Autour du gallo. État des lieux, analyses et perspectives.
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-00430440 ; Presses Universitaires de Rennes, pp.236, 2008 (2008)
|
|
BASE
|
|
Show details
|
|
98 |
Normalisation et alignement de corpus français et vietnamiens : Format et Logiciels
|
|
|
|
In: Actes JATD 2008 ; journées internationales d'analyse statistique des données textuelles ; https://hal.archives-ouvertes.fr/hal-01705630 ; journées internationales d'analyse statistique des données textuelles, Jun 2008, Lyon, France (2008)
|
|
BASE
|
|
Show details
|
|
99 |
L'Académie de la langue hébraïque et la morphologie de l'hébreu contemporain
|
|
|
|
In: Regards croisés sur les mots non simples ; https://halshs.archives-ouvertes.fr/halshs-00370876 ; Barbara Kaltz. Regards croisés sur les mots non simples, ENS Editions, pp.95-109, 2008, Langages (2008)
|
|
BASE
|
|
Show details
|
|
100 |
A test of the effectiveness of speaker verification for differentiating between identical twins.
|
|
|
|
BASE
|
|
Show details
|
|
|
|