logo Idiap Research Institute        
 [BibTeX] [Marc21]
Impact du degre de supervision sur l'adaptation a un domaine d'un modele de langage a partir du Web
Type of publication: Idiap-RR
Citation: Lecorve_Idiap-RR-23-2012
Number: Idiap-RR-23-2012
Year: 2012
Month: 7
Institution: Idiap
Note: in French
Abstract: Domain adaptation of a language model aims at re-estimating word sequence probabilities in order to better match the peculiarities of a given broad topic of interest. To achieve this task, a common strategy consists in retrieving adaptation texts from the Internet based on a given domain-representative seed text. In this paper, we study the influence of the choice of this seed text on the adaptation process and on the performances of adapted language models in automatic speech recognition. More precisely, the goal of this original study is to analyze the differences between supervised adaptation, in which the seed text is manually generated, and unsupervised adaptation, where the seed text is an automatic transcript. Experiments carried out on videos from a real-world use case mainly show that differences vary according to adaptation scenarios and that the unsupervised approach is globally convincing, especially according to its low cost.
Keywords: ASR, Automatic Speech Recognition, domain adaptation, Language Models, supervision, Web data
Projects Idiap
Authors Lecorvé, Gwénolé
Dines, John
Hain, Thomas
Motlicek, Petr
Crossref by Lecorve_JEP_2012
Added by: [ADM]
Total mark: 0
  • Lecorve_Idiap-RR-23-2012.pdf (MD5: 3d322f7640e45914edf46d13b16c3010)