%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:00:10 PM

@TECHREPORT{Lecorve_Idiap-RR-23-2012,
         author = {Lecorv{\'{e}}, Gw{\'{e}}nol{\'{e}} and Dines, John and Hain, Thomas and Motlicek, Petr},
       keywords = {ASR, Automatic Speech Recognition, domain adaptation, Language Models, supervision, Web data},
       projects = {Idiap},
          month = {7},
          title = {Impact du degr{\'{e}} de supervision sur l'adaptation {\`{a}} un domaine d'un mod{\`{e}}le de langage {\`{a}} partir du Web},
           type = {Idiap-RR},
         number = {Idiap-RR-23-2012},
           year = {2012},
    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.},
            pdf = {https://publications.idiap.ch/attachments/reports/2012/Lecorve_Idiap-RR-23-2012.pdf}
}