%Aigaion2 BibTeX export from Idiap Publications
%Thursday 18 April 2024 09:41:53 AM

         author = {Imseng, David and Motlicek, Petr and Bourlard, Herv{\'{e}} and Garner, Philip N.},
       projects = {Idiap, SNSF-MULTI, IM2},
          title = {Using out-of-language data to improve an under-resourced speech recognizer},
        journal = {Speech Communication},
           year = {2013},
           issn = {0167-6393},
            url = {http://www.sciencedirect.com/science/article/pii/S0167639313000101},
            doi = {10.1016/j.specom.2013.01.007},
       abstract = {Under-resourced speech recognizers may benefit from data in languages other than the target language. In this paper, we report how to boost the performance of an Afrikaans automatic speech recognition system by using already available Dutch data. We successfully exploit available multilingual resources through 1) posterior features, estimated by multilayer perceptrons (MLP) and 2) subspace Gaussian mixture models (SGMMs). Both the MLPs and the SGMMs can be trained on out-of-language data. We use three different acoustic modeling techniques, namely Tandem, Kullback-Leibler divergence based HMMs (KL-HMM) as well as SGMMs and show that the proposed multilingual systems yield 12\% relative improvement compared to a conventional monolingual HMM/GMM system only trained on Afrikaans. We also show that KL-HMMs are extremely powerful for under-resourced languages: using only six minutes of Afrikaans data (in combination with out-of-language data), KL-HMM yields about 30\% relative improvement compared to conventional maximum likelihood linear regression and maximum a posteriori based acoustic model adaptation.},
            pdf = {https://publications.idiap.ch/attachments/papers/2013/Imseng_SPECOM_2013.pdf}