logo Idiap Research Institute        
 [BibTeX] [Marc21]
Language dependent universal phoneme posterior estimation for mixed language speech recognition
Type of publication: Idiap-RR
Citation: Imseng_Idiap-RR-13-2011
Number: Idiap-RR-13-2011
Year: 2011
Month: 5
Institution: Idiap
Abstract: This paper presents a new approach to estimate "universal" phoneme posterior probabilities for mixed language speech recognition. More specifically, we propose a new theoretical framework to combine phoneme class posterior probabilities in a principled way by using (statistical) evidence about the language identity. We investigate the proposed approach in a mixed language environment (SpeechDat(II)) consisting of five European languages. Our studies show that the proposed approach can yield significant improvements on a mixed language task, while maintaining the performance on monolingual tasks. Additionally, through a case study, we also demonstrate the potential benefits of the proposed approach for non-native speech recognition.
Projects Idiap
Authors Imseng, David
Bourlard, Hervé
Magimai.-Doss, Mathew
Dines, John
Crossref by Imseng_ICASSP_2011
Added by: [ADM]
Total mark: 0
  • Imseng_Idiap-RR-13-2011.pdf (MD5: 881b94238cc550130a102c72d0d50c07)