Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition

Ghazi Bouselmi 1 Dominique Fohr 1 Irina Illina 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : In this paper, we present several adaptation methods for non-native speech recognition. We have tested pronunciation modelling, MLLR and MAP non-native pronunciation adaptation and HMM models retraining on the HIWIRE foreign accented English speech database. The ``phonetic confusion'' scheme we have developed consists in associating to each spoken phone several sequences of confused phones. In our experiments, we have used different combinations of acoustic models representing the canonical and the foreign pronunciations: spoken and native models, models adapted to the non-native accent with MAP and MLLR. The joint use of pronunciation modelling and acoustic adaptation led to further improvements in recognition accuracy. The best combination of the above mentioned techniques resulted in a relative word error reduction ranging from 46% to 71%.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/inria-00184560
Contributor : Bouselmi Ghazi <>
Submitted on : Monday, November 5, 2007 - 4:31:12 PM
Last modification on : Thursday, January 11, 2018 - 6:19:56 AM
Long-term archiving on: Monday, April 12, 2010 - 1:05:25 AM

Files

is2007_latex_template.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00184560, version 1
  • ARXIV : 0711.0811

Collections

Citation

Ghazi Bouselmi, Dominique Fohr, Irina Illina. Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition. InterSpeech 2007, Aug 2007, Antwerp, Belgium. ⟨inria-00184560⟩

Share

Metrics

Record views

277

Files downloads

250