logo Idiap Research Institute        
 [BibTeX] [Marc21]
Automatic Out-of-Language Detection based on Confidence Measures derived from LVCSR Word and Phone Lattices
Type of publication: Idiap-RR
Citation: Motlicek_Idiap-RR-06-2009
Number: Idiap-RR-06-2009
Year: 2009
Month: 5
Institution: Idiap
Address: Rue Marconi 19, martigny, Switzerland
Abstract: Confidence Measures (CMs) estimated from Large Vocabulary Continuous Speech Recognition (LVCSR) outputs are commonly used metrics to detect incorrectly recognized words. In this paper, we propose to exploit CMs derived from frame-based word and phone posteriors to detect speech segments containing pronunciations from non-target (alien) languages. The LVCSR system used is built for English, which is the target language, with medium-size recognition vocabulary (5k words). The efficiency of detection is tested on a set comprising speech from three different languages (English, German, Czech). Results achieved indicate that employment of specific temporal context (integrated in the word or phone level) significantly increases the detection accuracies. Furthermore, we show that combination of several CMs can also improve the efficiency of detection.
Projects Idiap
Authors Motlicek, Petr
Added by: [ADM]
Total mark: 0
  • Motlicek_Idiap-RR-06-2009.pdf (MD5: 09f10fef2365c0048f820c719fcfe273)