Detection of OOV words by combining acoustic confidence measures with linguistic features

Frederik Stouten (1) , Dominique Fohr (1) , Irina Illina (1)

1 PAROLE - Analysis, perception and recognition of speech

This paper describes the design of an Out-Of- Vocabulary words (OOV) detector. Such a system is assumed to detect segments that correspond to OOV words (words that are not included in the lexicon) in the output of a LVCSR system. The OOV detector uses acoustic confidence measures that are derived from several systems: a word recognizer constrained by a lexicon, a phone recognizer constrained by a grammar and a phone recognizer without constraints. On top of that it also uses some linguistic features. The experimental results on a French broadcast news transcription task showed that for our approach precision equals recall at 35%

Mots clés: LVCSR; OOV; confidence measures

Domaines: Interface homme-machine [cs.HC]

Frederik Stouten, Dominique Fohr, Irina Illina. Detection of OOV words by combining acoustic confidence measures with linguistic features. The eleventh biannual IEEE workshop on Automatic Speech Recognition and Understanding (ASRU), Dec 2009, Merano, Italy. pp.1-4. ⟨hal-00435087⟩