Peut-on utiliser les étiqueteurs morphosyntaxiques pour améliorer la transcription automatique ?
Stéphane Huet, Guillaume Gravier, Pascale Sébillot.
The aim of the paper is to study the interest of part-of-speech (POS)
tagging to improve speech recognition. We first evaluate the part of
misrecognized words that can be corrected using POS information; an
analysis of a short extract proves that a decrease of the word error
rate by 1.1 point can be expected. We also demonstrate quantitatively
that traditional POS taggers are reliable when applied to spoken
corpus, including automatic transcriptions. This new result enables us
to effectively use POS tag knowledge to improve, in a postprocessing
stage, the quality of transcriptions, especially correcting agreement
errors; these first preliminary results however still have to be
bettered to lower the overall word error rate.