4th International Conference on Spoken Language Processing
Philadelphia, PA, USA
This paper presents a novel approach to using confidence scores for word graph rescoring. For each word in the system's vocabulary, we computed the probability that the observation is correct given its acoustic score. Afterwards, we used these probabilities for rescoring word graphs outputted by the recognizer. We will present some implementation details as well as accuracy improvements obtained using this method.
Bibliographic reference. Fetter, Pablo / Dandurand, Frédéric / Regel-Brietzmann, Peter (1996): "Word graph rescoring using confidence measures", In ICSLP-1996, 10-13.