METHOD AND SYSTEM FOR AUTOMATICALLY PROVIDING LINGUISTIC FORMULATIONS THAT ARE OUTSIDE A RECOGNITION DOMAIN OF AN AUTOMATIC SPEECH RECOGNITION SYSTEM

摘要

Disclosed herein is a method for automatically providing a hypothesis of alinguistic formulation that is uttered by users of a voice service based on anautomatic speech recognition system and that is outside a recognition domainof the automatic speech recognition system. The method includes providing aconstrained (300) and an unconstrained speech recognition (310) from an inputspeech signal, identifying a part of the constrained speech recognitionoutside the recognition domain, identifying a part of the unconstrained speechrecognition (330) corresponding to the identified part of the constrainedspeech recognition, and providing the linguistic formulation hypothesis basedon the identified part of the unconstrained speech recognition.