摘要:Responsive adaptation in spoken dialogue systems involves a change in dialogue system behavior
in response to a user or a dialogue situation. In this paper we address responsive adaptation in
the automatic speech recognition module of a spoken dialogue system. We hypothesize that information
about the content of a user utterance may help improve speech recognition. We use a
two-step process to test this hypothesis: first, we automatically predict the task-relevant concept
types likely to be present in a user utterance using features from the dialogue context and from
the output of first-pass recognition of the utterance; and then, we adapt the speech recognizer’s
language model to the predicted content of the user’s utterance and run a second pass of speech
recognition. We show that: (1) it is possible to achieve high accuracy in determining presence or
absence of particular concept types in a post-confirmation utterance; and (2) 2-pass speech recognition
with concept type classification and language model adaptation can lead to improved speech
recognition performance for post-confirmation utterances.