Method and apparatus for conducting an interactive dialogue
AssigneeSRI International
InventorsKristin Precoda, Horacio Franco
Life of this patent
Estimating the term…
Abstract
The present invention relates to a method and apparatus for enhancing interactive translation and dialogue systems. In one embodiment, a method for conducting an interactive dialogue includes receiving an input signal in a first language, where the input signal includes one or more words, processing the words in accordance with a vocabulary, and adjusting a probability relating to at least one of the words in the vocabulary for an output signal. Subsequently, the method may output a translation of the input signal in a second language, in accordance with the vocabulary. In one embodiment, adjusting the probability involves adjusting a probability that the word will be used in actual conversation.
Claims17
A method for conducting an interactive dialogue, the method comprising:
- receiving a first audio input signal from a user, the first audio input signal comprising a first set of one or more words;
- processing the first audio input signal so as to recognize the first set of one or more words in accordance with a vocabulary comprising a collection of words and an associated set of probabilities corresponding to the collection of words;
- generating a first output signal responsive to the first audio input signal in accordance with the processing, the first output signal comprising a second set of one or more words, wherein the second set of one or more words includes at least one word that is not included in the first set of one or more words;
- adjusting at least one probability in the associated set of probabilities, the at least one probability corresponding to at least one word that is included in the second set of one or more words but is not included in the first set of one or more words, thereby producing an adjusted set of probabilities based on the first output signal;
- and
- processing a second audio input signal, received after the first output signal is outputted and comprising a third set of one or more words, so as to recognize the third set of one or more words in accordance with the vocabulary and the adjusted set of probabilities,
- wherein at least one of:
- the processing of the first audio input signal, the generating, the adjusting, or the processing of the second audio input signal is performed using a processor.
A non-transitory computer readable medium containing an executable program for conducting an interactive dialogue, where the program performs steps of:
- receiving a first audio input signal from a user, the first audio input signal comprising a first set of one or more words;
- processing the first audio input signal so as to recognize the first set of one or more words in accordance with a vocabulary comprising a collection of words and an associated set of probabilities corresponding to the collection of words;
- generating a first output signal responsive to the first audio input signal in accordance with the processing, the first output signal comprising a second set of one or more words, wherein the second set of one or more words includes at least one word that is not included in the first set of one or more words;
- adjusting at least one probability in the associated set of probabilities, the at least one probability corresponding to at least one word that is included in the second set of one or more words but is not included in the first set of one or more words, thereby producing an adjusted set of probabilities based on the first output signal;
- and
- processing a second audio input signal, received after the first output signal is outputted and comprising a third set of one or more words, so as to recognize the third set of one or more words in accordance with the vocabulary and the adjusted set of probabilities.
An interactive dialogue system, the system comprising:
- an input device for receiving a first audio input signal from a user, the first audio input signal comprising a first set of one or more words;
- a recognition processor for processing the first audio input signal so as to recognize the first set of one or more words in accordance with a vocabulary comprising a collection of words and an associated set of probabilities corresponding to the collection of words;
- an output device for producing a first output signal responsive to the first audio input signal in accordance with the processing, the first output signal comprising a second set of one or more words, wherein the second set of one or more words includes at least one word that is not included in the first set of one or more words;
- and
- a probability adjuster for adjusting at least one probability in the associated set of probabilities, the at least one probability corresponding to at least one word that is included in the second set of one or more words but is not included in the first set of one or more words, thereby producing an adjusted set of probabilities based on the first output signal,
- where the recognition processor is additionally for processing a second audio input signal, received after the first output signal is outputted and comprising a third set of one or more words, so as to recognize the third set of one or more words in accordance with the vocabulary and the adjusted set of probabilities.
Dependencies are inferred from the claim text.