Determining a system utterance with connective and content portions from a user utterance
Described is a voice dialogue system that includes a voice input unit which acquires a user utterance, an intention understanding unit which interprets an intention of utterance of a voice acquired by the voice input unit, a dialogue text creator which creates a text of a system utterance, and a voice output unit which outputs the system utterance as voice data. When creating a text of a system utterance, the dialogue text creator creates the text by inserting a tag in a position in the system utterance, and the intention understanding unit interprets an utterance intention of a user in accordance with whether a timing at which the user utterance is made is before or after an output of a system utterance at a position corresponding to the tag from the voice output unit.
1. A voice dialogue system, comprising:
a voice input unit configured to acquire user utterances of a user;
a dialogue text creator configured to create system utterances, wherein the dialogue text creator creates the system utterances based upon a stored history of dialogue performed in a past between the system and the user stored in a dialogue manager, the dialogue manager storing a time and date or location of the dialogue and enabling what kind of conversation had taken place with the user to be discerned and a response using previous dialogue as a reference to be generated;
a voice output unit configured to output the system utterances as voice data; and
a determiner configured to, in a case that a current user utterance is acquired while a system utterance is being output as voice data, determine whether or not the current user utterance acquired by the voice input unit is a response to a content that is output at a time of the current user utterance, wherein
the system utterance comprises a connective portion for connecting following sentences and a content portion that is a subject of the system utterance,
the content portion includes (a) a first content portion that is a first system utterance that is output before the connective portion and (b) a second content portion that is a second system utterance that is output after the connective portion,
the first content portion is a first question and the second content portion is a second question different from the first question,
the determiner determines, in a case that the current user utterance is acquired before the output of the second content portion has started, the current user utterance is a response to the first content portion, and
the determiner determines, in a case that the current user utterance is acquired after the output of the second content portion has started, the current user utterance is a response to the second content portion.
2. The voice dialogue system according to claim 1 , wherein the connective portion comprises one of an interjection, a gambit, or a repetition of a part of a previously acquired user utterance.
3. The voice dialogue system according to claim 2 , wherein
the dialogue creator is further configured to, when creating the system utterances, to insert an unvoiced tag between the connective portion and the content portion of the system utterances, and
the determiner is further configured to determine that the output of the content portion of the system utterance has started based at least on a position of the unvoiced tag in the system utterance.
4. The voice dialogue system according to claim 2 , wherein the determiner is further configured to:
calculate a first period of time that is a period of time that it will take to output the connective portion of the system utterance as voice data;
acquire a second period of time that is a period of time from a start of output of the system utterance as voice data to a start of the acquired current user utterance; and
compare the first period of time and the second period of time with each other to determine whether the current user utterance is acquired after the output of the content portion of the system utterance has started or before the output of the content portion of the system utterance has started.
5. The voice dialogue system according to claim 1 , wherein the determiner is further programmed to function as an intention understanding unit storing a corpus or a dictionary for interpreting utterance contents and interpreting a user utterance by referring to the corpus or the dictionary.
6. The voice dialogue system according to claim 1 , wherein the voice dialogue system includes a voice dialogue robot having movable joints, the voice dialogue robot configured to function as the voice input unit, the dialogue text creator, the voice output unit and the determiner.