公开(公告)号：WO2016042815A1

公开(公告)日：2016-03-24

申请号：PCT/JP2015/059010

申请日：2015-03-18

Applicant: KABUSHIKI KAISHA TOSHIBA

Inventor： YAMAMOTO, Ayana ,  FUJII, Hiroko

IPC: G10L15/22 ,  G06F17/28 ,  G10L15/10

CPC classification number: G10L15/22 ,  G10L15/1807 ,  G10L15/1815 ,  G10L15/1822 ,  G10L15/26 ,  G10L25/87 ,  G10L2015/223

Abstract: According to one embodiment, a speech interaction apparatus for performing an interaction with a user based on a scenario includes a speech recognition unit, a determination unit, a selection unit and an execution unit. The speech recognition unit recognizes a speech of the user and generates a recognition result text. The determination unit determines whether or not the speech includes an interrogative intention based on the recognition result text. The selection unit selects, when the speech includes the interrogative intention, a term of inquiry from a response sentence in the interaction in accordance with timing of the speech, the term of inquiry being a subject of the interrogative intention. The execution unit executes an explanation scenario including an explanation of the term of inquiry.

Abstract translation: 根据一个实施例，用于基于场景执行与用户的交互的语音交互装置包括语音识别单元，确定单元，选择单元和执行单元。 语音识别单元识别用户的语音并生成识别结果文本。 确定单元基于识别结果文本来确定语音是否包括询问意图。 选择单元在语音包括询问意图时，根据语音的时间选择来自交互中的响应句子的查询项，查询词是询问意图的对象。 执行单元执行包括对查询期限的说明的说明场景。