SPEECH INTERACTION DEVICE, SPEECH INTERACTION SYSTEM, AND SPEECH INTERACTION METHOD

• US 20160210961A1
• Filed: 11/12/2014
• Published: 07/21/2016
• Est. Priority Date: 03/07/2014
• Status: Abandoned Application

• Current Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Inventors: NAKANISHI, Masahiro, KAMAI, Takahiro, HOSHIMI, Masakatsu
• Application Number:
  US14/914,383
• Publication Number:
  US 20160210961A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: H04M 2203/1058 Shopping and product ordering
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A speech interaction device includes: an obtainment unit that obtains utterance data indicating an utterance made by a user; a memory that holds a plurality of keywords; a word determination unit that extracts a plurality of words from the utterance data and determines, for each of the plurality of words, whether or not to match any of the plurality of keywords; a response sentence generation unit that, when the plurality of words include a first word that is determined not to match any of the plurality of keywords, generates a response sentence that includes a second word, which is among the plurality of words and determined to match any one of the plurality of keywords, and asks for re-input of a part corresponding to the first word; and a speech generation unit that generates speech data of the response sentence.

Claims

1. A speech interaction device comprising:

an obtainment unit configured to obtain utterance data indicating an utterance made by a user;

a storage unit configured to hold a plurality of keywords;

a word determination unit configured to extract a plurality of words from the utterance data and determine, for each of the plurality of words, whether or not to match any of the plurality of keywords;

a response sentence generation unit configured to, when the plurality of words include a first word, generate a response sentence that includes a second word and asks for re-input of a part corresponding to the first word, the first word being determined not to match any of the plurality of keywords, and the second word being among the plurality of words and being determined to match any one of the plurality of keywords; and

a speech generation unit configured to generate speech data of the response sentence,

wherein the storage unit is configured to hold a first keyword and a second keyword in association with each other, the first keyword and the second keyword being included in the plurality of keywords, and

the response sentence generation unit is configured to, when the word determination unit extracts, from the utterance data, a second word matching the first keyword and another second word not matching the second keyword associated with the first keyword, determine that the other second word not matching the second keyword is not usable in the utterance data, and generate the response sentence including a condition to be satisfied for the second word associated with the first keyword.

2. The speech interaction device according to claim 1,

wherein the obtainment unit is further configured to obtain answer data indicating an other utterance made by the user which is uttered after output of the speech data of the response sentence,

the speech interaction device further includes

a data processing unit configured to obtain one or more answer candidates answering the response sentence, and when the answer data does not match any of the one or more answer candidates, discard the utterance data.

3. The speech interaction device according to claim 1,

wherein the response sentence including the condition to be satisfied includes the second keyword.

4. The speech interaction device according to claim 1,

wherein the word determination unit is configured to extract the plurality of words from the utterance data after eliminating a redundant word from the utterance data.

5. A speech interaction system comprising:

the speech interaction device according to claim 1; and

an automatic order post including;

a speech input unit configured to receive the utterance data of the user and provide the utterance data to the speech interaction device; and

a speech output unit configured to output a speech according to the speech data.

6. A speech interaction method performed by a speech interaction device that includes a database holding a plurality of keywords and a control unit which performs interaction processing with a user, the speech interaction method comprising:

obtaining, by the control unit, utterance data of the user;

extracting a plurality of words from the utterance data, and determining, for each of the plurality of words, whether or not to match any of the plurality of keywords, the extracting and the determining being performed by the control unit;

when the plurality of words include a first word, generating, by the control unit, a response sentence that includes a second word among the plurality of words and asks for re-input of a part corresponding to the first word, the first word being determined not to match any of the plurality of keywords, and the second word being determined to match any one of the plurality of keywords; and

generating, by the control unit, speech data of the response sentence by speech synthesis,

wherein a first keyword and a second keyword among the plurality of keywords are in association with each other, and

when a second word matching the first keyword and another second word not matching the second keyword associated with the first keyword are extracted from the utterance data, the generating of the response sentence includes;

determining that the other second word not matching the second keyword is not usable in the utterance data and generating the response sentence including a condition to be satisfied for the second word associated with the first keyword.