Voice interaction method, and device

• US 9,564,129 B2
• Filed: 06/10/2014
• Issued: 02/07/2017
• Est. Priority Date: 06/19/2013
• Status: Expired

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Inventors: Amano, Hiroshi, Kozuka, Masayuki, Ohmori, Motoji, Hirose, Takako, Nakano, Toshihisa, Yamaguchi, Takahiro
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US14/777,920
• Publication Number:
  US 20160322048A1
• Time in Patent Office: 973 Days
• Field of Search: 704/231, 704/235, 704/246, 704/270, 704/270.1, 704/271, 704/275, 704/276, 704/277
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/222 Barge in, i.e. overridable guidance for interrupting prompts
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A voice dialogue method performed by a voice dialog system includes: a voice signal generation unit; a voice dialog agent unit; a voice output unit; and a voice input control unit, the method including: a step of, by the voice signal generation unit, receiving a voice input and generating a voice signal based on the received voice input; a step of, by the voice dialog agent unit, performing voice recognition processing on the voice signal and performing processing based on a result of the voice recognition processing to generate a response signal; a step of, by the voice output unit, outputting a voice based on the response signal; and a step of, when the voice output unit outputs the voice, by the voice input control unit, keeping the voice signal generation unit, for predetermined period after output of the voice, a receivable state in which a voice input is receivable.

Claims

1. A voice dialogue method that is performed by a voice dialogue system, the voice dialogue system including:

a voice signal generation unit;

a voice dialogue agent unit;

an additional voice dialogue agent unit;

a voice output unit; and

a voice input control unit, the voice dialogue method comprising;

a step of, by the voice signal generation unit, receiving a voice input and generating a voice signal based on the received voice input;

a step of, by the voice dialogue agent unit, performing voice recognition processing on the generated voice signal and determining, based on a result of the voice recognition processing and agent information, which one of the voice dialogue agent unit and the additional voice dialogue agent unit is appropriate for performing voice-related processing that is processing based on the voice signal, the agent information being stored in a memory included in the voice dialogue agent unit and associating the additional voice dialogue agent unit with one or more keywords;

a step of, when the voice dialogue agent unit determines that the voice dialogue agent unit is appropriate for performing the voice-related processing, by the voice dialogue agent unit, performing processing based on the result of the voice recognition processing to generate a response signal, and by the voice output unit, outputting a voice based on the response signal generated by the voice dialogue agent unit;

a step of, when the voice dialogue agent unit determines that the additional voice dialogue agent unit is appropriate for performing the voice-related processing, by the voice dialogue agent unit, transferring the voice signal to the additional voice dialogue agent unit, by the additional voice dialogue agent unit, performing new voice recognition processing on the transferred voice signal and performing processing based on a result of the new voice recognition processing to generate a response signal, and by the voice output unit, outputting a voice based on the response signal generated by the additional voice dialogue agent unit; and

a step of, when the voice output unit outputs a voice, by the voice input control unit, keeping the voice signal generation unit in a receivable state for a predetermined period after output of the voice, the receivable state being a state in which a voice input is receivable.

2. The voice dialogue method of claim 1, wherein

the voice dialogue system further includes a display unit, and

the voice dialogue method further comprises

a step of, while the voice signal generation unit is in the receivable state, by the display unit, displaying that the voice signal generation unit is in the receivable state.

3. The voice dialogue method of claim 2, further comprising:

a step of, when the voice dialogue agent unit determines that the voice dialogue agent unit is appropriate for performing the voice-related processing, by the display unit, displaying that the voice dialogue agent unit is appropriate for performing the voice-related processing; and

a step of, when the voice dialogue agent unit determines that the additional voice dialogue agent unit is appropriate for performing the voice-related processing, by the display unit, displaying that the additional voice dialogue agent unit is appropriate for performing the voice-related processing.

4. The voice dialogue method of claim 2, further comprising

a step of, when the voice signal generation unit is in the receivable state and a response signal generated by the voice dialogue agent unit indicates that a new voice input does not need to be received, by the voice input control unit, switching the voice signal generation unit to an unreceivable state even during the predetermined period, the unreceivable state being a state in which a voice input is unreceivable.

5. The voice dialogue method of claim 1, wherein

the additional voice dialogue agent unit is provided in plural,

the agent information associates each of a plurality of identifiers with one or more keywords, the identifiers each identifying one of the additional voice dialogue agent units, and

the voice dialogue method further comprises

a step of, when any of the keywords is included in the result of the voice recognition processing, by the voice dialogue agent unit, determining that one of the additional voice dialogue agent units that is identified by an identifier associated with the included keyword is appropriate for performing the voice-related processing.