Speech recognizer control system, speech recognizer control method, and speech recognizer control program

• US 8,484,033 B2
• Filed: 01/24/2007
• Issued: 07/09/2013
• Est. Priority Date: 02/24/2006
• Status: Expired due to Fees

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Nagashima, Hisayuki
• Primary Examiner(s): He, Jialong
• Application Number:
  US11/656,943
• Publication Number:
  US 20070203699A1
• Time in Patent Office: 2,358 Days
• Field of Search: 704/270, 704/275
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A speech recognizer control system, a speech recognizer control method, and a speech recognizer control program make it possible to properly identify a device on the basis of a speech utterance of a user and to control the identified device. The speech recognizer control system includes a speech input unit to which a speech utterance is input from a user, a speech recognizer which recognizes the content of the input speech utterance, a device controller which identifies a device to be controlled among a plurality of devices on the basis of at least the recognized speech utterance content and which controls an operation of the identified device, and a state change storage which stores, as first auxiliary information for identifying a device to be controlled, a state change other than at least a state change caused by a speech utterance from the user among the state changes of operations in the individual devices of the plurality of devices. The device controller carries out first device identification processing for identifying the device to be controlled on the basis of the recognized speech utterance content, and if the device cannot be identified by the first device identification processing, then the device controller uses at least the first auxiliary information to identify the device.

Claims

1. A speech recognizer control system comprising:

a speech input element to which a speech utterance is inputted from a first user;

a speech recognition element which recognizes a content of the speech utterance input to the speech input element;

a device controlling element which identifies a device to be controlled among a plurality of devices on the basis of at least the content of the speech utterance recognized by the speech recognition element, wherein the content of the speech utterance controls an operation of the identified device; and

a state change storing element storing a first auxiliary information for identifying a device to be controlled, wherein the first auxiliary information comprises an identification of an active state corresponding to at least a state change not caused by a speech utterance from the first user, wherein the state change is stored as an active state until a predetermined amount of time elapses from a time at which the state change occurred, wherein the first auxiliary information further comprises an identification of at least one of a plurality of predetermined types of human senses associated with the content of the speech utterance;

wherein the device controlling element executes first device identification processing for identifying the device to be controlled on the basis of the content of the speech utterance recognized by the speech recognition element; and

if the device cannot be identified by the first device identification processing, then the device controlling element uses at least the first auxiliary information stored in the state change storing element to identify the device to be controlled.

2. The speech recognizer control system according to claim 1, wherein

the state change storing element stores, as the first auxiliary information, a state change which automatically takes place in each of the devices.

3. The speech recognizer control system according to claim 1, wherein

the speech input element receives speech utterances from the first user and another person other than the first user, respectively,

the speech recognition element recognizes the contents of the speech utterances input to the speech input element while distinguishing the content of the speech utterance of the first user from the content of the speech utterance of another person, and

the state change storing element stores, as the first auxiliary information, a state change of an operation in each of the devices that has caused by the speech utterance of another person.

4. The speech recognizer control system according to claim 1, wherein

the speech recognition element recognizes the content of the speech utterance input to the speech input element by associating the content of the speech utterance with one of the plurality of predetermined types of human senses,

the state change storing element associates the first auxiliary information with one of the plurality of types of human senses when storing the first auxiliary information, and

the device controlling element uses the first auxiliary information which is associated with the same type of human sense as the type of human sense with which the content of the speech utterance recognized by the speech recognition element is associated in the first auxiliary information stored by the state change storing element in order to identify the device to be controlled if the device cannot be identified by the first device identification processing.

5. The speech recognizer control system according to claim 1, wherein

the device controlling element uses a latest piece of first auxiliary information of the pieces of first auxiliary information stored by the state change storing element in order to identify the device to be controlled if the device to be controlled cannot be identified by the first device identification processing.

6. The speech recognizer control system according to claim 1, wherein

the state change storing element stores, in addition to the first auxiliary information, a state change caused by a speech utterance of the first user as second auxiliary information for identifying the device to be controlled, and

the device controlling element executes second device identification processing for identifying the device to be controlled by using the first auxiliary information stored by the state change storing element if the device cannot be identified by the first device identification processing, and if the device cannot be identified by the second device identification processing, then the device controlling element uses the second auxiliary information stored by the state change storing element to identify the device.

7. The speech recognizer control system according to claim 1, further comprising:

a response output element which outputs a response to the first user; and

a response controlling element which controls the response such that, if there is a plurality of pieces of the first auxiliary information related to the content of the speech utterance recognized by the speech recognition element, the piece of the first auxiliary information to be used for identifying the device to be controlled is identified from among the plurality of pieces of the first auxiliary information.

8. A speech recognizer control system which has a microphone to which a speech utterance is input from a first user and a computer having an interface circuit for accessing speech data obtained through the microphone, recognizes the content of the speech utterance of the first user input to the microphone by arithmetic processing by the computer, identifies a device to be controlled among a plurality of devices on the basis of at least the recognized content of the speech utterance, and controls an operation of the identified device, the speech recognizer control system comprising:

a memory which stores, as first auxiliary information for identifying the device to be controlled, an identification of an active state corresponding to at least a state change not caused by the speech utterance from the first user, wherein the state change is stored as an active state until a predetermined amount of time elapses from a time at which the state change occurred,

wherein the computer executes;

first device identification processing for identifying the device to be controlled on the basis of the content of the speech utterance recognized by the speech recognition element, and

second device identification processing for identifying the device by using at least the first auxiliary information if the device cannot be identified by the first device identification processing.

9. A speech recognizer control method comprising:

a speech recognizing step which recognizes a content of a speech utterance of a first user input to a speech input element;

a device controlling step which identifies a device to be controlled among a plurality of devices on the basis of at least the content of the speech utterance recognized in the speech recognizing step, wherein the content of the speech utterance controls an operation of the identified device; and

a state change storing step storing a first auxiliary information for identifying the device to be controlled, in a state change storing element, wherein the first auxiliary information comprises an identification of an active state corresponding to at least a state change not caused by the speech utterance from the first user, wherein the state change is stored as an active state until a predetermined amount of time elapses from a time at which the state change occurred, wherein the first auxiliary information further comprises an identification of at least one of a plurality of predetermined types of human senses associated with the content of the speech utterance,

wherein the device controlling step executes first device identification processing for identifying the device to be controlled on the basis of the content of the speech utterance recognized in the speech recognizing step, and if the device cannot be identified by the first device identification processing, then at least the first auxiliary information stored in the state change storing step is used to identify the device to be controlled.

10. A non-transitory storage medium encoded with a speech recognizer control program having control logic stored therein for causing a computer to execute:

speech recognition processing for recognizing a content of a speech utterance of a first user input to a speech input element;

device control processing for identifying a device to be controlled among a plurality of devices on the basis of at least the content of the speech utterance recognized by the speech recognition processing and for controlling an operation of the identified device based on the content of the speech utterance; and

state change storage processing for storing a first auxiliary information for identifying the device to be controlled, in a state change storing element, wherein the first auxiliary information comprises an identification of an active state corresponding to at least a state change not caused by the speech utterance from the first user, wherein the state change is stored as an active state until a predetermined amount of time elapses from a time at which the state change occurred, wherein the first auxiliary information further comprises an identification of at least one of a plurality of predetermined types of human senses associated with the content of the speech utterance,

wherein the device control processing has a function which causes the computer to execute;

first device identification processing for identifying the device to be controlled on the basis of the content of the speech utterance recognized by the speech recognition processing; and

second device identification processing for identifying the device to be controlled by using at least the first auxiliary information if the device cannot be identified by the first device identification processing.