Speech recognition device

• US 9,704,479 B2
• Filed: 01/29/2013
• Issued: 07/11/2017
• Est. Priority Date: 04/16/2012
• Status: Expired due to Fees

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Tsuji, Hideaki, Miyaguni, Satoshi
• Primary Examiner(s): Han, Qi
• Application Number:
  US14/384,400
• Publication Number:
  US 20150100317A1
• Time in Patent Office: 1,624 Days
• Field of Search: 704243, 704231, 704235, 704244, 704246, 704251
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence

Abstract

A speech recognition device starts to generate dictionary data for each type of name based on name data and paraphrase data, and executes dictionary registration of the dictionary data. The speech recognition device obtains text information same as text information for generating the dictionary data last time. When back-up data corresponding to the last time text information is generated, the speech recognition device executes the dictionary registration of the dictionary data generated as the back-up data. Further, a dictionary data generation device executes the dictionary registration of the dictionary data based on given name data every time the dictionary data generation device completes generation of the dictionary data based on the given name data.

Claims

1. A speech recognition device comprising:

at least one processor, the at least one processor is configured to;

acquire, by a text information acquisition device, text information including a plurality of name data from an external device;

generate, by a dictionary data generation device, dictionary data for each type of the plurality of name data based on the plurality of name data included in the text information acquired by the text information acquisition device;

control, by a dictionary data saving control device, a dictionary data saving device to store the dictionary data generated by the dictionary data generation device;

register, by a dictionary registration device, the dictionary data, which is stored in the dictionary data saving device, for each type of the plurality of name data, into a dictionary;

perform, by a speech recognition device, speech recognition using the dictionary data registered in the dictionary; and

generate, by a backup data generation device, backup data of the dictionary data for each type of the plurality of name data stored in the dictionary data saving device,

wherein the at least one processor is further configured to;

generate, by the dictionary data generation device, the dictionary data for each type of name based on the name data; and

in a case where the text information acquired from the external device at a present moment is the same as the text information acquired just at a last time from the external device, and the backup data corresponding to the text information acquired from the external device at the present moment is already generated by the backup data generation device,

register, by the dictionary registration device, as the backup data in the dictionary, for each type of the plurality of name data, the dictionary data which is generated, and

then register, by the dictionary registration device, into the dictionary, the dictionary data for each type of the plurality of name data based on given name data, every time the dictionary data generation device completes generation of the dictionary data for each type of the plurality of name data based on the given name data,

wherein there are a plurality of types of name data, the plurality of types of name data including each type of the plurality of name data, wherein each of the types of name data has subjects,

wherein the processor is further configured to set an order of processing the types of name data, wherein the order is based on smaller to larger data volume of the subjects for each of the types of name data, and the dictionary data generation device generates the dictionary data based on the name data in the order from smaller to larger data volume of the subjects, for which the dictionary data is generated.

2. The speech recognition device according to claim 1, wherein:

the dictionary data generation device generates the dictionary data based on the name data in an order from higher to lower frequencies of use as the dictionary data when the speech recognition device has performed speech recognition in the past.

3. The speech recognition device according to claim 1, wherein:

when given name data is changed since the text information has been acquired the last time, the dictionary data generation device generates dictionary data based on changed name data; and

when given name data is not changed since the text information has been acquired the last time, the dictionary data generation device skips generation of dictionary data based on unchanged name data.

4. The speech recognition device according to claim 1, wherein the at least one processor is further configured to

correlate, by a correlation device, a given name with paraphrase data,

wherein:

the dictionary data generation device generates the dictionary data based on the paraphrase data correlated with the given name by the correlation device, wherein generating the dictionary data is after the generation of the dictionary data based on all of the name data is completed; and

when the dictionary data generation device completes generation of dictionary data based on the paraphrase data, then the dictionary registration device registers the dictionary data based on the paraphrase data into the dictionary.

5. The speech recognition device according to claim 4, wherein:

when the correlation device respectively correlates a plurality of names with a plurality of paraphrase data, the dictionary data generation device generates dictionary data based on the plurality of paraphrase data for each type of name; and

every time the dictionary data generation device completes generation of dictionary data based on given paraphrase data, the dictionary registration device registers the dictionary data based on the given paraphrase data into the dictionary.

6. The speech recognition device according to claim 4, wherein:

the dictionary data generation device generates the dictionary data based on the plurality of paraphrase data in an order from higher to lower frequencies of use of the paraphrase data as the dictionary data when the speech recognition device has performed speech recognition in the past.

7. The speech recognition device according to claim 4, wherein:

when given paraphrase data is changed since the text information has been acquired the last time, the dictionary data generation device generates dictionary data based on changed paraphrase data; and

when given paraphrase data is not changed since the text information has been acquired the last time, the dictionary data generation device skips generation of dictionary data based on unchanged paraphrase data.

8. The speech recognition device according to claim 1, further comprising:

a notification control device that provides a notification using a notification device that speech recognition using the backup data by the speech recognition device is available when the backup data is already generated by the backup data generation device in a period, during which the dictionary data generation device is generating the dictionary data and the dictionary registration device is registering the dictionary data into the dictionary.

9. The speech recognition device according to claim 8, wherein:

when the dictionary data generation device completes generation of dictionary data based on the name data and the paraphrase data, the notification control device provides a notification using the notification device that speech recognition using the dictionary data by the speech recognition device is available.

10. The speech recognition device according to claim 9, wherein:

the notification control device provides a notification using the notification device immediately after the dictionary data generation device completes generation of dictionary data based on the name data and the paraphrase data that speech recognition using the dictionary data by the speech recognition device is available.

11. The speech recognition device according to claim 1, further comprising:

a notification control device that provides a notification using the notification device after generation of dictionary data based on the name data and the paraphrase data is completed by the dictionary data generation device that speech recognition using the dictionary data by the speech recognition device is available when the backup data is not generated by the backup data generation device in a period, during which the dictionary data generation device is generating the dictionary data.

12. The speech recognition device according to claim 1, wherein:

the text information acquisition device acquires music information including at least an artist name, an album name, a title name, and a playlist name as the text information.

13. The speech recognition device according to claim 1, wherein:

the types of the plurality of name data, in the plurality of name data acquired by the text information acquisition device, include at least an artist name, an album name, a title name, and a playlist name.

14. The speech recognition device according to claim 1, wherein

the text information acquisition device acquires music information from the external device, wherein the music information acquired by the text information acquisition device includes the text information that includes the plurality of name data on which the generated dictionary data is based,

the music information acquired as the text information by the text information acquisition device conforms to a standard pre-defined file format,

the standard pre-defined file format specifies a plurality of types of name data, wherein the plurality of types of name data includes each type of the plurality of name data,

the name data contained in the music information include one or more of:

name data of artist names, name data of album names, name data of title names, and name data of playlist names.

15. The speech recognition device according to claim 1, wherein

the text information acquisition device acquires music information from the external device, wherein the music information acquired by the text information acquisition device includes the text information that includes the plurality of name data on which the generated dictionary data is based,

the music information acquired as the text information by the text information acquisition device conforms to an mp3 file format or a wmv file format.

16. A speech recognition device comprising:

at least one processor, the at least one processor is configured to;

acquire, by a text information acquisition device, text information including a plurality of name data from an external device;

generate, by a dictionary data generation device, dictionary data for each type of the plurality of name data based on the plurality of name data included in the text information acquired by the text information acquisition device;

control, be a dictionary data saving control device, a dictionary data saving device to store the dictionary data generated by the dictionary data generation device;

register, by a dictionary registration device, speech recognition using the dictionary data registered in the dictionary; and

generate, by a backup data generation device, backup data of the dictionary data for each type of the plurality of name data stored in the dictionary data saving device,

wherein the at least one processor is further configured to;

generate, by the dictionary data generation device, the dictionary data for each type of name based on the name data; and

in a case where the text information acquired from the external device at a present moment is the same as the text information acquired just at a last time from the external device, and the backup data corresponding to the text information acquired from the external device at the present moment is already generated by the backup data generation device,

register, by the dictionary registration device, as the backup data in the dictionary, for each type of the plurality of name data, the dictionary data which is generated, and

then register, by the dictionary registration device, into the dictionary, the dictionary data for each type of the plurality of name data based on given name data, every time the dictionary data generation device completes generation of the dictionary data for each type of the plurality of name data based on the given name data,

wherein the at least one processor is further configured to correlate, by a correlation device, a given name with paraphrase data,

wherein the dictionary data generation device generates the dictionary data based on the paraphrase data correlated with the given name by the correlation device, wherein generating the dictionary data is after the generation of the dictionary data based on all of the name data is completed,

wherein, when the dictionary data generation device completes generation of dictionary data based on the paraphrase data, then the dictionary registration device registers the dictionary data based on the paraphrase data into the dictionary

wherein there are a plurality of types of name data, the plurality of types of name data including each type of the plurality of name data, wherein each of the types of name data has subjects, and

wherein the processor is further configured to set an order of processing the types of name data, the order is based on smaller to larger data volume of the subjects for each of the types of name data, and the dictionary data generation device generates the dictionary data based on the plurality of paraphrase data in the order from smaller to larger data volume of the subjects, for which the dictionary data is generated.

17. A speech recognition device comprising:

at least one processor, the at least one processor is configured to;

acquire, by a text information acquisition device, text information including a plurality of name data from an external device;

generate, by a dictionary data generation device, dictionary data for each type of the plurality of name data based on the plurality of name data included in the text information acquired by the text information acquisition device;

control, by a dictionary data saving control device, a dictionary data saving device to store the dictionary data generated by the dictionary data generation device;

register, by a dictionary registration device, the dictionary data, which is stored in the dictionary data saving device, for each type of the plurality of name data, into a dictionary;

perform, by a speech recognition device, speech recognition using the dictionary data registered in the dictionary; and

generate, by a backup data generation device, backup data of the dictionary data for each type of the plurality of name data stored in the dictionary data saving device,

wherein the at least one processor is further configured to;

generate, by the dictionary data generation device, the dictionary data for each type of name based on the name data; and

in a case where the text information acquired from the external device at a present moment is the same as the text information acquired just at a last time from the external device, and the backup data corresponding to the text information acquired from the external device at the present moment is already generated by the backup data generation device,

register, by the dictionary registration device, as the backup data in the dictionary, for each type of the plurality of name data, the dictionary data which is generated, and

then register, by the dictionary registration device, into the dictionary, the dictionary data for each type of the plurality of name data based on given name data, every time the dictionary data generation device completes generation of the dictionary data for each type of the plurality of name data based on the given name data,

wherein the performing of the speech recognition is executable after the dictionary data for each type of name is registered in the dictionary;

wherein, when a new dictionary data is generated and registered, the at least one processor is further configured to;

register, by the dictionary registration device, the backup data in the dictionary in order to enable the speech recognition; and

register, by the dictionary registration device, the new dictionary data for each type of name in the dictionary so as to update the dictionary every time the new dictionary data for each type of name is generated,

wherein there are a plurality of types of name data, the plurality of types of name data including each type of the plurality of name data, wherein each of the types of name data has subjects,

wherein the processor is further configured to set an order of processing the types of name data, wherein the order is based on smaller to larger data volume of the subjects for each of the types of name data, and the dictionary data generation device generates the dictionary data based on the name data in the order from smaller to larger data volume of the subjects, for which the dictionary data is generated.