Speech recognition dictionary creation apparatus and information search apparatus

• US 7,437,296 B2
• Filed: 03/10/2004
• Issued: 10/14/2008
• Est. Priority Date: 03/13/2003
• Status: Expired due to Fees

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Inoue, Tsuyoshi, Nishizaki, Makoto, Konuma, Tomohiro
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US10/796,037
• Publication Number:
  US 20040181391A1
• Time in Patent Office: 1,679 Days
• Field of Search: 704/270, 704/275, 348/114, 348/734, 715/727
• US Class Current: 704/275
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

A program guidance apparatus includes a recognition word storage unit (105) operable to store a past recognition word that is recognized by speech recognition in the past, a viewing history word storage unit (106) operable to store viewing history words that are the information of a viewed program and a dictionary creating unit (103) operable to create a customized recognition dictionary that is created by adding the past recognition word and viewing history words that are not included in the basic recognition dictionary to the basic recognition dictionary and another customized recognition dictionary to which weights are assigned using “item weight coefficient” according to the categories of words and “history weight coefficient” according to whether or not the word is recorded as a past recognition word or viewing history words.

Claims

1. A speech recognition dictionary creation apparatus for creating and storing recognition dictionaries for speech recognition, comprising:

a dictionary creating unit operable to create a plurality of recognition dictionaries with different contents depending on presence/absence of user experience;

an action history word obtaining unit operable to obtain an action history word recognized based on an action of a user;

an action history word storage unit operable to store the obtained action history word;

a fixed word storage unit operable to store fixed words set previously;

a word extracting unit operable to extract new recognition words recognized from inputted data,

wherein the dictionary creating unit creates one of the plurality of recognition dictionaries by selecting new registration words from the new recognition words, the fixed words and the action history word, registering the new registration words in the recognition dictionary and adding, to the new registration words, information indicating pronunciations and parts of speech of the new registration words.

2. The speech recognition dictionary creation apparatus according to claim 1,

wherein the dictionary creating unit creates the plurality of recognition dictionaries by registering words in the recognition dictionaries based on attributes of the words.

3. The speech recognition dictionary creation apparatus according to claim 1,

wherein the presence/absence of user experience is related to presence/absence of viewing, and

the dictionary creating unit creates the plurality of recognition dictionaries based on the presence/absence of the viewing.

4. The speech recognition dictionary creation apparatus according to claim 1,

wherein the presence/absence of user experience is related to presence/absence of using, and

the dictionary creating unit creates the plurality of recognition dictionaries based on the presence/absence of the using.

5. The speech recognition dictionary creation apparatus according to claim 1,

wherein the presence/absence of user experience is related to presence/absence of visiting, and

the dictionary creating unit creates the plurality of recognition dictionaries based on the presence/absence of the visiting.

6. The speech recognition dictionary creation apparatus according to claim 1, further comprising:

a recognition word obtaining unit operable to obtain a past recognition word recognized by speech recognition; and

a past recognition word storage unit operable to store the past recognition word,

wherein the dictionary creating unit creates one of the plurality of recognition dictionaries by selecting new registration words from the new recognition words, the fixed words, the action history word and the past recognition word, registering the new registration words in the recognition dictionary and adding, to the new registration words, information indicating pronunciations and parts of speech of the new registration words.

7. The speech recognition dictionary creation apparatus according to claim 6,

wherein the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on whether or not the words are included in the past recognition word and adding, to the new registration words, information related to the assigned weights.

8. The speech recognition dictionary creation apparatus according to claim 6,

wherein the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on whether or not the words are included in the action history word and the words are included in the past recognition word and adding, to the new registration words, information related to the assigned weights.

9. The speech recognition dictionary creation apparatus according to claim 6,

wherein the inputted data is structured data,

the word extracting unit extracts attributes of the new recognition words together with the new recognition words, and

the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on the attributes of the new recognition words and adding, to the new registration words, information related to the assigned weights.

10. The speech recognition dictionary creation apparatus according to claim 6, further comprising:

a user information obtaining unit operable to obtain user recognition information for identifying the user,

wherein the dictionary creating unit creates the recognition dictionary for each piece of the user recognition information.

11. The speech recognition dictionary creation apparatus according to claim 6,

wherein the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on whether or not the words are included in the action history word and adding, to the new registration words, information related to the assigned weights.

12. The speech recognition dictionary creation apparatus according to claim 1,

wherein the dictionary creating unit determines, as the new registration words, following three kinds of words:

the new recognition words;

the fixed words; and

a word that is not included either in the new recognition words or in the fixed words and that belongs both to the action history word and to the past recognition word.

13. The speech recognition dictionary creation apparatus according to claim 1,

wherein the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on whether or not the words are included in the action history word and adding, to the new registration words, information related to the assigned weights.

14. The speech recognition dictionary creation apparatus according to claim 1,

wherein the inputted data is structured data,

the word extracting unit extracts attributes of the new recognition words together with the new recognition words, and

the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on the attributes of the new recognition words and adding, to the new registration words, information related to the assigned weights.

15. The speech recognition dictionary creation apparatus according to claim 14,

wherein the dictionary creating unit creates one of the plurality of recognition dictionaries with different weights for the new registration words according to purposes, these weights being determined based on attributes of the new recognition words.

16. The speech recognition dictionary creation apparatus according to claim 14, further comprising:

an instruction accepting unit operable to accept an instruction from the user related to use purpose of the recognition dictionary,

wherein the dictionary creating unit creates one of the plurality of recognition dictionaries by assigning weights to each of the new registration words based on the attributes of the new recognition words in response to the instruction related to the use purpose that is accepted by the instruction accepting unit.

17. The speech recognition dictionary creation apparatus according to claim 14, further comprising:

a user information obtaining unit operable to obtain user recognition information for identifying a user,

wherein the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words for each piece of the user recognition information.

18. The speech recognition dictionary creation apparatus according to claim 1, further comprising:

a user information obtaining unit operable to obtain user recognition information for identifying the user,

wherein the dictionary creating unit creates the recognition dictionary for each piece of the user recognition information.

19. The speech recognition dictionary creation apparatus according to claim 1,

wherein the action history word obtaining unit records action date and time together with the action history word in the action history word storage unit,

the dictionary creating unit creates the recognition dictionary by further adding the action date and time to some of new registration words, these new registration words being selected from the action history word, and

the speech recognition dictionary creation apparatus further comprises

a word deleting unit operable to delete, from the recognition dictionary, the registration words which have been stored for a predetermined time period starting from the action date and time of the registration words.

20. The speech recognition dictionary creation apparatus according to claim 1, further comprising:

an EPG receiving unit operable to demultiplex, from a TV signal, the EPG data that is an electronic program guide,

wherein an action of the user is the action that the user has viewed a program,

the action history word obtaining unit obtains the action history word in response to the action that the user has viewed the program, and

the word extracting unit extracts, from the EPG data, the new recognition words for each category that is the attribute.

21. The speech recognition dictionary creation apparatus according to claim 20,

wherein the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on the categories of the EPG data and adding, to the new registration words, information related to the assigned weights.

22. The speech recognition dictionary creation apparatus according to claim 21,

wherein the dictionary creating unit creates a recognition dictionary for programs broadcasted in the future and another recognition dictionary for recorded programs, the recognition dictionary for programs broadcasted having higher weights for the registration words whose categories are “

genre” and

lower weights for the registration words whose categories are “

title” and

the recognition dictionary for recorded programs having higher weights for the registration words whose categories are “

title” and

lower weights for the registration words whose categories are “

genre”

.

23. The speech recognition dictionary creation apparatus according to claim 1,

wherein the dictionary creating unit determines, as the new registration words, following three kinds of words:

the new recognition words;

the fixed words; and

a word that is not included either in the new recognition words or in the fixed words and that belongs to the action history word.

24. An information search apparatus for creating and storing recognition dictionaries for speech recognition and searching information using a speech signal based on speech of a user, comprising:

a dictionary creating unit operable to create a plurality of recognition dictionaries depending with different contents on presence/absence of user experience;

a speech recognition unit operable to recognize a specific word from the speech signal by referring to one of the recognition dictionaries;

a data storage unit operable to store inputted data; and

a control unit operable to search the data for a word that is recognized by the speech recognition unit and output corresponding information

an action history word obtaining unit operable to obtain an action history word recognized based on an action of a user;

an action history word storage unit operable to store the obtained action history word;

a fixed word storage unit operable to store fixed words previously;

a word extracting unit operable to extract new recognition words recognized from inputted data; and

a dictionary storage unit operable to store the created recognition dictionary,

wherein the dictionary creating unit creates the recognition dictionary by selecting new registration words from the new recognition words, the fixed words and the action history word, registering the new registration words in the recognition dictionary and adding, to the new registration words, information indicating pronunciations and parts of speech of the new registration words.

25. The information search apparatus according to claim 24,

wherein the dictionary creating unit creates the plurality of recognition dictionaries based on attributes of words registered in the recognition dictionaries.

26. The information search apparatus according to claim 24,

wherein the presence/absence of the user experience is related to presence/absence of viewing, and

the dictionary creating unit creates the plurality of recognition dictionaries based on presence/absence of the viewing.

27. The information search apparatus according to claim 24,

wherein the presence/absence of the user experience is related to presence/absence of viewing, and

the dictionary creating unit creates the plurality of recognition dictionaries based on the presence/absence of the viewing.

28. The information search apparatus according to claim 24,

wherein the presence/absence of the user experience is related to presence/absence of visiting, and

the dictionary creating unit creates the plurality of the recognition dictionaries based on the presence/absence of the visiting.

29. The information search apparatus according to claim 24,

wherein the inputted data is structured data, the word extracting unit extracts attributes of the new recognition words together with the new recognition words, and

the dictionary creating unit creates the recognition dictionary by assigning weights to each of the new registration words based on the attributes of the new recognition words and adding, to the new registration words, information related to the assigned weights and creates the plurality of recognition dictionaries with different weights for the new registration words depending on purposes, these weights being determined based on attributes of the new recognition words,

the information search apparatus further comprises:

a dictionary selection accepting unit operable to accept a dictionary selected by a user from the plurality of recognition dictionaries stored in the dictionary storage unit,

wherein the speech recognition unit recognizes a specific word obtained from a speech signal based on speech of a user by referring to the recognition dictionary accepted by the dictionary selection accepting unit.

30. The information search apparatus according to claim 24, further comprising:

an EPG receiving unit operable to demultiplex, from a TV signal, EPG data that is an electronic program guide,

wherein the action of the user is the action that the user has viewed a program,

the action history word obtaining unit obtains the action history word in response to the action that the user has viewed the program,

the word extracting unit extracts, from the EPG data, the new recognition word for each category that is the attribute,

the data storage unit stores the EPG data, and

the control unit outputs information related to corresponding program by searching the EPG data for the word recognized by the speech recognition unit.

31. A speech recognition dictionary creation apparatus for creating storing recognition dictionaries used for speech recognition, comprising:

an action history word obtaining unit operable to obtain an action history word recognized based on actions of a user;

an action history word storage unit operable to store the obtained action history word;

a fixed word storage unit operable to store fixed words set previously;

a word extracting unit operable to extract new recognition words recognized from inputted data;

a dictionary creating unit operable to create the recognition dictionary by selecting new registration words from the new recognition words, the fixed words and the action history word, registering the new registration words in the recognition dictionary and adding, to the new registration words, information indicating pronunciations and parts of speech of the new registration words; and

a dictionary storage unit operable to store the created recognition dictionary.

32. A speech recognition dictionary creation method for creating storing recognition dictionaries used for speech recognition comprising:

creating a plurality of recognition dictionaries with different contents depending on presence/absence of user experience;

obtaining an action history word recognized based on an action of a user;

storing the action history word;

storing fixed words set previously;

extracting new recognition words recognized from inputted data;

storing the plurality of created recognition dictionaries,

wherein one of the plurality of recognition dictionaries is created by selecting new registration words from the new recognition words, the fixed words and the action history word, registering the new registration words in the recognition dictionary and adding, to the new registering words, information indicating pronunciations and parts of speech of the new registration words.

33. An information search method for creating and storing recognition dictionaries used for speech recognition and searching information obtained from a speech signal based on speech of a user, comprising:

creating a plurality of recognition dictionaries with different contents depending on presence/absence of user experience;

recognizing a specific word from the speech signal by referring to the recognition dictionaries; and

searching the inputted data for a word recognized by the speech recognition unit and outputting corresponding data;

obtaining an action history word recognized based on an action of a user;

storing the action history word;

storing fixed words set previously;

extracting new recognition words recognized from inputted data;

storing the plurality of created recognition dictionaries,

wherein one of the plurality of recognition dictionaries is created by selecting new registration words from the new recognition words, the fixed words and the action history word, registering the new registration words in the recognition dictionary and adding, to the new registration words, information indicating pronunciations and parts of speech of the new registration words.

34. “

A program stored on a computer readable storage medium for causing”

a computer to execute a process of creating and storing recognition dictionaries used for speech recognition, comprising;

creating a plurality of recognition dictionaries with different contents depending on presence/absence of user experience; and

obtaining an action history word recognized based on an action of a user;

storing the action history word;

storing fixed words set previously;

extracting new recognition words recognized from inputted data;

storing the plurality of created recognition dictionaries,

wherein one of the plurality of recognition dictionaries is created by selecting new registration words from the new recognition words, the fixed words and the action history word, registering the new registration words in the recognition dictionary and adding, to the new registration words, information indicating pronunciations and parts of speech of the new registration words.

35. “

A program stored on a computer readable storage medium for causing”

a computer to processes of creating and storing recognition dictionaries for speech recognition and searching information obtained from a speech signal based on speech of a user, comprising;

creating a plurality of recognition dictionaries with different contents depending on presence/absence of user experience;

storing the plurality of created recognition dictionaries;

recognizing a specific word from the speech signal by referring to one of the recognition dictionaries; and

searching the inputted data for words recognized by the speech recognition unit and outputting corresponding information

obtaining an action history word recognized based on an action of a user;

storing the action history word;

storing fixed words set previously;

extracting new recognition words recognized from inputted data;

storing the plurality of created recognition dictionaries,

wherein one of the plurality of recognition dictionaries is created by selecting new registration words from the new recognition words, the fixed words and the action history word, registering the new registration words in the recognition dictionary and adding, to the new registration words, information indicating pronunciations and parts of speech of the new registration words.