Information access system and recording system

• US 5,903,867 A
• Filed: 11/23/1994
• Issued: 05/11/1999
• Est. Priority Date: 11/30/1993
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Minamino, Katsuki, Watanabe, Kazuo, Omote, Masanori, Asano, Yasuharu, Ogawa, Hiroaki, Kagami, Tetsuya, Akabane, Makoto, Ishii, Kazuo, Kato, Yasuhiko, Watari, Masao, Iwahashi, Yusuke
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Opsasnick, Michael N.
• Application Number:
  US08/344,843
• Time in Patent Office: 1,630 Days
• Field of Search: 395/2.79, 395/2.8, 395/2.84, 395/600, 395/761, 704/270, 704/272
• US Class Current: 704/270
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G09B 21/001 Teaching or communicating with blind persons G09B21/02 - G09B21/06 take precedence

Abstract

A book database stores at least phonetic signal information including phoneme information and rhythm information as document data, a central system transmits phonetic signal information stored on the book database to a terminal and the terminal receives the phonetic signal information is then carried out at the terminal and the document is then recited via synthesized sounds.

Claims

1. An information access system, comprising:

a central system having a database on which information is stored; and

a terminal connected to the central system by a communications line, which can access information on the database, said terminal including speech synthesizing means for synthesizing speech from phonetic signal information and said terminal further including input means for inputting keywords from desired documents;

wherein the database stores at least phonetic signal information including phoneme information, rhythm information and items related to publications, the central system transmits phonetic signal information stored on the database to the terminal, and the terminal receives the phonetic signal information transmitted from the central system, and further

wherein said central system further includes searching means for searching the database for phonetic signal information relating to the publications corresponding to the keywords sent from the terminal, wherein keywords outputted by the input means are sent to the central system and searching means search results are sent to the terminal.

2. The system of claim 1 wherein items relating to an abstract from within phonetic signal information relating to the document present in the searching means search results are transmitted by the central system to the terminal.

3. The system of claim 1 wherein said central system further includes central speech recognition means for recognizing the speech inputted to the input means, and further wherein the keywords for the desired document are inputted to the input means verbally and the search means searches for phonetic signal information relating to the document on the database using central speech recognition means recognition results.

4. The system of claim 3, wherein, when a plurality of the keywords are inputted verbally at the input means, the speech recognition means determines whether or not a combination of respective speech recognition results has been obtained for the plurality of keywords, and outputs respective speech recognition results for the plurality of keywords based on the speech recognition results.

5. The system of claim 1 wherein said input means includes a keyboard, button, jog dial or shuttle ring.

6. The system of claim 1 wherein the keyword is attribute data expressing the attributes of the document, a relationship table expressing the relationship between the attribute data and the document corresponding to the attribute data is stored on the database, and the search means executes searches with reference to the relationship table.

7. The system of claim 6 wherein unique document identity numbers or attribute identity numbers for identification are assigned respectively to the document or the attribute data and the relationship table describes the corresponding relationship using the document identity number and the attribute identity number.

8. The system of claim 6 wherein the attribute data is constituted by items for which speech has been recognized, and the search means carries out the search from the phonetic signal information relating to the document corresponding to the attribute data for which the plausibility of the speech recognition results is highest.

9. The system of claim 6 wherein said attribute data includes the document title, name of publisher, name of the author, day of issue, page number or field.

10. The system of claim 7 wherein the central system further includes past search information recording means for storing document identity numbers and attribute identity numbers which were searched in the past, wherein the search means searches by initially referring to the past search information recording means.

11. The system of claim 1 wherein the central system further includes search scope storage means for storing the scope of the search, wherein the search means carries out the search within the search scope stored in the search scope storage means.

12. The system of claim 1 wherein said central system further includes search frequency storage means for storing the frequency with which the phonetic signal information relating to the document is searched for by the search means, wherein the search means refers to the search frequency storage means and searches sequentially from the group of items of phonetic signal information relating to documents of a high search frequency.

13. The system of claim 1 wherein the attribute data is constituted by items for which speech has been recognized, and the search means carries out the search from the phonetic signal information relating to the document corresponding to the attribute data for which the plausibility of the speech recognition results is highest.

14. An information access system, comprising:

a central system having a database on which information is stored, said central system including an authoring system which produces phonetic signal information from information relating to the document and stores the phonetic signal information at the database, said authoring system including;

analyzing means for analyzing the document text data and generating phonetic signal information based on the analysis results;

mistaken reading correction means for correcting words which have been read incorrectly from document text data in the analysis means analysis results; and

mistaken de-voicing correction means for correcting mistakes in the de-voicing of vowels when the de-voicing has been mistaken in vowels occurring in document text data in the analyzing means analysis results; and

a terminal connected to the central system by a communications line, which can access information on the database;

wherein the database stores at least phonetic signal information including phoneme information and rhythm information, the central system transmits phonetic signal information stored on the database to the terminal, and the terminal receives the phonetic signal information transmitted from the central system.

15. The system of claim 14 wherein the authoring system further includes mistaken accent correction means for correcting mistakenly accented words occurring in document text data in the analysis means analysis results.

16. The system of claim 15 wherein the authoring system further includes mistaken pause position correction means for correcting mistakenly inserted pause positions in the analysis means analysis results document text data.

17. The system of claim 16 wherein the authoring system further includes mistaken phrase correction means for correcting mistaken phrases occurring in the document text data for the analysis means analysis results.

18. The system of claim 17 wherein the authoring system further includes mistaken vowel voice length correcting means for correcting mistaken vowel voice lengths when the voice length of vowels occurring in the document text data are mistaken in the analysis means analysis results.