Language independent voice-based search system

• US 6,999,932 B1
• Filed: 10/10/2000
• Issued: 02/14/2006
• Est. Priority Date: 10/10/2000
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Zhou, Guojun
• Primary Examiner(s): Azad, Abul K.
• Application Number:
  US09/685,419
• Time in Patent Office: 1,953 Days
• Field of Search: 704/270.1, 704/275, 704/270, 704/277, 704/251, 704/260, 704/266
• US Class Current: 704/277
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3337 Translation of the query language, e.g. Chinese to English
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/42 Data-driven translation
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A language independent, voice based user interface method includes receiving voice input data spoken by a user, identifying a language spoken by the user from the voice input data, converting the voice input data into a first text in the identified language by recognizing the user'"'"'s speech in the voice input data based at least in part on the language identifier, parsing the first text to extract a keyword, and using the keyword as a command to an application. Further actions include receiving results to the command, converting the results into a second text in a natural language format according to the identified language, and rendering the second text for perception by the user.

Claims

1. A method of interfacing to a system comprising:

receiving speech input data from a user;

identifying a language spoken by the user from the speech input data;

converting the speech input data into a first text in the identified language by recognizing the user'"'"'s speech in the speech input data based at least in part on the language identifier;

parsing the first text to extract keywords;

automatically translating the keywords into a plurality of automatically selected languages other than the identified language;

using the translated keywords as a command to an application;

receiving results to the command;

automatically summarizing the results;

converting the summarized results into a second text with a prosodic pattern according to the language spoken by the user; and

rendering the second text for perception by the user.

2. The method of claim 1, wherein rendering comprises converting the second text into speech and rendering the speech to the user.

3. The method of claim 1, further comprising using the keywords as a search query to at least one search engine, wherein the results comprise search results from the at least one search engine operating on the search query.

4. The method of claim 1, further comprising automatically translating the keywords into a plurality of automatically selected languages other than the identified language and using the translated keywords as a search query to at least one search engine in multiple languages, wherein the results comprise search results in multiple languages from the at least one search engine operating on the search query.

5. The method of claim 4, further comprising automatically translating search results in languages other than the language spoken by the user into the language spoken by the user.

6. The method of claim 1, wherein the application comprises a web browser.

7. The method of claim 6, wherein the web browser interfaces with at least one search engine and the command comprises a search query.

8. The method of claim 6, wherein the web browser interfaces with a shopping web site and the command comprises at least one of a purchase order and a request for product information.

9. The method of claim 1, wherein the speech comprises conversational speech.

10. The method of claim 1, wherein the prosodic pattern is capable of making the second text sound natural and grammatically correct.

11. An article comprising:

a storage medium having a plurality of machine readable instructions, wherein when the instructions are executed by a processor, the instructions provide for interfacing to a system by receiving speech input data from a user, identifying a language spoken by the user from the speech input data, converting the speech input data into a first text in the identified language by recognizing the user'"'"'s speech in the speech input data based at least in part on the language identifier, parsing the first text to extract keywords, automatically translating the keywords into a plurality of automatically selected languages other than the identified language, using the translated keywords as a command to an application, receiving results to the command, automatically summarizing the results, converting the summarized results into a second text a prosodic pattern according to the language spoken by the user, and rendering the second text for perception by the user.

12. The article of claim 11, wherein instructions for rendering comprise instructions for converting the second text into speech and rendering the speech to the user.

13. The article of claim 11, further comprising instructions for using the keywords as a search query to at least one search engine, wherein the results comprise search results from the at least one search engine operating on the search query.

14. The article of claim 11, further comprising instructions for automatically translating the keywords into a plurality of automatically selected languages other than the identified language and using the translated keywords as a search query to at least one search engine in multiple languages, wherein the results comprise search results in multiple languages from the at least one search engine operating on the search query.

15. The article of claim 14, further comprising instructions for automatically translating search results in languages other than the language spoken by the user into the language spoken by the user.

16. The article of claim 11, wherein the application comprises a web browser.

17. The article of claim 16, wherein the web browser interfaces with at least one search engine and the command comprises a search query.

18. The article of claim 16, wherein the web browser interfaces with a shopping web site and the command comprises at least one of a purchase order and a request for product information.

19. The article of claim 11, wherein the speech comprises conversational speech.

20. The article of claim 11, wherein the prosodic pattern makes the second text sound natural and grammatically correct.

21. A language independent speech based user interface system comprising:

a language identifier to receive speech input data from a user and to identify the language spoken by the user;

at least one speech recognizer to receive the speech input data and the language identifier and to convert the speech input data into a first text based at least in part on the language identifier;

at least one natural language processing module to parse the first text to extract keywords;

at least one summarization module to automatically summarize the search results from at least one search engine operating on the search query using the extracted keywords;

at least one language translator to automatically translate the keywords into a plurality of automatically selected languages other than the identified language for use as a command to an application, and to translated results to the command in languages other than a language spoken by the user to the language spoken by the user; and

at least one natural language generator to convert the summarized results into a second text with a prosodic pattern according to the language spoken by the user.

22. The system of claim 21, further comprising at least one text to speech module to render the second text audibly to the user.

23. The system of claim 21, further comprising at least one language translator to automatically translate the keywords into a plurality of automatically selected languages for use as a search query, and to automatically translate the search results in languages other than the language spoken by the user into the language spoken by the user prior to summarizing the translated results and converting the summarized results into the second text in a natural language format.

24. The system of claim 21, wherein the system is coupled to a web browser.

25. The system of claim 24, wherein the web browser interfaces with at least one search engine, the keyword comprises a search query, and the second text comprises search results from the at least one search engine.

26. The system of claim 24, wherein the web browser interfaces with a shopping web site and the command comprises at least one of a purchase order and a request for product information.

27. The system of claim 21, wherein the prosodic pattern makes the second text sound natural and grammatically correct.

28. A language independent speech based search system comprising:

a language identifier to receive speech input data from a user and to identify the language spoken by the user;

at least one speech recognizer to receive the speech input data and the language identifier and to convert the speech input data into a first text based at least in part on the language identifier;

at least one natural language processing module to parse the first text to extract keywords;

at least one search engine to use the keywords as a search term and to return search results;

at least one language translator to automatically translate the keyword into a plurality of automatically selected languages prior to input to the at least one search engine to search across multiple languages, and to automatically translate search results in languages other than the language spoken by the user into the language spoken by the user;

at least one automatic summarization module to automatically summarize the translated search results;

at least one natural language generator to convert the summarized results into a second text with a prosodic pattern according to the language spoken by the user.

29. The system of claim 28, further comprising at least one text to speech module to render the second text audibly to the user.

30. The system of claim 28, wherein the prosodic pattern makes the second text sound natural and grammatically correct.