Automatic search of audio channels by matching viewer-spoken words against closed-caption/audio content for interactive television

• US 6,480,819 B1
• Filed: 02/25/1999
• Issued: 11/12/2002
• Est. Priority Date: 02/25/1999
• Status: Expired due to Term

• Current Assignee: Intertrust Technologies Corporation (Fidelio Acquisition Co LLC)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Junqua, Jean-Claude, Boman, Robert
• Primary Examiner(s): EDOUARD, PATRICK NESTOR
• Application Number:
  US09/258,115
• Time in Patent Office: 1,356 Days
• Field of Search: 704/9, 704/8-10, 704/243, 704/250, 704/251, 704/252, 704/253, 704/254, 704/255, 704/256, 704/257, 704/270, 704/272, 704/275
• US Class Current: 704/9
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method and apparatus is provided to enable a user watching and/or listening to a program to search for new information in the stream of a telecommunications data. The apparatus includes a voice recognition system that recognizes the user'"'"'s request and causes a search to be performed in the long stream of data of at least one other telecommunication channel. The system includes a storage device for storing and processing the request. Upon recognition of the request, the incoming signal or signals are scanned for matches with the request. Upon finding the match between the request and the incoming signal, information related to the data is brought to the viewer'"'"'s attention. This can be accomplished by either changing the viewer'"'"'s station or by bringing in a split screen display forward into the display.

Claims

1. A system receiving an input signal from a telecommunications infrastructure and displaying information on a display, the input signal having a plurality of information components derived from the input signal and being organized into channels, said system comprising:

a speech recognizer for receiving a user-spoken request from a user and producing a first output;

a systematic analyzer for processing the first output to produce a word list;

a text pattern matcher for comparing the word list with the plurality of information components; and

a channel selector operative to select a channel of the input signal in response to said text pattern matcher comparing the word list with the plurality of information components.

2. The system of claim 1 further comprising a plurality of digital tuners for parsing the input'"'"'s signal into the information components.

3. The system of claim 2 wherein the speech recognizer further contains a plurality of speech models, each model representing either a sub-word unit or a letter template.

4. The system of claim 3 wherein the semantic analyzer contains a natural language analyzer which recognizes at least one of:

synonymous, spelled word, system commands.

5. The system of claim 4 wherein the speech recognizer provides a plurality of likely requests and the word selector determines which request in the word list will be used in the search.

6. The system of claim 5 wherein the semantic analyzer stores historical information or past searches and uses historical information in its determination of which words from the word list will be searched.

7. The system of claim 5 wherein the word selector semantic analyzer contains a local parser and a global parser.

8. The system of claim 5 wherein the word selector semantic analyzer provides synonyms of search terms to the text pattern matcher.

9. The system of claim 5 wherein the text pattern matcher compares the word list to the data from the plurality of tuners.

10. The system of claim 1, wherein the channel selected for display corresponds to a matching channel having matching information components that correspond at least in part to the word list.

11. The system of claim 10, wherein the matching information components correspond to closed-caption/audio content composed of text that corresponds at least in part to the word list.

12. The system of claim 10, wherein the word list contains a synonym of a word of which the user-spoken request is comprised.

13. A method for selecting a channel for display in a telecommunications system, the method comprising:

receiving an input signal having a plurality of channels, wherein at least one channel includes an information component;

receiving a user-spoken request comprised of at least one user-spoken word;

recognizing at least one recognized word corresponding to the user-spoken word;

generating a word list based on the recognized word;

comparing the word list to the information component; and

displaying the channel as a result of comparing the word list to the information component.

14. The method of claim 13, wherein the information component corresponds to closed-caption/audio content of the channel.

15. The method of claim 13, wherein the word list includes a synonym of the recognized word.

16. The method of claim 13, wherein said displaying of the channel is further defined to occur as a result of a successful search for matching content between the word list and the information component.