Speech controlled access to content on a presentation medium

• US 7,519,534 B2
• Filed: 10/30/2003
• Issued: 04/14/2009
• Est. Priority Date: 10/31/2002
• Status: Active Grant

• Current Assignee: Promptu Systems Corporation
• Original Assignee: Agiletv Corporation (Promptu Systems Corporation)
• Inventors: Williams, Jody, Jordan, Adam, Maddux, Scott Lynn, Printz, Harry W.
• Primary Examiner(s): Lerner; Martin
• Application Number:
  US10/699,543
• Publication Number:
  US 20040193426A1
• Time in Patent Office: 1,993 Days
• Field of Search: 704/275, 704/251, 704/255, 704/257, 704/270
• US Class Current: 704/255
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 25/24 the extracted parameters being the cepstrum
• CPC Class Codes: H03M 7/3082 Vector coding for television signals, see H04N19/94

Abstract

One embodiment of the invention provides television viewers with an intuitive and easy-to-use way to find the programs they want and to control their television viewing experience. In a further embodiment, a speech control interface, in combination with a variety of search functions, is provided such that television viewers have an intuitive and easy-to-use way to find the programs and information they want. The invention also provides the use of personalization as a way to filter and deliver relevant content and services to users based upon individual preferences. Another aspect of the invention provides a hierarchical user interface for speech-controlled, interactive applications, that gives television viewers an intuitive and easy-to-use way to find the programs they want and to control their television viewing experience. The invention also provides a method and apparatus where the channel lineup in a television service is dynamic and changeable, i.e. the list of available channels can be modified, in real time, to suit the preferences and usage of a particular subscriber. Further, the invention provides a method and apparatus that addresses the use of speaker, group, language, or emotional state identification systems to target advertising, to users who are or are not enrolled in a speaker ID system.

Claims

1. A method for linking grammars into a hierarchy of operations, comprising the steps of:

establishing various grammars each grammar including various utterances and, for each utterance, the following associated attributes;

(1) an indication of whether the utterance is explicitly chained to a further grammar, or (2) contextual information indicating a type of data implicitly specified by the utterance;

where each one of the various grammars further includes, for each utterance that is explicitly chained to a further grammar, a chained command attribute identifying the further grammar for activating responsive to a user issuing that utterance while said further grammar is activated for speech recognition;

where the various grammars include command grammars and information-type grammars, and;

utterances in the command grammars form commands to control a manner of presenting video programs;

utterances in the information-type grammars form keywords pertaining to content of video programs;

accepting a statement comprising a series of uninterrupted user utterances containing more than one user command for controlling a video program; and

performing a series of operations by activating a chained series of one or more grammars recognized from the statement, wherein for each grammar that contains a user utterance that is explicitly chained to a further grammar, activating the further grammar; and

for each grammar that contains a user utterance having contextual information associated within, determining which options to make available to user next, thus activating a further grammar based on the contextual information of a preceding grammar, wherein the further grammar at least partially includes the options.

2. The method of claim 1, further comprising operations responsive to receiving an utterance in a given information-type grammar while said given grammar is activated for speech recognition, comprising:

if said given grammar lacks an indication that the utterance is explicitly chained to a further grammar, processing said utterance based on (1) application context of a user-driven system for presenting video programs and (2) type of data specified by the received utterance according to the given grammar.

3. The method of claim 1, the type of data indicated by the contextual information in information-type grammars is selected from among program name, genre, actor, director, writer, episode, date, popularity, quality rating, subject matter rating.

4. The method of claim 1, wherein the utterances comprise user defined preference settings.

5. The method of claim 4, wherein the user defined preference settings are selected from among a subset of program categories, a popularity requirement, a parental-warning type rating, and a quality requirement.

6. The method of claim 1, further comprising:

deducing predicted preferences from the various utterances, wherein the predicted preference settings are defined by processes selected from among a viewing pattern analysis, a user profile analysis, an analysis of user behavior relating to frequency of content requests by way of utterance.

7. The method of claim 6, wherein the predicted preference settings are added to a user defined preference setting.