Method and system for linguistic command processing in a video server network

• US 5,832,439 A
• Filed: 12/14/1995
• Issued: 11/03/1998
• Est. Priority Date: 12/14/1995
• Status: Expired due to Term

• Current Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Original Assignee: MediaOne Group Inc. (Comcast Corporation), U S West Inc.
• Inventors: Bauer, Paul M., Mueller, Hans-Peter, Cox, Louis A. Jr.
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/572,095
• Time in Patent Office: 1,055 Days
• Field of Search: 395/2.4, 395/2.59, 395/2.58, 395/2.64, 395/2.63, 395/2.79, 395/2.84, 704/275, 704/231, 704/250, 704/255, 704/254, 704/270, 704/257
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A method for providing a user with the facility to linguistically direct a computer system to present desired audio/video programming is provided. The method is intended to be used in conjunction with a computer system having an input device, an audio interface, a controller, and a monitor. The method begins with the step of presenting to a user a menu of options at the monitor. The method continues with the step of identifying a set of key phonemes including phonemes associated with the menu of options. The method next includes the step of receiving at the audio interface a command signal representing a linguistic audio command. The command signal is then converted into a command phoneme which is matched with a phoneme of the set of key phonemes. Finally, the controller performs a task associated with the matched phoneme.

Claims

1. A method for use with a computer system having an audio input device, an audio interface, a set top terminal, a video server in communication with the set top terminal via a computer network, and a monitor remotely located from the video server, the method providing a user with the facility to linguistically direct the computer system to present desired audio/video programming from the video server onto the monitor, the method comprising:

presenting a menu of options at the monitor for a user to obtain desired audio/video programming from the video server onto the monitor;

identifying at the audio interface a set of key phonemes including phonemes associated with the menu of options on the monitor, wherein the set of key phonemes includes demi-phonemes and key phonemes associated with the options of sub-menus, wherein the options correspond to videos stored on the video server and virtual Video Cassette Recorder (VCR) functions;

receiving at the audio interface via the audio input device a command signal representing a linguistic audio command of the user;

converting at the audio interface the command signal into a command phoneme;

matching at the audio interface the command phoneme with a phoneme of the set of key phonemes to identify a matched phoneme;

providing a control signal indicative of the matched phoneme from the audio interface to the set top terminal;

processing the control signal indicative of the matched phoneme at the set top terminal; and

presenting a video associated with the matched phoneme from the video server onto the monitor in accordance with a command signal from the set top terminal.

2. The method of claim 1 further comprising:

performing virtual VCR functions associated with the matched phoneme to the video presented onto the monitor using the set top terminal.

3. A computer system for providing a user with the facility to linguistically direct the computer system to present desired audio/video programming, the computer system comprising:

an audio input device;

a video server;

a monitor remotely located from the video server for presenting a menu of options to a user to obtain desired audio/video programming from the video server;

an audio interface operative to identify a set of key phonemes including phonemes associated with the menu of options on the monitor, wherein the set of key phonemes includes demi-phonemes and key phonemes associated with the options of submenus, wherein the options correspond to videos stored on the video server and virtual Video Cassette Recorder (VCR) functions, the audio interface further operative to receive from the audio input device a command signal representing a linguistic audio command of the user, convert the command signal into a command phoneme, match the command phoneme with a phoneme of the set of key phonemes to identify a matched phoneme, and generate a control signal indicative of the matched phoneme; and

a set top terminal, in communication with the audio interface and the video server via a computer network, for processing the control signal indicative of the matched phoneme and then presenting a video associated with the matched phoneme from the video server onto the monitor.

4. The system of claim 3 wherein:

the set top terminal is further operative to perform virtual VCR functions associated with the matched phoneme to the video presented onto the monitor.