User display in speech recognition system

• US 6,359,971 B1
• Filed: 08/21/1995
• Issued: 03/19/2002
• Est. Priority Date: 04/06/1994
• Status: Expired due to Term

• Current Assignee: Sound View Innovations, LLC (Sound View Innovation Holdings, LLC)
• Original Assignee: American Telephone & Telegraph Company (AT&T, Inc.)
• Inventors: Haimi-Cohen, Raziel, Reed, Adam Victor
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US08/524,106
• Time in Patent Office: 2,402 Days
• Field of Search: 379/67, 379/88, 379/89, 379/88.01, 379/88.02, 379/88.03, 379/88.04, 395/2.79, 395/2.84, 395/2.85, 381/43, 381/110, 704/270, 704/271, 704/275, 704/276, 704/277
• US Class Current: 379/88.01
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/42204 Arrangements at the exchange for service or number selection by voice at the terminal H04M1/27
• CPC Class Codes: H04M 3/4931 Directory assistance systems

Abstract

A speech recognizer system for use with a telecommunication network wherein an input signal generated onto the network from a first terminal is directed to a speech recognizer for estimating the verbal content of the input signal. The speech recognizer or associated equipment then directs an estimate of the verbal content as an output signal back to the first terminal, the estimate including one or more approximations of the verbal content of the input signal. At the first terminal the user then confirms a correct estimate, or selects from a plurality of approximations, the verbal content of the input signal.

Claims

1. A method of speech recognition in a telecommunication network consisting essentially of the steps of placing an input signal onto the network from a first terminal, estimating the content of the input signal within the network, transmitting an output signal comprising an estimate of the content of the input signal back to the first terminal for confirmation, said estimate comprising more than one approximation of the input signal, and confirming one of the more than one approximation.

2. The method of claim 1 further comprising the step of digitizing the output signal prior to the transmission to the first terminal.

3. The method of claim 1 further comprising visually displaying one or more of the approximations of the content of the input signal at the first terminal.

4. The method of claim 1 wherein the approximations are presented sequentially at the first terminal with a most probable approximation presented first and a successive next most probable alternative presented after said most probable approximation only if the most probable approximation has not been confirmed.

5. The method of claim 1 wherein a plurality of the more than one approximation are simultaneously presented at the first terminal for confirmation.

6. The method of claim 5 wherein the step of confirming one of the more than one approximation comprises activating a means for selecting an approximation.

7. The method of claim 1 further comprising the steps of accessing a database in response to the input signal and providing additional information which relates to the approximations.

8. A method of speech recognition in a telecommunication network consisting of the steps of placing an input signal onto the network from a first terminal, estimating the content of the input signal within the network, transmitting an output signal comprising an estimate of the content of the input signal back to the first terminal for confirmation, said estimate comprising more than one approximation of the input signal, and confirming one of the more than one approximation.

9. A method of speech recognition in a telecommunications network comprising the steps of placing an input signal onto the network from a first terminal, estimating the content of the input signal within the network, determining a presentation capacity available to the first terminal, transmitting an output signal comprising more than one approximation of the content of the input signal consistent with the presentation capacity to the first terminal for confirmation and confirming one of the more than one approximation.

10. The method of claim 9 wherein the step of determining a presentation capacity comprises the steps of prompting the first terminal for the presentation capacity available and transmitting a response to said prompt from the first terminal.

11. A method of speech recognition in a telecommunications network comprising the steps of placing an input signal onto the network from a first terminal, estimating the content of the input signal within the network, transmitting an output signal comprising more than one approximation of the content of the input signal to the first terminal for confirmation, said output signal comprising both visual and aural presentation signals, and confirming one of the more than one approximation.