Speech recognition front end controller to voice mail systems

• US 6,601,031 B1
• Filed: 07/28/2000
• Issued: 07/29/2003
• Est. Priority Date: 01/13/2000
• Status: Expired due to Term

• Current Assignee: Gemalto SA (Thales SA)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: OʼBrien, Stephen Anthony
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/627,286
• Time in Patent Office: 1,096 Days
• Field of Search: 704/270, 704/275, 704/270.1, 379/88.01, 379/88.02, 379/88.04, 379/88.22, 379/88.23, 379/88.18, 379/389, 379/67.1
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/533 Voice mail systems
• CPC Class Codes: H04M 3/53383 Message registering commands or announcements; Greetings

Abstract

A speech recognition system front end interface to provide a subscriber voice control over many voice mail functions. The speech recognition system converts spoken instructions into DTMF instructions for voice mail systems while allowing prompts form the voice mail system and DTMF tones from the subscriber to pass through without any interference by the speech recognition system. To accomplish these pass through functions, the speech recognition system sets up what is know as a hairpin connection between the subscriber, the speech recognition system and the voice mail system.

Claims

1. An apparatus, comprising:

an input that receives speech commands over a network from a station set of a subscriber, said speech commands controlling a service being provided by a service unit with at least part of the service operation being controlled by control signals sent across the network;

a speech recognition unit, coupled to said input, that converts the speech commands into control signals;

an output that transmits the control signals over a public switched telephone network to the service unit that is located remote from the speech recognition unit;

wherein the commanded service function is delivered from the service unit through the network, through the speech recognition unit and subsequently to the station set of the subscriber.

2. The apparatus of claim 1, wherein said speech commands are converted into DTMF signals, which are the control signals.

3. The apparatus according to claim 1 further comprising a mechanism providing a hairpin call connection between the input and output at said speech recognition system such that the speech recognition system listens to the subscriber and at the same time the subscriber listens to the voice mail system.

4. A method for controlling a voice mail system comprising the steps of:

a. receiving a call from a subscriber over a public telecommunication network at a system providing speech recognition services and collecting a caller ID;

b. initiating another call to a voice mail system subscribed to by the subscriber based upon the caller ID, the another call originated by the system providing speech recognition services and placed over the public telecommunication network;

c setting up a hairpin call connection between the call and the another call at said speech recognition system such that the speech recognition system listens to the subscriber; and

at the same time the subscriber listens to the voice mail system;

d. said speech recognition system converting speech commands received from the subscriber into control signals;

e transmitting the control signals over a public switched telephone network to the voice mail system that is located remote from the speech recognition system.

5. The method of claim 4 wherein the control signals comprise DTMF signals.

6. The method of claim 4 further comprising the step of receiving by the speech recognition system a personal identification number spoken by the subscriber and recognizing the personal indentification number by the speech recognition system.

7. A method for providing a speech recognition interface for a voice mail system comprising the steps of:

receiving a call at a speech recognition system speech commands from a subscriber transmitted over a telecommunication network;

translating the speech commands at the speech recognition system into control signals adapted for controlling the voice mail system;

originating another call from the speech recognition system to the voice mail system over the telecommunication network

transmitting from the speech recognition system the control signals via the another call over the telecommunication network to the voice mail system.

8. The method according to claim 7 further comprising the step of establishing a hairpin call connection between the call and the another call through the telecommunication network so that the speech recognition system receives communications from the subscriber while simultaneously transmitting information from the voice mail system to the subscriber.

9. The method according to claim 7 further comprising the step of terminating a telephone call by the subscriber to the speech recognition system.

10. The method according to claim 7 wherein said translating step comprises identifying valid spoken commands that correspond to control signals understood by the voice mail system, and upon identifying a valid spoken command converting it into a DTMF signal that corresponds to the spoken command.

11. The method according to claim 8 wherein said translating step comprises identifying valid spoken commands that correspond to control signals understood by the voice mail system, and upon identifying a valid spoken command converting it into a DTMF signal that corresponds to the spoken command.