Voice enabled system for remote access of information

• US 6,404,859 B1
• Filed: 05/06/1999
• Issued: 06/11/2002
• Est. Priority Date: 03/16/1999
• Status: Expired due to Fees

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Hasan, Mohʼd Abdel-Hamid
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US09/306,034
• Time in Patent Office: 1,132 Days
• Field of Search: 379/88.01, 379/88.02, 379/88.04, 379/88.14, 379/88.16, 379/88.22, 379/93.01, 379/93.02, 379/93.03, 704/270, 704/271, 704/272, 704/273, 704/275, 704/277, 709/225, 455/412, 455/413, 455/414, 713/182, 713/184, 713/201, 707/1, 707/9, 707/10
• US Class Current: 379/88.04
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: H04L 63/0227 Filtering policies mail message filtering H04L51/212
• CPC Class Codes: H04L 63/0846 using time-dependent-passwords, e.g. periodically changing passwords
• CPC Class Codes: H04L 63/0853 using an additional device, e.g. smartcard, SIM or a different communication terminal cryptographic mechanisms or cryptographic arrangements for entity authentication involving additional secure or trusted devices H04L9/3234
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/565 Conversion or adaptation of application format or content adding application control or application functional data H04L67/561
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML
• CPC Class Codes: H04W 12/068 using credential vaults, e.g. password manager applications or one time password [OTP] applications
• CPC Class Codes: H04W 4/00 Services specially adapted for wireless communication networks; Facilities therefor
• CPC Class Codes: H04W 4/18 Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals

Abstract

An arrangement for remotely retrieving information from a computer memory over an audio channel includes an audio channel such as a telephone line. A user speaks a command into the audio channel, and it is received at the other end, which is within a private network. Within the private network, the user is authenticated, as by evaluation of a code number or by voice signature. Once authenticated, the user'"'"'s spoken command is applied to a speech recognition arrangement, also within the private network, which converts the spoken command into a computer-executable command. The executable command is applied to the appropriate network memory, and the computer file is retrieved. The retrieved file is applied to a firewall in order to block transmission of any information from the private network which is deemed to be inappropriate for transmission over the audio channel, or which should not leave the private network in computer-readable form. If not blocked, the file is applied to a text-to-speech converter within the-private network, and converted into speech. The speech signals representing the retrieved information are applied to the second end of the audio channel, and transmitted to the user. Thus, computer-readable files do not leave the private network. In a particularly advantageous embodiment, the information is e-mail.

Claims

1. A method for accessing information stored on a remote computer, said method comprising the steps of:

uttering a command into a first end of an audio channel which includes a publicly accessible portion, so that an electronic equivalent of said speech appears at a second end of said audio channel, remote from said first end;

coupling said electronic equivalent of said speech from said second end of said audio channel to a private network which is not accessible to the public;

within said private network, converting said spoken command into an executable command;

within said private network, in response to said executable command, retrieving information identified by said command from computer memory, to thereby generate retrieved information;

applying said retrieved information to a firewall evaluation arrangement within said private network, for determining if said retrieved information is of a type which may be allowed to be transmitted over said audio channel;

if said retrieved information is of a type which may not be allowed to be transmitted over said audio channel, blocking said retrieved information to prevent its leaving said private network, and if said retrieved information is of a type which may be allowed to be transmitted over said audio channel, within said private network, converting said retrieved information into speech representing said retrieved data;

applying said speech representing said retrieved data to said second end of said audio channel, for transmission to said first end of said audio channel.

2. A method according to claim 1, further comprising the step, between said steps of coupling said electronic equivalent of said speech and converting said speech into an executable command, of:

within said private network, authenticating the source of said speech signal, to thereby provide access to said private network.

3. A method according to claim 1, wherein said retrieved information is e-mail.

4. A method according to claim 1, wherein said uttering step includes the step of uttering said command into a first end of an audio channel which includes an air path.

5. An apparatus for remotely accessing, by way of an audio channel, information stored in a computer memory within a private network, said apparatus comprising:

a memory within said private network, on which information to be remotely accessed is stored in files;

an audio communication channel including a first end available to any user and a second end to which user voice commands can be sent;

a speech recognition engine within said private network which, when commanded by a voice, converts voice commands identifying a designated file into an executable command to find said designated file;

file search means within said private network for, in response to said executable command, controllably accessing said designated file in said memory;

information content authenticating means within said private network, said authenticating means being coupled to said memory, for evaluating the information of said designated file, and for passing said designated file only when said designated file contains unrestricted information;

a text-to-speech engine within said private network, said engine being coupled to said information content authenticating means and to said second end of said audio communication channel, for converting the contents of said designated file into speech, and for transmitting said speech to said user.

6. An apparatus according to claim 5, further comprising user authentication means within said private network, said authenticating means being coupled to said second end of said audio communication channel and to said speech recognition engine, for generating a path by which said user voice command can reach said speech recognition engine only when said user is authenticated.

7. An apparatus according to claim 6, wherein said user authentication means comprises:

a clocked pseudorandom generator for generating a time-variant code number;

comparison means coupled to said pseudorandom generator, and also coupled to said second end of said audio channel, for comparing an identification number transmitted from said user to said comparison means over said audio channel with said time-variant code number; and

a second clocked pseudorandom generator available to said user, said second pseudorandom generator being sufficiently similar to said first pseudorandom generator to produce said time-variant code number, whereby said comparison means authenticates said user by comparing said time-variant code number from said first and second pseudorandom generators.

8. An apparatus according to claim 6, wherein said user authentication means comprises a voice authenticator, which processes the voice of said user to establish said authenticity of said user.

9. An apparatus according to claim 6, wherein said user authentication means comprises a PIN authenticating means coupled to a speech passing gate, for passing speech when said PIN is authenticated.

10. An apparatus according to claim 5, wherein said audio communication channel includes an air path.