Providing automated voice responses with variable user prompting

• US 6,385,584 B1
• Filed: 04/30/1999
• Issued: 05/07/2002
• Est. Priority Date: 04/30/1999
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Verizon Services Corporation (Verizon Communications Inc.)
• Inventors: Curry, James E., McAllister, Alexander I.
• Primary Examiner(s): Knepper, David D.
• Application Number:
  US09/302,432
• Time in Patent Office: 1,103 Days
• Field of Search: 704/270-275, 704/257, 340/573.1, 379/10.01
• 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: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/42059 Making use of the calling party identifier
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/4931 Directory assistance systems
• CPC Class Codes: H04M 3/533 Voice mail systems
• CPC Class Codes: H04M 3/54 Arrangements for diverting calls for one subscriber to another predetermined subscriber based on the calling party profile H04M3/42059; based on location H04M3/42348; based on presence H04M3/42365; to voice mail H04M3/53308

Abstract

A voice response unit (VRU) includes a library of content equivalent messages and prompts which may be substituted for one another to vary the presentation of messages provided to a user and thereby more closely simulate a human operator. Groups of content equivalent messages and prompts include multiple audio files, each with a slightly different wording or phraseology, but conveying substantially the same information. After a particular message content is selected, the corresponding group of messages is identified and a random number is generated and used to select one of the audio files of the group for playback. The VRU may be included as part of an automated dialer or auto attendant. In such a system, a calling party is greeted by the VRU and is prompted by a randomly selected prompt to speak the name of the called party. The system accesses a telephone directory, attempts to identify a name corresponding to the name spoken, and dials the number. The caller may interrupt or request alternative processing during a predetermined time period after the system has selected and read back a closest matching name or its corresponding telephone number. If processing is halted by the caller indicating that the name or telephone number selected by the system is incorrect, the system will attempt to identify a second closest guess, or if none is available, to ask the caller to reinput the name of the called party. Alternative processing includes hearing the telephone number without having it dialed, and diverting a call to voice mail.

Claims

1. A voice response unit for responding to spoken commands, comprising:

a memory storing a plurality of voice messages arranged in groups of content equivalent messages, each of the messages of a group having different a wording;

a speech recognition engine receiving a speech input signal and, in response, providing an output signal indicative of said speech input signal;

a processor responsive to (i) said output signal for selecting one of said groups of content equivalent messages and (ii) a pseudorandom number for selecting one of said voice messages within the selected group;

a speech output device providing an audio signal corresponding to the selected voice message stored in said memory.

2. The voice response unit according to claim 1 wherein said processor further includes a pseudorandom number generator supplying said pseudorandom number.

3. The voice response unit according to claim 1 wherein said processor further includes a pseudorandom number generator calculating numeric values falling within a predetermined range, said range divided into a plurality of subranges wherein, within each of said groups of voice messages, each voice message is associated with a different one of said subranges.

4. The voice response unit according to claim 3 wherein said subranges are substantially coextensive and equal in number to a number of voice messages within each of said groups of content equivalent messages.

5. The voice response unit according to claim 3 wherein said numeric values comprise uniform deviates within the predetermined range.

6. The voice response unit according to claim 1 wherein said processor further includes a pseudorandom number generator calculating numeric values falling within a predetermined range wherein, within each of said groups of voice messages, each voice message is associated with a different one of said numeric values.

7. The voice response unit according to claim 1 wherein each of said voice message are stored in said memory in a WAV format.

8. The voice response unit according to claim 1 wherein each of said voice message are stored in said memory in a compressed audio for mat.

9. The voice response unit according to claim 8 wherein said compressed audio format is MPEG Layer 3 (MP3).

10. The voice response unit according to claim 1 further including:

an interface connected to a telephone switch and receiving said speech input signal;

a telephone directory listing subscribers and respective telephone numbers of said subscribers; and

dialing means responsive to a selected one of said telephone numbers for completing a telephone call to a corresponding one of said subscribers, wherein said processor is responsive to said output signal from said speech recognition engine for selecting one of said subscribers and an associated one of said telephone numbers from said telephone directory.

11. A method of responding to spoken commands, comprising the steps of:

storing a plurality of voice messages arranged in groups of content equivalent messages, each of the messages of a group having different a wording;

receiving a speech input signal;

processing said speech signal to recognize a content thereof;

selecting, in response to said content, one of said groups of content equivalent messages;

generating a pseudorandom number;

selecting one of said voice messages within the selected group in response to said pseudorandom number; and

providing an audio signal corresponding to the selected voice message stored in said memory.

12. The method according to claim 11 wherein said storing step includes converting a speech signal into a WAV file.

13. The method according to claim 11 wherein said storing step includes compressing a speech signal to form a compressed speech signal and encoding the compressed speech signal.

14. The method according to claim 13 wherein said encoding step is performed using an MP3 compliant encoding scheme.

15. A computer readable medium containing program instructions stored therein that implement a method of responding to spoken commands, said method comprising the steps of:

storing a plurality of voice messages arranged in groups of content equivalent messages, each of the messages of a group having different a wording;

receiving a speech input signal;

processing said speech signal to recognize a content thereof;

selecting, in response to said content, one of said groups of content equivalent messages;

generating a pseudorandom number;

selecting one of said voice messages within the selected group in response to said pseudorandom number; and

providing an audio signal corresponding to the selected voice message stored in said memory.

16. The computer readable medium according to claim 15 wherein said storing step according to said method includes converting a speech signal into a WAV file.

17. The computer readable medium according to claim 15 wherein said storing step according to said method includes compressing a speech signal to form a compressed speech signal and encoding the compressed speech signal.

18. The computer readable medium according to claim 17 wherein said encoding step according to said method is performed using an MP3 compliant encoding scheme.