Providing automated voice responses with variable user prompting
First Claim
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.
6 Assignments
0 Petitions
Accused Products
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.
-
Citations
18 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
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. - View Dependent Claims (12, 13, 14)
-
-
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. - View Dependent Claims (16, 17, 18)
-
Specification