Method for selecting interactive voice response modes using human voice detection analysis
View Patent ↗In an interactive voice response system, a method is provided for selective enhancement of voice recognition capability during an interaction. The method includes the acts (a) taking a call and prompting for a voice response from the caller, (b) failing to recognize the response, (c) executing a routine to detect and isolate the captured word or phrase in the response, and (d) attempting to recognize the response a second time.
1. A dual-mode interactive voice response (IVR) system, comprising:
a processor; and
a memory, wherein the memory stores instructions that, when executed by the processor, cause the processor to:
provide an audio message to a caller prompting a selection from among a plurality of selectable options;
receive an audio response signal from the caller;
process the audio response signal for recognizing the selection from among the plurality of selectable options;
separate a human voice pattern from a background noise in the audio response signal in response to not recognizing the selection from among the plurality of selectable options; and
process the human voice pattern for recognizing the selection from among the plurality of selectable options, wherein, after processing the human voice pattern, the instructions further cause the processor to provide an instruction to the caller to provide another audio response signal in response to not recognizing the selection from among the plurality of selectable options.
2. The dual-mode IVR system of claim 1 , wherein the instructions further cause the processor to subtract the background noise from the audio response signal.
3. The dual-mode IVR system of claim 1 , wherein the instructions further cause the processor to execute the selection from among the plurality of selectable options.
4. The dual-mode IVR system of claim 1 , wherein, after processing the human voice pattern, the instructions further cause the processor to initiate a touch tone mode in response to not recognizing the selection from among the plurality of selectable options.
5. The dual-mode IVR system of claim 1 , wherein the instructions further cause the processor to receive an audio communication from the caller prior to providing the audio message.
6. The dual-mode IVR system of claim 1 , wherein the instructions further cause the processor to initiate a communication to the caller as an outbound call.
7. The dual-mode IVR system of claim 1 , wherein the instructions further cause the processor to identify a language used in the audio response signal or the human voice pattern and to provide subsequent output to the caller in the language.
8. The dual-mode IVR system of claim 1 , wherein the instructions further cause the processor to provide a notification to the caller indicating a high level of background noise.
9. The dual-mode IVR system of claim 1 , wherein the instructions further cause the processor to provide subsequent instructions to the caller to select from among the plurality of selectable options using touch tone buttons.
10. A method for enhancing voice recognition in an interactive voice response system, the method comprising:
providing, by a processor, an audio message to a caller prompting a selection from among a plurality of selectable options;
receiving, by the processor, an audio response signal from the caller;
processing, by the processor, the audio response signal for recognizing the selection from among the plurality of selectable options;
separating, by the processor, a human voice pattern from a background noise in the audio response signal in response to not recognizing the selection from among the plurality of selectable options;
processing, by the processor, the human voice pattern for recognizing the selection from among the plurality of selectable options; and after processing the human voice pattern, providing, by the processor, an instruction to the caller to provide another audio response signal in response to not recognizing the selection from among the plurality of selectable options.
11. The method of claim 10 , further comprising subtracting, by the processor, the background noise from the audio response signal.
12. The method of claim 10 , further comprising executing, by the processor, the selection from among the plurality of selectable options.
13. The method of claim 10 , further comprising after processing the human voice pattern, initiating, by the processor, a touch tone mode in response to not recognizing the selection from among the plurality of selectable options.
14. The method of claim 10 , further comprising receiving, by the processor, an audio communication from the caller prior to providing the audio message.
15. The method of claim 10 , further comprising initiating, by the processor, a communication to the caller as an outbound call.
16. The method of claim 10 , further comprising identifying, by the processor, a language used in the audio response signal or the human voice pattern and to provide subsequent output to the caller in the language.
17. The method of claim 10 , further comprising providing, by the processor, a notification to the caller indicating a high level of background noise.
18. The method of claim 10 , further comprising providing, by the processor, subsequent instructions to the caller to select from among the plurality of selectable options using touch tone buttons.