IVR engagements and upfront background noise
Embodiments of the present invention pertain to reducing or eliminating speech recognition error when background noise is detected at a caller's location. For example, when background noise is detected at the caller's location, the caller may be prompted to use dual-tone multi-frequency (DTMF).
1. An apparatus, comprising:
memory comprising a set of instructions; and
at least one processor;
wherein the set of instructions, when executed by the at least one processor, are configured to cause the apparatus to:
listen to background noise from a location of a call;
in response to listening to the background noise:
play a welcome message to a caller;
discontinue listen to background noise from the location of the call;
determine whether a sufficient degree of background noise at the location of the call would make speech recognition impossible based on decibels of the background noise; and
prompt the caller to use dual-tone multi-frequency (DTMF) based on the decibels of the background noise.
2. The apparatus of claim 1 wherein the set of instructions, when executed by the at least one processor, are configured to cause the apparatus to listen for the background noise at the location of the caller.
3. The apparatus of claim 1 wherein the set of instructions, when executed by the at least one processor, are configured to cause the apparatus to listen for the background noise at the location of the caller when a call is received.
4. The apparatus of claim 3 , wherein the set of instructions, when executed by the at least one processor, are configured to cause the apparatus to instruct the caller to use speech recognition during the call when the background noise is not excessive.
5. The apparatus of claim 3 , wherein the set of instructions, when executed by the at least one processor, are configured to cause the apparatus to determine whether a speech recognition error occurred during the call.
6. The apparatus of claim 3 , wherein the set of instructions, when executed by the at least one processor, are configured to cause the apparatus to instruct the caller to use the DTMF when a speech recognition error is detected during the call.
7. The apparatus of claim 1 wherein the set of instructions, when executed by the at least one processor, are configured to cause the apparatus to prompt the caller to use the DTMF when the decibels of the background noise are determined to be excessive.
8. A computer-implemented method, comprising:
listening to background noise from a location of a call;
in response to listening to the background noise:
playing a welcome message to a caller;
discontinue listening to background noise from the location of the call;
determining whether a sufficient degree of background noise at the location of the caller would make speech recognition impossible based on decibels of the background noise; and
prompting, by the computing system, the use of dual-tone multi-frequency (DTMF) when the decibels of the background noise are excessive.
9. The computer-implemented method of claim 8 , further comprising listening, by a computing system, for the background noise at the location.
10. The computer-implemented method of claim 9 , further comprising listening, by a computing system, for the background noise at the location when a call is received.
11. The computer-implemented method of claim 10 , further comprising instructing a caller, by the computing system, to use speech recognition during the call when the background noise is not excessive.
12. The computer-implemented method of claim 10 , further comprising determining, by the computing system, whether a speech recognition error occurred during the call.
13. The computer-implemented method of claim 10 , further comprising instructing a caller, by the computing system, to use the DTMF when a speech recognition error is detected during the call.
14. The computer-implemented method of claim 10 , further comprising instructing a caller, by the computing system, to use the DTMF when the signal strength of the background noise is determined to be excessive.
15. A computer program embodied on a non-transitory computer-readable medium, the computer program configured to cause at least one processor to:
listen to background noise from a location of a call;
in response to listening to the background noise:
play a welcome message to a caller;
discontinue listen to background noise from the location of the call;
determine whether a sufficient degree of background noise at the location of the call would make speech recognition impossible based on decibels of the background noise; and
prompt the caller to use dual-tone multi-frequency (DTMF) when the decibels of the background noise are excessive.
16. The non-transitory computer-readable medium of claim 15 , wherein the computer program is further configured to cause the at least one processor to listen for background noise at the location of the caller.
17. The non-transitory computer-readable medium of claim 15 , wherein the computer program is further configured to cause the at least one processor to listen for background noise at the location of the caller when a call is received.
18. The non-transitory computer-readable medium of claim 17 , wherein the computer program is further configured to cause the at least one processor to instruct the caller to use speech recognition during the call when the background noise is not excessive.
19. The non-transitory computer-readable medium of claim 17 , wherein the computer program is further configured to cause the at least one processor to determine whether speech recognition error occurred during the call.
20. The non-transitory computer-readable medium of claim 15 , wherein the computer program is further configured to cause the at least one processor to instruct the caller to use the DTMF when a speech recognition error is detected during the call.