Expected next prompt to reduce response time for a voice system
Various embodiments described herein relate to generating and/or employing an expected next prompt to reduce response time for a voice system. In this regard, a candidate audio signal is generated for a predicted prompt to be presented via a user audio device. Additionally, in response to audio response data provided by the user audio device, the predicted prompt is compared to a prompt associated with the audio response data. In response to a determination that the predicted prompt matches the prompt, the candidate audio signal is presented via the user audio device.
1. A system, comprising:
a processor; and
a memory that stores executable instructions that, when executed by the processor, cause the processor to:
generate multiple predicted prompts based on one or more previous prompts presented to a user audio device;
generate multiple candidate audio signals for the multiple predicted prompts to be presented via the user audio device, wherein the multiple candidate audio signals are generated based on a set of predefined prompt expressions;
compare audio response data for a previous prompt with expected audio response data for the previous prompt;
in response to determining that the audio response data matches the expected audio response data, select a candidate audio signal from the multiple candidate audio signals via the user audio device; and
based on selection of the candidate audio signal from the multiple candidate audio signals, discard one or more other candidate audio signals from the multiple candidate audio signals.
2. The system of claim 1 , wherein the executable instructions further cause the processor to:
generate the multiple candidate audio signals based on historical data associated with the one or more previous prompts.
3. The system of claim 1 , wherein the executable instructions further cause the processor to:
generate the multiple candidate audio signals based on a set of predefined prompts.
4. The system of claim 1 , wherein the executable instructions further cause the processor to:
generate the multiple candidate audio signals based on context data associated with a previously generated prompt for the user audio device.
5. The system of claim 1 , wherein the executable instructions further cause the processor to:
in response to determining that the audio response data does not match the expected audio response data, discard the multiple candidate audio signals and generate a new audio signal based on the audio response data.
6. The system of claim 1 , wherein the user audio device is a wearable device.
7. The system of claim 1 , wherein the user audio device is a headset device.
8. A method, comprising:
generating multiple predicted prompts based on one or more previous prompts presented to a user audio device;
generating multiple candidate audio signals for the multiple predicted prompts to be presented via the user audio device, wherein the multiple candidate audio signals are generated based on a set of predefined prompt expressions;
comparing audio response data for a previous prompt with expected audio response data for the previous prompt;
in response to determining that the audio response data matches the expected audio response data, selecting a candidate audio signal from the multiple candidate audio signals via the user audio device; and
based on selection of the candidate audio signal from the multiple candidate audio signals, discarding one or more other candidate audio signals from the multiple candidate audio signals.
9. The method of claim 8 , further comprising:
generating the multiple candidate audio signals based on historical data associated with the one or more previous prompts.
10. The method of claim 8 , further comprising:
generating the multiple candidate audio signals based on a set of predefined prompt expressions.
11. The method of claim 8 , further comprising:
generating the multiple candidate audio signals based on context data associated with a previously generated prompt for the user audio device.
12. A computer program product comprising at least one non-transitory computer-readable storage medium having program instructions embodied thereon, the program instructions executable by a processor to cause the processor to:
generate multiple predicted prompts based on one or more previous prompts presented to a user audio device;
generate multiple candidate audio signals for the multiple predicted prompts to be presented via the user audio device, wherein the multiple candidate audio signals are generated based on a set of predefined prompt expressions;
compare audio response data for a previous prompt with expected audio response data for the previous prompt;
in response to determining that the audio response data matches the expected audio response data, select a candidate audio signal from the multiple candidate audio signals via the user audio device; and
based on selection of the candidate audio signal from the multiple candidate audio signals, discard one or more other candidate audio signals from the multiple candidate audio signals.