System and method for context aware audio enhancement
Contact centers strive to provide a positive and productive customer-agent interaction to successfully resolve the issue for a call. While audio content, such as music or messages, on hold are commonplace, selecting audio enhancements to be inserted into, and concurrently with, the customer-agent provides the customer and/or agent with cues and motivations to promote the successful completion of the call. Cues may be provided to announce the arrival or departure of an agent, virtually take a customer from one location to another for a different portion of the interaction, add excitement and anticipation to an upcoming event by providing an audio experience foreshadowing of the actual event, calm frayed nerves, or other purpose.
1. A system, comprising:
a network interface to a network; and
a processor configured with machine-readable instructions maintained in a non-transitory storage that cause the processor to perform:
monitoring a communication between an agent, utilizing an agent communication device, and a customer, utilizing a customer communication device, wherein the communication comprises encoded audio signals transmitted over the network;
accessing a purpose of the communication;
selecting an audio enhancement comprising an audio, from a plurality of audio enhancements, which corresponds to a purpose of the communication; and
overlapping the audio enhancement with speech from the agent in the communication to comprise a portion of the encoded audio signals and wherein
the speech from the agent is presented to the customer communication device.
2. The system of claim 1 , wherein the encoded audio signals comprise the audio enhancement concurrently with speech from the customer.
3. The system of claim 1 , wherein the audio enhancement further comprises an attribute of the audio enhancement comprising at least one of volume, tempo, pace, pitch, fade-in rate, fade-out rate, maximum volume, or minimum volume.
4. The system of claim 1 , wherein the instructions further cause the processor to perform:
accessing the purpose of the communication further comprising determining a current emotion of the customer, the current emotion being an apparent emotion presented by the customer during the communication;
determining a desired emotion for the customer; and
selecting the audio enhancement corresponding to an emotion mitigating attribute previously determined to result in a subject having the current emotion to transition to having the desired emotion.
5. The system of claim 1 , wherein the instructions cause the processor to select the audio enhancement further comprising causing the processor to select the audio enhancement in accordance with a demographic attribute of the customer.
6. The system of claim 1 , wherein the instructions further cause the processor to perform:
accessing the purpose of the communication further comprising causing the customer to perform a task; and
selecting the audio enhancement corresponding to an associated sound of the task.
7. The system of claim 1 , wherein the audio enhancement is provided to one of the customer communication device or the agent communication device and not both.
8. The system of claim 1 , wherein the instructions further cause the processor to perform:
monitoring a second portion of the communication between the agent and the customer, the second portion of the communication occurring concurrently with overlapping of the audio enhancement;
updating the purpose of the communication in accordance with content of the communication provided by the customer; and
upon determining the content of the communication provided by the customer is in conflict with the audio enhancement, modifying the audio enhancement.
9. The system of claim 8 , wherein the instructions cause the processor to modify the audio enhancement comprising one or more of terminating overlapping of the audio enhancement, altering the content of the audio enhancement, altering a pace of the audio enhancement, altering a volume of the audio enhancement, or altering a pitch of the audio enhancement.
10. A system, comprising:
a network interface to a network; and
a processor configured with machine-readable instructions maintained in a non-transitory storage that cause the processor to perform:
monitoring a communication between an agent, utilizing an agent communication device, and a customer, utilizing a customer communication device, wherein the communication comprises encoded audio signals transmitted over the network;
accessing a purpose of the communication;
providing the purpose of the communication to a neural network trained to select an audio enhancement comprising an audio, from a plurality of audio enhancements, which corresponds to a purpose of the communication;
obtaining, from the neural network, the audio enhancement; and
overlapping the audio enhancement with speech from the agent into the communication to comprise a portion of the encoded audio signals and wherein the speech from the agent is presented to the customer communication device.
11. The system of claim 10 , wherein the neural network is trained to select the audio enhancement, further comprising:
accessing a set of past communications between a number of previous customers and a corresponding number of previous agents;
applying one or more transformations to each past communication of the set of past communications including one or more of substituting a word with a synonymous word, substituting a word with a synonymous phrase, substituting a purpose of the communication for an object associated with the purpose, substituting the object associated with the purpose of the communication with a purpose, inserting at least one redundant word, or removing at least one redundant word to create a modified set of past communications;
creating a first training set comprising the set of past communications, the modified set of past communications, and a set of different purposes previously determined to be unrelated to the purpose;
training the neural network in a first state using the first training set;
creating a second training set for a second state of training comprising the first training set and the set of different purposes previously determined to be unrelated to the purpose that are incorrectly identified as being related to the purpose; and
training the neural network in the second state of training using the second training set.
12. The system of claim 11 , wherein the audio enhancement further comprises an attribute of the audio enhancement comprising at least one of volume, tempo, pace, pitch, fade-in rate, fade-out rate, maximum volume, or minimum volume.
13. The system of claim 11 , wherein the instructions further cause the processor to perform:
accessing the purpose of the communication further comprising determining a current emotion of the customer, the current emotion being an apparent emotion presented by the customer during the communication;
determining a desired emotion of the customer; and
modifying the purpose to comprise transitioning the customer to have the desired emotion.
14. The system of claim 11 , wherein the instructions cause the processor to select the audio enhancement further comprising causing the processor to select the audio enhancement in accordance with a demographic attribute of the customer.
15. The system of claim 11 , wherein the instructions further cause the processor to perform:
accessing the purpose of the communication further comprising causing the customer to perform a task; and
selecting the audio enhancement corresponding to an associated sound of the task.
16. The system of claim 11 , wherein the audio enhancement is provided to one of the customer communication device or the agent communication device and not both.
17. The system of claim 11 , wherein the instructions further cause the processor to perform:
monitoring a second portion of the communication between the agent and the customer, the second portion of the communication occurring concurrently with overlapping of the audio enhancement;
updating the purpose of the communication in accordance with content of the communication provided by the customer; and
upon determining the content of the communication provided by the customer is in conflict with the audio enhancement, modifying the audio enhancement.
18. The system of claim 17 , wherein the instructions cause the processor to modify the audio enhancement comprising one or more of terminating overlapping of the audio enhancement, altering the content of the audio enhancement, altering a pace of the audio enhancement, altering a volume of the audio enhancement, or altering a pitch of the audio enhancement.
19. A method, comprising:
monitoring a communication between an agent, utilizing an agent communication device, and a customer, utilizing a customer communication device, wherein the communication comprises encoded audio signals transmitted over a network;
accessing a purpose of the communication;
selecting an audio enhancement comprising an audio, from a plurality of audio enhancements, which
corresponds to a purpose of the communication; and
overlapping the audio enhancement with speech from the agent into the communication to comprise a portion of the encoded audio signals and wherein the speech from the agent is presented to the customer communication device.
20. The method of claim 19 , wherein the audio enhancement further comprises an attribute of the audio enhancement comprising at least one of volume, tempo, pace, pitch, fade-in rate, fade-out rate, maximum volume, or minimum volume.