Evaluation of voice communications
View Patent ↗One-to-many comparisons of callers' words and/or voice prints with known words and/or voice prints to identify any substantial matches between them. When a customer communicates with a particular entity, such as a customer service center, the system makes a recording of the real-time call including both the customer's and agent's voices. The system segments the recording to extract different words, such as words of anger. The system may also segment at least a portion of the customer's voice to create a tone profile, and it formats the segmented words and tone profiles for network transmission to a server. The server compares the customer's words and/or tone profiles with multiple known words and/or tone profiles stored on a database to determine any substantial matches. The identification of any matches may be used for a variety of purposes, such as providing representative feedback or customer follow-up.
1. A method, comprising:
receiving, by a computing system, an electronic representation of a voice communication of a user;
extracting, by the computing system, at least a portion of the electronic representation, to form a voice print;
determining, by the computing system, a tone profile of the voice print;
initiating an action associated with the voice communication in response to determining that the tone profile matches a stored tone profile that is associated with one or more levels of customer satisfaction; and
modifying the one or more levels of customer satisfaction associated with the stored tone profile based on a survey response from the user that indicates a level of customer satisfaction of the user.
2. The method of claim 1 , wherein the action includes scheduling a follow-up communication with the user.
3. The method of claim 1 , wherein the action includes altering a survey response of the user.
4. The method of claim 1 , wherein the action includes asserting a signal to indicate that the voice communication is becoming negative in tone.
5. The method of claim 1 , wherein the action includes rating a customer service representative involved in the voice communication.
6. The method of claim 1 , wherein the initiating the action is further performed in response to determining that the voice communication includes one or more words associated with one of the emotional states.
7. The method of claim 6 , further comprising comparing the one or more words with one or more known words using at least one of:
a Gaussian Mixture Model, voice recognition analysis, tone segmentation, fundamental frequency information, vocal energy information, frequency spectral analysis, formant analysis, linear predictive coding, neural network analysis, ensembles of classifiers analysis, spectral analysis, or signal amplification.
8. The method of claim 6 , further comprising tracking a number of words during the voice communication that are associated with one or more predetermined classifications of words.
9. A non-transitory computer-readable medium having instructions stored thereon that are executable by a computing device to perform operations comprising:
receiving an electronic representation of a voice communication of a user;
extracting at least a portion of the electronic representation, to form a user voice print;
determining a tone profile of the user voice print;
initiating an action associated with the voice communication in response to determining that the tone profile matches a stored tone profile that is associated with one or more levels of customer satisfaction; and
modifying the one or more levels of customer satisfaction associated with the stored tone profile based on a survey response from the user that indicates a level of customer satisfaction of the user.
10. The non-transitory computer-readable medium of claim 9 , wherein the operations further comprise segmenting at least a portion of the electronic representation to separate a voice of the user from a voice of another individual in the voice communication.
11. The non-transitory computer-readable medium of claim 9 , wherein the action includes providing feedback to a customer service representative involved in the voice communication.
12. The non-transitory computer-readable medium of claim 11 , wherein the feedback includes outputting at least one of: a screen change, an audible signal, an electronic signal, or a print message.
13. The non-transitory computer-readable medium of claim 9 , wherein the operations further comprise storing tone profile information associated with emotional states that include at least one of: unsatisfied, angry, confused, unhappy, or disappointed.
14. The non-transitory computer-readable medium of claim 9 , wherein the action includes indicating that the user matches a voice print associated with previous attempted fraudulent transactions.