System and method for providing hiring recommendations of agents within a call center
View Patent ↗A system and method for providing hiring recommendations of agents within a call center is provided. A voice sample is received from a candidate agent. The voice sample is analyzed by comparing the voice sample with at least one voice model associated with voice characteristics for two or more populations of a trait. One of the populations to which the candidate agent belongs for that trait is identified. A score is assigned to the candidate agent based on the identified population for the trait. A recommendation for hire for the candidate agent is provided based on the assigned score.
1. A system for providing hiring recommendations of agents within a call center, comprising:
a handset to collect a voice sample from a candidate agent;
a spectrum analyzer device to determine within the voice sample voice characteristics comprising at least one of pitch, range of resonance frequencies of vowel, average resonance frequency of particular vowels, spectral tilt, breathiness, creakiness, nasality, speed of words, pause duration and intonation; and
a speech recognition server comprising a central processing unit, memory, an input port that receives the voice sample from the handset, and an output port, wherein the central processing unit is configured to:
compare the voice characteristics from the voice sample with at least one graph comprising voice characteristics for two or more populations of a trait, which are each represented by a curve;
assign a score to the candidate agent by identifying at least a portion of the voice characteristics from the voice sample on the graph based on the comparison, assigning a numerical value to each identified voice characteristic from the voice sample based on the comparison, and summing the numerical values for the identified voice characteristics as the score;
identify one of the populations to which the candidate agent belongs for that trait based on the assigned score; and
provide a recommendation for hire for the candidate agent based on the assigned score and the identified population.
2. A system according to claim 1 , further comprising:
a characteristic module to identify at least one of linguistic and paralinguistic factors within the voice sample during the analysis.
3. A system according to claim 1 , further comprising:
a population module to identify a second population of the trait to which the candidate agent shares voice characteristics.
4. A system according to claim 3 , further comprising:
an inclusion module to determine for each of the population and the further population, a percentage of inclusion with which the candidate agent shares voice characteristics for that population.
5. A system according to claim 1 , further comprising:
a voice characteristic module to increase the score when the voice sample is comparable to the voice model.
6. A system according to claim 1 , further comprising:
a database to store a list of candidate agents recommended for hire and candidate agents not recommended for hire.
7. A system according to claim 1 , further comprising:
a scoring determination module to determine the score based on at least one of a sum of individual scores assigned to each identified voice characteristic and on one or more of a presence and absence of predetermined voice characteristics.
8. A system according to claim 1 , further comprising:
a threshold module to apply a threshold to the score and to provide the recommendation for hire when the score satisfies the threshold.
9. A system according to claim 1 , further comprising at least one of:
a review module to review the recommendation for hire;
a confirmation module to confirm the recommendation for hire; and
an override module to override the recommendation for hire.
10. A system according to claim 1 , further comprising:
a display to provide access to one or more of a recording of the voice sample and the score.
11. A method for providing hiring recommendations of agents within a call center, comprising:
receiving into a call center, a voice sample collected from a candidate agent via a handset;
gathering via a speech recognition server the voice sample from the candidate agent, wherein the server comprises a central processing unit, memory, an input port that receives the voice sample from the handset, and an output port;
measuring via a spectrum analyzer device within the voice sample voice characteristics comprising at least one of pitch, range of resonance frequencies of vowel, average resonance frequency of particular vowels, spectral tilt, breathiness, creakiness, nasality, speed of words, pause duration and intonation and comparing the voice characteristics from the voice sample with at least one graph comprising voice characteristics for two or more populations of a trait, which are each represented by a curve;
assigning a score to the candidate agent by identifying at least a portion of the voice characteristics from the voice sample on the graph based on the comparison, assigning a numerical value to each identified voice characteristic from the voice sample based on the comparison, and summing the numerical values for the identified voice characteristics as the score;
identifying by the server one of the populations to which the candidate agent belongs for that trait based on the assigned score; and
providing by the server a recommendation for hire within the call center for the candidate agent based on the assigned score and the identified population.
12. A method according to claim 11 , further comprising:
identifying at least one of linguistic and paralinguistic factors within the voice sample during the analysis.
13. A method according to claim 11 , further comprising:
identifying a second population of the trait to which the candidate agent shares voice characteristics.
14. A method according to claim 13 , further comprising:
determining for each of the population and the further population, a percentage of inclusion with which the candidate agent shares voice characteristics for that population.
15. A method according to claim 11 , further comprising:
increasing the score when the voice sample is comparable to the voice model.
16. A method according to claim 11 , further comprising:
storing a list of candidate agents recommended for hire and candidate agents not recommended for hire.
17. A method according to claim 11 , further comprising:
determining the score based on at least one of a sum of individual scores assigned to each identified voice characteristic and on one or more of a presence and absence of predetermined voice characteristics.
18. A method according to claim 11 , further comprising:
applying a threshold to the score; and
providing the recommendation for hire when the score satisfies the threshold.
19. A method according to claim 11 , further comprising at least one of:
reviewing the recommendation for hire;
confirming the recommendation for hire; and
overriding the recommendation for hire.
20. A method according to claim 11 , further comprising:
providing a display with access to one or more of a recording of the voice sample and the score.