System and method for determining the compliance of agent scripts

1. A method of script identification in audio data, the method comprising:

obtaining audio data;

segmenting the audio data into a plurality of utterances;

obtaining a plurality of script models, each script model ben a data structure including a series of connected nodes, each connected node representing a word in a script text and a set of alternative nodes connected to nodes in the series of connected nodes, each alternative, node representing a compliant word variation to the script text;

decoding the plurality of utterances, wherein decoding the plurality of utterances comprises applying each of the plurality of script models to each of the plurality of utterances and producing an indication of which of the script models are identified in the plurality of utterances;

for each of the script models identified, determining if the audio data is non-compliant; and

for each determined non-compliant audio data, initiating at least one remedial action that is selected from a graphical display to present on screen guidance to a customer service agent.

2. The method of claim 1 , further comprising:

filtering the plurality of utterances to include only utterances attributed to a customer service agent;

extracting acoustic features from the filtered plurality of utterances; and

using the extracted acoustic features in decoding the plurality of utterances.

3. The method of claim 1 , wherein if any of the plurality of script models are determined to have occurred in the audio data, further comprising:

transcribing the utterance containing the script to produce an utterance transcription;

comparing the script text to the utterance transcription; and

determining a script accuracy.

4. The method of claim 3 , further comprising evaluating a compliance of the audio data with a script requirement threshold by comparing the script accuracy to the script requirement threshold.

5. The method of claim 1 , wherein the audio data is an instance of an exchange including at least one customer service agent.

6. The method of claim 1 , wherein at least one of the plurality of utterances consists of more than a single word.

7. The method of claim 1 , wherein each script model includes one or more alternative nodes as compliant variations of the script text.

8. A non-transitory computer readable medium comprising computer readable code on a system that upon execution by a computer processor causes the system to:

obtain audio data;

segment the audio data into a plurality of utterances;

obtain a plurality of script models, each script model being a data structure including a series of connected nodes, each connected node representing a word in a script text and a set of alternative nodes connected to nodes in the series of connected nodes each alternative node re resenting a compliant word variation to the script text;

decode the plurality of utterances, wherein decoding the plurality of utterances comprises applying each of the plurality of script models to each of the plurality of utterances and producing an indication of which of the script models are identified in the plurality of utterances;

for each of the script models identified, determine if the audio data is non-compliant; and

for each determined non-compliant audio data, initiate at least one remedial action that is selected from a graphical display to present on screen guidance to a customer service agent.

9. The non-transitory computer readable medium of claim 8 , further causing the system to:

filter the plurality of utterances to include only utterances attributed to a customer service agent;

extract acoustic features from the filtered plurality of utterances; and

use the extracted acoustic features in decoding the plurality of utterances.

10. The non-transitory computer readable medium of claim 8 , wherein if any of the plurality of script models are determined to have occurred in the audio data, further causing the system to:

transcribe the utterance containing the script to produce an utterance transcription;

compare the script text to the utterance transcription; and

determine a script accuracy.

11. The non-transitory computer readable medium of claim 10 , further causing the system to evaluate a compliance of the audio data with a script requirement threshold by comparing the script accuracy to the script requirement threshold.

12. The non-transitory computer readable medium of claim 8 , wherein the audio data is an instance of an exchange including at least one customer service agent.

13. The non-transitory computer readable medium of claim 8 , wherein at least one of the plurality of utterances consists of more than a single word.

14. The non-transitory computer readable medium of claim 8 , wherein each script model includes one or more alternative nodes as compliant variations of the script text.

15. A system for identification of a script in audio data, the system comprising:

an audio data source;

a script model database comprising a plurality of script models each script model being a data structure including a series of connected nodes, each connected node representing a word in a script text and a set of alternative nodes connected to nodes in the series of connected nodes, each alternative node representing a compliant word variation to the script text; and

a processing system communicatively connected to the script model database and the audio data source, the processing system:

obtains audio data,

segments the audio data into a plurality of utterances,

obtains a plurality of script models,

decodes the plurality of utterances, wherein decoding the plurality of utterances comprises applying each of the plurality of script models to each of the plurality of utterances and producing an indication of which of the script models are identified in the plurality of utterances,

for each of the script models identified, determines if the audio data is non-compliant, and

for each determined non-compliant audio data, initiates at least one remedial action that is selected from a graphical display to present on screen guidance to a customer service agent.

16. The system of claim 15 , wherein the processing system further:

filters the plurality of utterances to include only utterances attributed to a customer service agent,

extracts acoustic features from the filtered plurality of utterances, and

uses the extracted acoustic features in decoding the plurality of utterances.

17. The system of claim 15 , wherein if any of the plurality of script models are determined to have occurred in the audio data, the processing system further:

transcribes the utterance containing the script to produce an utterance transcription,

compares the script text to the utterance transcription, and

determines a script accuracy.

18. The system of claim 17 , wherein the processing system further evaluates a compliance of the audio data with a script requirement threshold by comparing the script accuracy to the script requirement threshold.

19. The system of claim 15 , wherein the audio data is an instance of an exchange including at least one customer service agent.

20. The system of claim 15 , wherein at least one of the plurality of utterances consists of more than a single word.