System and method for three-way call detection
A system for detecting three-way calls in a monitored telephone conversation includes a speech recognition processor that transcribes the monitored telephone conversation and associates characteristics of the monitored telephone conversation with a transcript thereof, a database to store the transcript and the characteristics associated therewith, and a three-way call detection processor to analyze the characteristics of the conversation and to detect therefrom the addition of one or more parties to the conversation. The system preferably includes at least one domain-specific language model that the speech recognition processor utilizes to transcribe the conversation. The system may operate in real-time or on previously recorded conversations. A query and retrieval system may be used to retrieve and review call records from the database.
1. A system for detecting three-way calls in a monitored telephone conversation, the system comprising:
a speech recognition processor that transcribes the monitored telephone conversation and associates at least two characteristics of the monitored telephone conversation with a transcript of the monitored telephone conversation;
a database that stores at least the transcript of the monitored telephone conversation and the at least two characteristics associated therewith; and
a three-way call detection processor that analyzes the at least two characteristics associated with the transcript of the monitored telephone conversation to detect the addition of one or more third parties to the monitored telephone conversation, wherein the at least one characteristic includes at least one network characteristic and one speech characteristic.
2. The system according to claim 1 , further comprising at least one domain-specific language model, and wherein the speech recognition processor utilizes the domain-specific language model to transcribe the monitored telephone conversation.
3. The system according to claim 2 , wherein the at least one domain-specific language model is domain specific to inmate telephony.
4. The system according to claim 2 , wherein the at least one domain-specific language model comprises a plurality of domain-specific language models trained for a plurality of ethnic groups.
5. The system according to claim 2 , wherein the at least one domain-specific language model comprises a plurality of domain-specific language models trained for a plurality of regional dialects.
6. The system according to claim 2 , wherein the at least one domain-specific language model comprises a plurality of domain-specific language models trained for a plurality of foreign languages.
7. The system according to claim 1 , wherein the database further stores a sound recording of the monitored telephone conversation.
8. The system according to claim 1 , wherein the speech recognition processor transcribes the monitored telephone conversation and associates the at least two characteristics with the transcript of the monitored telephone conversation in real-time.
9. The system according to claim 1 , wherein the speech recognition processor comprises a solid-state device.
10. The system according to claim 1 , wherein the at least one network characteristic is selected from the group consisting of: dial tones; dial pulses; ring tones; and the at least one speech characteristic is selected from the group consisting of gaps in conversation; speaker turns; telephone salutations, and verbal cues.
11. The system according to claim 1 , further comprising a translation processor to translate the transcript of one or more of the monitored telephone conversations from a first language into a second language.
12. The system according to claim 1 , wherein the three-way call detection processor assigns a score to the monitored telephone conversation based on the at least two characteristics associated with the transcript thereof, wherein the score is indicative of a likelihood that at least one third party was added to the monitored telephone conversation.
13. The system according to claim 1 , wherein the three-way call detection processor utilizes one or more call-processing algorithms to detect the addition of one or more third parties to the monitored telephone conversation, wherein the one or more call-processing algorithms are selected from the group consisting of: algorithms that measure frequency of phrases uttered during the monitored telephone conversation; algorithms that measure timing of phrases uttered during the monitored telephone conversation; algorithms that extract entities from phrases uttered during the monitored telephone conversation; pattern detection algorithms that compare timings of utterances within the monitored telephone conversation with timings of the at least one characteristic associated therewith; and any combinations thereof.
14. A method of detecting three-way calls in a monitored telephone conversation, comprising:
transcribing the monitored telephone conversation;
extracting a plurality of characteristics of the monitored telephone conversation;
associating the extracted plurality of characteristics with a transcript of the monitored telephone conversation;
utilizing a scoring algorithm to assign a score to the monitored telephone conversation based on the extracted plurality of characteristics, wherein the score is indicative of a likelihood that at least one third party was added to the monitored telephone conversation, wherein the plurality of characteristics includes at least one network characteristic and one speech characteristic; and
generating information regarding addition of a third party to the monitored telephone conversation.
15. The method according to claim 14 , wherein the step of utilizing a scoring algorithm to assign a score to the monitored telephone conversation comprises: identifying one or more characteristics indicative of addition of a third party to the monitored telephone conversation within the extracted plurality of characteristics; and utilizing a scoring function to calculate the score based upon the identified one or more characteristics indicative of addition of a third party.
16. The method according to claim 15 , wherein the scoring function comprises a logistic function.
17. The method according to claim 15 , wherein the scoring function comprises a threshold function.
18. The method according to claim 14 , wherein the step of generating information regarding addition of a third party to the monitored telephone conversation comprises tagging the transcript of the monitored telephone conversation to identify portions of the transcript pertinent to addition of the third party.
19. The method according to claim 14 , wherein the step of generating information regarding addition of a third party to the monitored telephone conversation comprises:
identifying likely beginnings of one or more detected three-way calls in the monitored telephone conversation; and
associating information regarding the identified likely beginnings of the one or more detected three-way calls with one or more of the monitored telephone conversation and the transcript of the monitored telephone conversation.
20. The method of claim 19 , further comprising providing a sound recording of the monitored telephone conversation, wherein the information regarding the identified likely beginnings of the one or more detected three-way calls comprises one or more time points in the sound recording of the monitored telephone conversation where the one or more detected three-way calls begin.
21. The method of claim 19 , wherein the information regarding the identified likely beginnings of the one or more detected three-way calls comprises one or more word- or character-lengths into the transcript of the monitored telephone conversation where the one or more detected three-way calls begin.
22. A method of detecting three-way calls in a monitored telephone conversation, comprising:
transcribing the monitored telephone conversation;
extracting a plurality of characteristics of the monitored telephone conversation, wherein the plurality of characteristics extracted are indicators of a third party being added to the monitored telephone conversation;
calculating a score for the monitored telephone conversation based upon at least two of the plurality of characteristics extracted from the monitored telephone conversation, wherein the score is indicative of a likelihood that at least one third party was added to the monitored telephone conversation, wherein the plurality of characteristics includes at least one network characteristic and one speech characteristic; and
generating information regarding addition of a third party to the monitored telephone conversation.
23. The method according to claim 22 , wherein the step of calculating a score for the monitored telephone conversation based upon at least two of the plurality of characteristics extracted from the monitored telephone conversation comprises calculating a score for the monitored telephone conversation based upon at least three of the plurality of characteristics extracted from the monitored telephone conversation.
24. The method according to claim 22 , wherein the step of calculating a score for the monitored telephone conversation based upon at least two of the plurality of characteristics extracted from the monitored telephone conversation comprises calculating a score for the monitored telephone conversation based upon at least four of the plurality of characteristics extracted from the monitored telephone conversation.
25. A query and retrieval system for monitored telephone conversations, comprising:
a database of monitored telephone conversations including a plurality of call records, wherein at least some of the call records comprise:
a sound recording of the monitored telephone conversation;
a transcript of the monitored telephone conversation; and
a score assigned to the monitored telephone conversation, wherein the score assigned to the monitored telephone conversation reflects a likelihood that the monitored telephone conversation included one or more three-way calls, and wherein the score is based upon one or more characteristics of the monitored telephone conversation indicative of adding a third party thereto, wherein the one or more characteristics includes at least one network characteristic and one speech characteristic;
an query interface that accepts search criteria input by a user, wherein the search criteria include at least a score criterion;
a processor that retrieves one or more call records from the database based upon the search criteria;
a selection interface that permits user selection of a call record from the retrieved one or more call records; and
an output device that provides synchronized playback and visualization, respectively, of the recording and transcript comprising the selected call record.
26. The system according to claim 25 , wherein the output device further provides a visual identification of the one or more characteristics of the monitored telephone conversation indicative of adding a third party thereto.
27. The system according to claim 25 , further comprising an interface that permits direct navigation to one or more three-way calls within the monitored telephone conversation.