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 a three-way call in a monitored telephone conversation, the system comprising:
one or more circuits configured to:
convert an audio of the monitored telephone conversation to a transcript using a domain specific language model;
detect a predefined utterance within the monitored telephone conversation based on the transcript of the monitored telephone conversation;
perform an audio analysis of the audio, the audio analysis including a frequency analysis, to detect a predefined non-verbal characteristic within the monitored telephone conversation;
determine a proximity of the predefined utterance to the predefined non-verbal characteristic within the monitored telephone conversation;
determine that the monitored telephone conversation includes the three-way call based on the proximity; and
transmitting a signal to a call routing element to connect a third-party monitoring individual to the monitored telephone conversation for intelligence gathering.
2. The system of claim 1 , wherein the predefined utterance is a spoken contact identifier.
3. The system of claim 2 , wherein the spoken contact identifier is a telephone number.
4. The system of claim 1 , wherein the predefined non-verbal characteristic is a dual-tone multi-frequency tone indicative of a phone signaling operation.
5. The system of claim 1 , wherein the predefined non-verbal characteristic is a period of inactivity that is defined by a predetermined length of time without speaking by any telephone conversation participant.
6. The system of claim 1 , wherein the one or more circuits are further configured to tag the transcript with a timestamp at a starting point of the three-way call in the monitored telephone conversation.
7. The system of claim 1 , wherein to convert the audio of the monitored telephone conversation to the transcript using the domain specific language model, the one or more circuits are configured to:
translate the transcript of the monitored telephone conversations from a first language into a second language.
8. A method for detecting a three-way call in a monitored telephone conversation, the method comprising:
converting an audio of the monitored telephone conversation to a transcript using a domain specific language model;
detecting a predefined utterance within the monitored telephone conversation based on the transcript of the monitored telephone conversation;
performing an audio analysis of the audio, the audio analysis including a frequency analysis, to detect a predefined non-verbal characteristic within the monitored telephone conversation;
determining a proximity of the predefined utterance to the predefined non-verbal characteristic within the monitored telephone conversation;
determining that the monitored telephone conversation includes the three-way call based on the proximity; and
transmitting a signal to a call routing element to connect a third-party monitoring individual to the monitored telephone conversation for intelligence gathering.
9. The method of claim 8 , wherein the predefined utterance is a spoken contact identifier.
10. The method of claim 9 , wherein the spoken contact identifier is a telephone number.
11. The method of claim 8 , wherein the predefined non-verbal characteristic is a dual-tone multi-frequency tone indicative of a phone signaling operation.
12. The method of claim 8 , wherein the predefined non-verbal characteristic is a period of inactivity that is defined by a predetermined length of time without speaking by any telephone conversation participant.
13. The method of claim 8 , wherein the one or more circuits are further configured to tag the transcript with a timestamp at a starting point of the three-way call in the monitored telephone conversation.
14. The method of claim 8 , wherein to convert the audio of the monitored telephone conversation to the transcript using the domain specific language model, the one or more circuits are configured to:
translate the transcript of the monitored telephone conversations from a first language into a second language.
15. A non-transitory computer-readable device having instructions stored thereon that, when executed by at least one computing device, causes the at least one computing device to perform operations comprising:
converting an audio of the monitored telephone conversation to a transcript using a domain specific language model;
detecting a predefined utterance within the monitored telephone conversation based on the transcript of the monitored telephone conversation;
performing an audio analysis of the audio, the audio analysis including a frequency analysis, to detect a predefined non-verbal characteristic within the monitored telephone conversation;
determining a proximity of the predefined utterance to the predefined non-verbal characteristic within the monitored telephone conversation;
determining that the monitored telephone conversation includes the three-way call based on the proximity; and
transmitting a signal to a call routing element to connect a third-party monitoring individual to the monitored telephone conversation for intelligence gathering.
16. The non-transitory computer-readable device of claim 15 , wherein the predefined utterance is a spoken contact identifier.
17. The non-transitory computer-readable device of claim 16 , wherein the spoken contact identifier is a telephone number.
18. The non-transitory computer-readable device of claim 15 , wherein the predefined non-verbal characteristic is a dual-tone multi-frequency tone indicative of a phone signaling operation.
19. The non-transitory computer-readable device of claim 15 , wherein the predefined non-verbal characteristic is a period of inactivity that is defined by a predetermined length of time without speaking by any telephone conversation participant.
20. The non-transitory computer-readable device of claim 15 , wherein the one or more circuits are further configured to tag the transcript with a timestamp at a starting point of the three-way call in the monitored telephone conversation.