Multi-party conversation analyzer and logger
View Patent ↗In one aspect, the present invention facilitates the investigation of networks of criminals, by gathering associations between phone numbers, the names of persons reached at those phone numbers, and voice print data. In another aspect the invention automatically detects phone calls from a prison where the voiceprint of the person called matches the voiceprint of a past inmate. In another aspect the invention detects identity scams in prisons, by monitoring for known voice characteristics of likely imposters on phone calls made by prisoners. In another aspect, the invention automatically does speech-to-text conversion of phone numbers spoken within a predetermined time of detecting data indicative of a three-way call event while monitoring a phone call from a prison inmate. In another aspect, the invention automatically thwarts attempts of prison inmates to use re-dialing services. In another aspect, the invention automatically tags audio data retrieved from a database, by steganographically encoding into the audio data the identity of the official retrieving the audio data.
1. A method of detecting suspicious voice communications between an inmate of a controlled-environment facility and a non-inmate, comprising:
monitoring the voice communication between the inmate and the non-inmate,
detecting one or more sounds within the monitored voice conversation that are indicative of suspicious behavior, wherein the sounds are detected based on spectral analysis of the monitored voice conversation;
calculating a suspiciousness score for the monitored voice communication based on the detected suspicious sounds, wherein the calculation of the suspiciousness score is based on a weighting of each of the detected suspicious sounds according to a type of each of the detected suspicious sounds, wherein the calculation of the suspiciousness score is further based on a classification of the inmate;
alerting a call control official if the calculated suspiciousness score indicates a suspicious voice communication is detected;
providing a graphical user interface configured to allow the call control official to confirm the detected suspicious sounds as being suspicious; and
adjusting the suspiciousness score for the monitored voice communication based on the confirmation by the call control official via the user interface.
2. The method of claim 1 , further comprising logging the detected suspicious sounds in a database.
3. The method of claim 1 , wherein the suspicious sounds comprise a phone number spoken within thirty seconds of detecting a potential three-way call event in the monitored voice communication.
4. The method of claim 1 , wherein the weighting of each of the detected suspicious sounds is adjusted based on the classification of the inmate.
5. The method of claim 1 , wherein the confirmation of the detected suspicious sounds by the call control official is used to adjust the weight for the type of the detected suspicious sounds, where the adjusted weight is used in monitoring future voice communications for suspicious sounds.
6. A non-transitory computer-accessible storage medium storing program instructions that, when executed by a data processing device, cause the data processing device to implement operations for detecting suspicious voice communications between an inmate of a controlled-environment facility and a non-inmate, the operations comprising:
monitoring the voice communication between the inmate and the non-inmate;
detecting one or more sounds during the monitored call, wherein the detected sounds are indicative of suspicious behavior, wherein the sounds are detected based on spectral analysis of the monitored voice conversation;
calculating a suspiciousness score for the monitored voice communication based on the detected suspicious sounds, wherein the calculation of the suspiciousness score is based on a weighting of each of the detected suspicious sounds according a type of each of the detected suspicious sounds, wherein the calculation of the suspiciousness score is further based on a classification of the inmate; and
alerting a call control official if the calculated suspiciousness score indicates a suspicious voice communication is detected;
providing a graphical user interface configured to allow the call official to confirm the detected suspicious sounds as being suspicious; and
adjusting the suspiciousness score for the monitored voice communication based on the confirmation by the call control official via the user interface.
7. The non-transitory computer-accessible storage medium of claim 6 , wherein the suspicious sounds comprise the detection of a phone number spoken within thirty seconds of detecting a potential three-way call event in the monitored voice communication.
8. The non-transitory computer-accessible storage medium of claim 6 , wherein the weighting of each of the detected suspicious sounds is adjusted based on the classification of the inmate.
9. The non-transitory computer-accessible storage medium of claim 7 , wherein the confirmation of the detected suspicious sounds by the call control official is used to adjust the weight for the type of the detected suspicious sounds, where the adjusted weight is used in monitoring future voice communications for suspicious sounds.
10. A system for detecting suspicious voice communication comprising a processor and a memory coupled to the processor, the memory configured to store program instructions executable by the processor to cause the computer system to:
monitor the voice communication between the inmate and the non-inmate;
detect one or more suspicious sounds during the monitored voice communication, where the detected sounds are indicative of suspicious behavior, wherein the sounds are detected based on spectral analysis of the monitored voice conversation;
calculate a suspiciousness score for the monitored voice communication based on the detected suspicious sounds, wherein the calculation of the suspiciousness score is based on a weighting of each of the detected suspicious sounds according a type of each of the detected suspicious sounds, wherein the calculation of the suspiciousness score is further based on a classification of the inmate; and
alert a call control official if the calculated suspiciousness score indicates a suspicious voice communication is detected;
provide a graphical user interface configured to allow the call official to confirm the detected suspicious sounds as being suspicious;
adjust the suspiciousness score for the monitored voice communication based on the confirmation by the call control official via the user interface.
11. The system of claim 10 , wherein the suspicious sounds comprise the detection of a phone number spoken within thirty seconds of detecting a potential three-way call event in the monitored phone voice communication.
12. The system of claim 10 , wherein the weighting of each of the suspicious sounds is adjusted based on the classification of the inmate.
13. The system of claim 10 , wherein the confirmation of the detected suspicious sounds by the call control official is used to adjust the weight for the type of the detected suspicious sounds, where the adjusted weight is used in monitoring future voice communications for suspicious sounds.
14. The method of claim 1 , wherein the suspicious sounds comprise whispering detected during the voice communication.
15. The method of claim 1 , wherein the suspicious sounds comprise the detection of a new participant in the voice communication.
16. The method of claim 1 , wherein the suspicious sounds comprise the detection of the voice of a specific individual participating in the voice communication.
17. The non-transitory computer-accessible storage medium of claim 6 , wherein the suspicious sounds comprise whispering detected during the voice communication.
18. The non-transitory computer-accessible storage medium of claim 6 , wherein the suspicious sounds comprise the detection of a new participant in the voice communication.
19. The system of claim 10 , wherein the suspicious sounds comprise the detection of a new participant in the voice communication.
20. The system of claim 10 , wherein the suspicious sounds comprise the detection of the voice of a specific individual participating in the voice communication.