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 system for voice identity verification, the system comprising:
means for prompting an inmate, requesting a voice communication with a non-inmate, to speak the inmate's name,
means for prompting the inmate to speak the name of said non-inmate,
means for generating a voice model for the non-inmate based on the spoken name of the non-inmate provided by the inmate;
means for monitoring the voice communication between the inmate and the non-inmate;
means for selecting a plurality of boundaries in the monitored voice communication, wherein the boundaries separate the monitored voice communication into a plurality of speech segments, and wherein the boundaries are selected to increase the length of the speech segments spoken by the non-inmate; and
means for improving the voice model based on the speech segments spoken by the non-inmate during the monitored voice communication.
2. The system of claim 1 , further comprising
means for prompting the non-inmate to speak their name before connecting the voice communication.
3. The system of claim 2 , further comprising
means for improving the voice model based on the name spoken by the non-inmate.
4. The system of claim 1 , further comprising
means for improving the voice model based on additional voice communications between the inmate and the non-inmate.
5. The system of claim 1 , wherein a photographic image taken of the non-inmate is associated with the voice model.
6. The system of claim 1 ,
wherein the plurality of boundaries comprises pauses in the monitored voice communication.
7. The system of claim 1 , wherein the plurality of boundaries comprises portions of the monitored voice communication where two or more simultaneous speakers are detected.
8. A method for voice identity verification within a prison phone system comprising:
prompting an inmate requesting a voice communication to speak the inmate's name;
prompting the inmate to speak the name of a non-inmate
generating a voice model for the non-inmate based on the spoken name of the non-inmate provided by the inmate;
monitoring the voice communication between the inmate and the non-inmate;
selecting a plurality of boundaries in the monitored voice communication, wherein the boundaries separate the monitored voice communication into a plurality of speech segments, and wherein the boundaries are selected to increase the length of the speech segments spoken by the non-inmate; and
improving the voice model based on the speech segments spoken by the non-inmate during the monitored voice communication.
9. The method of claim 8 , further comprising
prompting the non-inmate to speak their name before connecting the voice communication.
10. The method of claim 9 , further comprising
improving the voice model based on the name spoken by the non-inmate.
11. The method of claim 8 , further comprising
improving the voice model based on additional voice communications between the inmate and the non-inmate.
12. The method of claim 8 , wherein a photographic image taken of the non-inmate is associated with the voice model.
13. The method of claim 8 ,
wherein the plurality of boundaries comprises pauses in the monitored voice communication.
14. The method claim 8 , wherein the plurality of boundaries comprises portions of the monitored voice communication where two or more simultaneous speakers are detected.
15. 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 voice identity verification in a prison phone system, the operations comprising:
prompting an inmate requesting a voice communication to speak the inmate's name;
prompting the inmate to speak the name of a non-inmate,
generating a voice model for the non-inmate based on the spoken name of the non-inmate provided by the inmate;
monitoring the voice communication between the inmate and the non-inmate;
selecting a plurality of boundaries in the monitored voice communication, wherein the boundaries separate the monitored voice communication into a plurality of speech segments, and wherein the boundaries are selected to increase the length of the speech segments spoken by the non-inmate; and
improving the voice model based on the speech segments spoken by the non-inmate during the monitored voice communication.
16. The non-transitory computer-accessible storage medium of claim 15 , the operations further comprising
prompting the non-inmate to speak their name before connecting the voice communication.
17. The non-transitory computer-accessible storage medium of claim 15 , the operations further comprising
improving the voice model based on additional voice communications between the inmate and the non-inmate.
18. The non-transitory computer-accessible storage medium of claim 15 , wherein a photographic image taken of the non-inmate is associated with the voice model.
19. The non-transitory computer-accessible storage medium of claim 15 ,
wherein the plurality of boundaries comprises pauses in the monitored voice communication.
20. The non-transitory computer-accessible storage medium claim 15 , wherein the plurality of boundaries comprises portions of the monitored voice communication where two or more simultaneous speakers are detected.