Back to results
US 2014/0369479 A1Published application
System and Method for Live Voice and Voicemail Detection
AssigneeNobelBiz, Inc.
InventorJames Siminoff
Life of this patent
Estimating the term…
Abstract
A computer system for processing audio on a call having a processor in communication with non-volatile memory having code for converting recorded audio into a vector, comparing the recorded audio vector with a plurality of audio vectors and generating a comparative match number for each comparison, identifying a closest audio vector having a highest comparative match number above a predetermined threshold match number, connecting the call to an agent when the closest audio vector is designated as live-voice.
Claims18
A computer system for processing audio on a call, comprising:
- a processor in communication with non-volatile memory, the non-volatile memory comprising:
- code for detecting audio on the call;
- code for recording audio on the call and converting the recorded audio into a vector;
- code for comparing the recorded audio vector with a plurality of audio vectors stored in a database and generating a comparative match number for each comparison, where each of the plurality of audio vectors is designated as live-voice or pre-recorded;
- code for identifying a closest audio vector having a highest comparative match number above a predetermined threshold match number;
- code for connecting the call to an agent when the closest audio vector is designated as live-voice and storing the recorded audio vector in the database with live-voice designation;
- and
- code storing the recorded audio vector in the database with pre-recorded designation when the closest audio vector is designated as pre-recorded.
5 more elements
A computer system for processing audio on a call, comprising:
- a processor in communication with non-volatile memory, the non-volatile memory comprising:
- an audio detection system in electrical communication with a database, the audio detection system capable of
- detecting audio on the call;
- recording audio on the call;
- converting the recorded audio into a vector;
- comparing the recorded audio vector with a plurality of audio vectors stored in the database and generating a comparative match number for each comparison, where each of the plurality of audio vectors is designated as live-voice or pre-recorded;
- and
- identifying a closest audio vector having a highest comparative match number above a predetermined threshold match number;
- a call distribution system in electrical communication with the audio detection system, the database, and a communication network, the call distribution system capable of placing the call;
- connecting the call to an agent when the closest audio vector is designated as live-voice and storing the recorded audio vector in the database with live-voice designation;
- and
- storing the recorded audio vector in the database with pre-recorded designation when the closest audio vector is designated as pre-recorded.
9 more elements
Dependencies are inferred from the claim text.