Generating call context metadata from speech, contacts, and common names in a geographic area

Patent metadata

Field	Value
Publication number	US-9747904-B2
Application number	US-201615393442-A
Country	US
Kind code	B2
Filing date	Dec 29, 2016
Priority date	Nov 23, 2015
Publication date	Aug 29, 2017
Grant date	Aug 29, 2017

Abstract

A computer detects a connected voice or video call between participants and records a brief media sample. Speech recognition is utilized to determine when the call is connected as well as to transcribe the content of the audio portion of the media sample. The recorded media sample and transcribed content is associated with the connected voice or video call such that a user may reference it at a later point. The computer additionally suggests creating or editing contact information associated with the participants of the connected voice or video call based on the transcribed content.

First claim

What is claimed is:

1. A computer system for generating call context metadata, the computer system comprising:
one or more computer processors, one or more computer-readable storage media, and program instructions stored on one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
one or more computer-readable storage media and program instructions stored on the one or more computer-readable storage media, the program instructions comprising:
program instructions to detect that a call is connected, wherein the call is connected based on speech being detected;
program instructions to record a media sample corresponding to the connected call, wherein the media sample includes an audio recording of at least a portion of the detected speech;
program instructions to identify one or more words contained within the at least a portion of the detected speech, wherein identifying the one or more words further comprises:
program instructions to identify a first portion of the one or more words by comparing a voiceprint associated with the first portion with a voiceprint database and program instructions to identify a second portion of the one or more words by comparing a voiceprint associated with the second portion with the voiceprint database, and wherein the first portion of the one or more words corresponds to a first speaker and the second portion of the one or more words corresponds to a second speaker;

program instructions to determine whether a phone number associated with the connected call is associated with one or more contacts detailed by a contact list of a user;
based on determining that the phone number associated with the connected call is not associated with the one or more contacts detailed by the contact list of the user, program instructions to store the recorded media sample and the identified one or more words in association with the connected call;
program instructions to determine a location of the user based on analyzing Global Positioning System (GPS) information associated with a device of the user;
program instructions to reference a common name list, wherein the common name list details a set of commonly used names associated with a geographic area, and wherein the geographic area is an area within a distance of the location of the user;
program instructions to determine whether at least one of the identified one or more words matches at least one of one or more names detailed by the common name list;
based on determining that at least one of the identified one or more words matches at least one of the one or more names detailed by the common name list, program instructions to present an option to the user to add the at least one of the identified one or more words to the contact list of the user in association with the phone number associated with the connected call;
based on the user selecting the option to add the at least one of the identified one or more words to the contact list of the user in association with the phone number associated with the connected call, program instructions to add the at least one of the identified one or more words to the contact list of the user in association with the phone number associated with the connected call; and
program instructions to delete the recorded media sample and the identified one or more words stored in association with the connected call,
wherein one or more steps of the above method are performed using one or more computers.

Assignees

• IBM

Inventors

• Gorthi Ramakrishna J
• Joshi Chandrajit G
• Shah Romil J

Classifications

• H04M2201/41

  using speaker recognition · CPC title

• H04M2250/74

  with voice recognition means · CPC title

• G10L17/06

  Decision making techniques; Pattern matching strategies · CPC title

• H04M1/645 Primary

  with speech synthesis · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title