Selective voice transmission during telephone calls

Patent metadata

Field	Value
Publication number	US-9293147-B2
Application number	US-201414501191-A
Country	US
Kind code	B2
Filing date	Sep 30, 2014
Priority date	Oct 17, 2013
Publication date	Mar 22, 2016
Grant date	Mar 22, 2016

Abstract

Embodiments of the disclosure relate to selective voice transmission and include receiving an identification of one or more authorized speakers for a telephone call and retrieving a voice sample for each of the one or more authorized speakers. Embodiments also include receiving one or more audio signals for the telephone call and filtering the one or more audio signals by removing a portion of the one or more audio signals that do not contain a voice of at least one of the one or more authorized speakers in the one or more audio signals.

First claim

What is claimed is:

1. A method for selective voice transmission, comprising:
receiving, by a processor, an identification of one or more authorized speakers for a telephone call;
retrieving, by the processor, a voice sample for each of the one or more authorized speakers;
receiving, by the processor, one or more audio signals for the telephone call; and
filtering, by the processor, the one or more audio signals by removing a portion of the one or more audio signals that does not contain a voice of at least one of the one or more authorized speakers in the one or more audio signals.

2. The method of claim 1 , wherein retrieving a voice sample for each of the one or more authorized speakers further comprises retrieving the voice sample from a voice repository.

3. The method of claim 1 , wherein retrieving a voice sample for each of the one or more authorized speakers further comprises collecting the voice sample from the one or more authorized speakers.

4. The method of claim 3 , wherein collecting the voice sample from the one or more authorized speakers occurs during a portion of the telephone call.

5. The method of claim 1 , wherein the identification of one or more authorized speakers includes an identity of each of the one or more authorized speakers and an authorized time period for each of the one or more authorized speakers.

6. The method of claim 5 , wherein the filtering further comprises removing a portion of the one or more audio signals that contains the voice of an authorized speaker in the one or more audio signals if a current time is not within the authorized time period corresponding to the authorized speaker.

7. A computer program product for selective voice transmission, the computer program product comprising:
a tangible storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising:
receiving an identification of one or more authorized speakers for a telephone call;
retrieving a voice sample for each of the one or more authorized speakers;
receiving one or more audio signals for the telephone call; and
filtering the one or more audio signals by removing a portion of the one or more audio signals that do not contain a voice of at least one of the one or more authorized speakers in the one or more audio signals.

8. The computer program product of claim 7 , wherein retrieving a voice sample for each of the one or more authorized speakers further comprises retrieving the voice sample from a voice repository.

9. The computer program product of claim 7 , wherein retrieving a voice sample for each of the one or more authorized speakers further comprises collecting the voice sample from the one or more authorized speakers.

10. The computer program product of claim 9 , wherein collecting the voice sample from the one or more authorized speakers occurs during a portion of the telephone call.

11. The computer program product of claim 7 , wherein the identification of one or more authorized speakers includes an identity of each of the one or more authorized speakers and an authorized time period for each of the one or more authorized speakers.

12. The computer program product of claim 11 , wherein the filtering further comprises removing the portion of the one or more audio signals that contains the voice of one of the authorized speaker in the one or more audio signals if a current time is not within the authorized time period corresponding to the authorized speaker.

Assignees

• Globalfoundries Inc
• Globalfoundries Inc

Inventors

• Chu Jean
• Diamond Susan L
• Fang William L
• Hom Peter B
• Li Jenny S
• Yuan Jing-Na

Classifications

• G10L2021/02087

  the noise being separate speech, e.g. cocktail party · CPC title

• H04M3/4936

  Speech interaction details (speech recognition per se G10L15/00) · CPC title

• H04M3/2236

  Quality of speech transmission monitoring · CPC title

• G10L21/0208 Primary

  Noise filtering · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title