Browse Prior Art Database

Method for Automatic Mute Detection using Language Identification

IP.com Disclosure Number: IPCOM000236986D
Publication Date: 2014-May-23
Document File: 3 page(s) / 58K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a method for determining whether ambient noise during a conference call is an identifiable language and whether that language is the intended language of the call. If the noise or language is not part of the call, then the system automatically mutes the associated line.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 65% of the total text.

Page 01 of 3

Method for Automatic Mute Detection using Language Identification

Having to tell people on a conference call to go on mute due to ambient noise is disruptive to a meeting. When there is ambient noise during a conference call, a request has to be made to all parties to mute the associated lines or the moderator can force all lines to mute. Often on global calls, there is background noise that is speech, but the language of the speech is not in the intended language of the conference call.

Known solutions identify speech, yet simply determining speech to change the mute attributes of a call is not sufficient for international calls on which the background noise is in another language. For instance, if during a conference call that is intended to be in English, the call is in a mute active mode and speech triggers a line change into a mute deactivated mode. If a participant starts speaking in French, it disrupts the call.

The novel contribution is a method for detecting whether the sounds picked up by the telephone are coming from a person, based on the identification of the language as the active language of the conference call. In addition to identifying speech, the identification of language improves automatic mute solutions for international calls.

The components and process for implementing the method follow:

1. Enter a conference call 2. Language of the call is determined 3. Lines are in mute 'on' or mute 'off' mode 4. A noise is detected 5. The noise is iden...