Method for associating a device with a speaker in a gateway, corresponding computer program, computer and apparatus
AssigneeInterDigital CE Patent Holdings, SAS
InventorsChristopher HOWSON, Philippe GILBERTON, Patrick FONTAINE, Christoph NEUMANN
Life of this patent
Estimating the term…
Abstract
The present disclosure proposes a solution to associate a device with a user by capturing a voice of a speaker by a microphone connected to the network device (e.g. a residential or home gateway), monitoring the IP traffic of the network device and detecting the device contributing to this IP traffic in order to establish a link between the speaker and his device(s) and associate the device with the speaker.
Claims15
A method for associating a device with a speaker, in a network device having a microphone and handling network traffic of a plurality of devices, said method comprising:
- extracting first voice features representative of the temporal voice activity captured by said microphone;
- extracting traffic features representative of the temporal traffic activity of voice-related stream generated by at least one device;
- if first voice features and traffic features are correlated, associating said device identifier with an identifier of said speaker, wherein the identifier of said speaker is determined using second voice features representative of speakers.
An apparatus for associating a device with a speaker, said apparatus handling network traffic of a plurality of devices and comprising a microphone configured to capture a voice of said speaker by said microphone, and a processor configured to:
- extract first voice features representative of the temporal voice activity captured by said microphone;
- extract traffic features representative of the temporal traffic activity of voice-related stream generated by at least one device;
- if first voice features and traffic features are correlated, associate said device identifier with an identifier of said speaker, wherein the identifier of said speaker is determined using second voice features representative of speakers.
Dependencies are inferred from the claim text.