Methods and systems for processing audio signals containing speech data
Methods and systems for processing audio signals containing speech data are disclosed. Biometric data associated with at least one speaker are extracted from an audio input. A correspondence is determined between the extracted biometric data and stored biometric data associated with a consenting user profile, where a consenting user profile is a user profile indicates consent to store biometric data. If no correspondence is determined, the speech data is discarded, optionally after having been processed.
1 . A method comprising:
storing one or more user profiles that are each associated with one of one or more users of a computing system, wherein each user profile is associated with biometric data that uniquely characterizes a respective user of the one or more users of the computing system, and wherein at least one of the one or more user profiles is a consenting user profile, wherein each consenting user profile of a respective user indicates consent to store biometric data of the respective user;
determining first biometric data associated with a first speaker based at least in part on speech content derived from first image data of the first speaker;
determining whether the first biometric data associated with the first speaker corresponds to any biometric data associated with any consenting user profile indicating consent to store biometric data of a respective user; and
responsive to determining that the first biometric data associated with the first speaker does not correspond to any voiceprint associated with any consenting user profile:
deleting the first image data within a time period.
2 . The method of claim 1 further comprising:
processing second image data of a second speaker, wherein processing the second image data of the second speaker comprises extracting, from the second image data of the second speaker, second biometric data associated with the second speaker;
determining whether the second biometric data associated with the second speaker corresponds to any biometric data associated with any consenting user profile indicating consent to store biometric data of a respective user; and
responsive to determining that the second biometric data extracted from the second image data of the second speaker corresponds to a voiceprint associated with a consenting user profile, performing at least one of:
processing the second image data; or
storing the second image data in an archive.
3 . The method of claim 1 , wherein determining the first biometric data associated with the first speaker comprises analysing the first image data to determine the speech content based on movements of one or more facial features of the first speaker.
4 . The method of claim 3 , wherein the one or more facial features comprise one or more of a mouth, lips or jaw.
5 . The method of claim 1 , wherein determining the first biometric data associated with the first speaker comprises extracting, from the first image data of the first speaker, image-based biometric data associated with the first speaker.
6 . The method of claim 5 , wherein determining the first biometric data associated with the first speaker is further based on first speech data of the first speaker.
7 . The method of claim 6 , wherein determining the first biometric data associated with the first speaker further comprises extracting, from the first speech data of the first speaker, speech-based biometric data associated with the first speaker.
8 . The method of claim 1 , further comprising creating a consenting user profile, wherein creating a consenting user profile comprises:
verifying credentials of a first user of the computing system against a data source to ensure that the first user is authorized to provide consent to store speech data;
initializing a user profile associated with a second user, on instruction of the first user, wherein the second user is a child and the first user is a parent of the second user;
receiving speech data of the second user;
extracting biometric data from the speech data of the second user;
storing the biometric data from the speech data of the second user and associating the biometric data from the speech data of the second user with the user profile associated with the second user; and
storing the user profile associated with the second user as a consenting user profile.
9 . The method of claim 1 , further comprising matching additional biometric data acquired from the first speaker against stored biometric data associated with a respective consenting user profile.
10 . The method of claim 9 , wherein the additional biometric data is selected from:
a. image data of a face of the first speaker;
b. iris pattern data;
c. fingerprint data;
d. hand geometry data;
e. palm blood vessel pattern data;
f. retinal blood vessel pattern data;
g. mouth movement data; or
h. behavioural data.
11 . The method of claim 1 , further comprising creating a non-consenting user profile, wherein creating a non-consenting user profile comprises:
initializing a second user profile associated with a second user;
receiving speech data of the second user;
extracting second biometric data from the speech data of the second user;
storing the second biometric data and associating the second biometric data with the second user profile; and
storing the second user profile as a non-consenting user profile.
12 . A non-transitory computer-readable medium comprising instructions, which when executed by a processor, cause the processor to perform operations comprising:
storing one or more user profiles that are each associated with one of one or more users of a computing system, wherein each user profile is associated with biometric data that uniquely characterizes a respective user of the one or more users of the computing system, and wherein at least one of the one or more user profiles is a consenting user profile, wherein each consenting user profile of a respective user indicates consent to store biometric data of the respective user;
determining first biometric data associated with a first speaker based at least in part on speech content derived from first image data of the first speaker;
determining whether the first biometric data associated with the first speaker corresponds to any biometric data associated with any consenting user profile indicating consent to store biometric data of a respective user; and
responsive to determining that the first biometric data associated with the first speaker does not correspond to any voiceprint associated with any consenting user profile:
deleting the first image data within a time period.
13 . The non-transitory computer-readable medium of claim 12 , the operations further comprising:
processing second image data of a second speaker, wherein processing the second image data of the second speaker comprises extracting, from the second image data of the second speaker, second biometric data associated with the second speaker;
determining whether the second biometric data associated with the second speaker corresponds to any biometric data associated with any consenting user profile indicating consent to store biometric data of a respective user; and
responsive to determining that the second biometric data extracted from the second image data of the second speaker corresponds to a voiceprint associated with a consenting user profile, performing at least one of:
processing the second image data; or
storing the second image data in an archive.
14 . The non-transitory computer-readable medium of claim 12 , wherein determining the first biometric data associated with the first speaker comprises analysing the first image data to determine the speech content based on movements of one or more facial features of the first speaker, wherein the one or more facial features comprise one or more of a mouth, lips or jaw.
15 . The non-transitory computer-readable medium of claim 12 , wherein determining the first biometric data associated with the first speaker comprises extracting, from the first image data of the first speaker, image-based biometric data associated with the first speaker.
16 . The non-transitory computer-readable medium of claim 15 , wherein determining the first biometric data associated with the first speaker is further based on first speech data of the first speaker.
17 . The non-transitory computer-readable medium of claim 16 , wherein determining the first biometric data associated with the first speaker further comprises extracting, from the first speech data of the first speaker, speech-based biometric data associated with the first speaker.
18 . A system comprising:
a memory; and
a processing device coupled to the memory, to perform operations comprising:
storing one or more user profiles that are each associated with one of one or more users of a computing system, wherein each user profile is associated with biometric data that uniquely characterizes a respective user of the one or more users of the computing system, and wherein at least one of the one or more user profiles is a consenting user profile, wherein each consenting user profile of a respective user indicates consent to store biometric data of the respective user;
determining first biometric data associated with a first speaker based at least in part on speech content derived from first image data of the first speaker;
determining whether the first biometric data associated with the first speaker corresponds to any biometric data associated with any consenting user profile indicating consent to store biometric data of a respective user; and
responsive to determining that the first biometric data associated with the first speaker does not correspond to any voiceprint associated with any consenting user profile:
deleting the first image data within a time period.
19 . The system of claim 18 , the operations further comprising:
processing second image data of a second speaker, wherein processing the second image data of the second speaker comprises extracting, from the second image data of the second speaker, second biometric data associated with the second speaker;
determining whether the second biometric data associated with the second speaker corresponds to any biometric data associated with any consenting user profile indicating consent to store biometric data of a respective user; and
responsive to determining that the second biometric data extracted from the second image data of the second speaker corresponds to a voiceprint associated with a consenting user profile, performing at least one of:
processing the second image data; or
storing the second image data in an archive.
20 . The system of claim 18 , wherein determining the first biometric data associated with the first speaker comprises analysing the first image data to determine the speech content based on movements of one or more facial features of the first speaker, wherein the one or more facial features comprise one or more of a mouth, lips or jaw.