|
Work item:
|
X.1097 (ex X.tas)
|
|
Subject/title:
|
Telebiometric authentication using speaker recognition
|
|
Status:
|
Consented on 2025-12-11 [Issued from previous study period]
|
|
Approval process:
|
AAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
2025-12 (Medium priority)
|
|
Liaison:
|
ISO/IEC JTC1 SC27,SC37, ITU-T SG12
|
|
Supporting members:
|
Mali (Republic of), South Africa, and Sénégal
|
|
Summary:
|
In today's world, there are more and more risks of fraud such as spoofing. It is necessary to fight against these risks and to restore trust between the client and the company providing the services. With the advent of artificial intelligence, it is now possible to reduce these types of risks through new authentication methods, such as speaker recognition using machine learning (ML) like neural network techniques.
This Recommendation addresses speaker recognition systems and telebiometric authentication models using the technologies of speaker recognition. Speaker recognition technologies have been considered for telebiometric authentication, which integrates speech over the telecommunication and biometric systems. This Recommendation provides functional requirements for each subsystem comprising the speaker recognition system. Several architectures for implementing telebiometric speaker authentication are described, including the case of integrating with voice assistant devices.
This Recommendation identifies threats and vulnerabilities at each step of the telebiometric speaker authentication system, including speech presentation, feature extraction, comparison and decision-making. It also provides countermeasures for the identified threats at each step of the telebiometric authentication.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2018-04-12 16:39:19
|
|
Last update:
2026-01-14 13:20:41
|
