ISO IEC 19794-13:2018 pdf free

ISO IEC 19794-13:2018 pdf free.Information technology一Biometric data interchange formats
This clause defines the fundamental elements of SIV interactions called “capture process”, as defined in ISO/IEC 2382-37, and the VRs of data subject speech captured during those interactions or “sessions”.During a capture process voice sounds stemming not from the targeted speaker may be unintentionally recorded overlapping or not overlapping targeted speech sequences; this speech should be considered as noise. Compatible capture process structuring and acoustic signal descriptions are required for interoperability between and among SIV engines.
A voice utterance is assumed to come from a single speaker for the purpose of recognizing individuals,(or to be used to create a reference for future comparisons). In the case that other voices from different individuals are included within the utterance, this information should be considered as noise, which might affect the SIV system. It is not the purpose of this document to specify how voice utterances will be demarcated, but they will generally be separated by: 1) a change in or repeat of a prompt; or 2) a pause of far longer duration than the inter-syllabic rate. There is no minimum or maximum length to a voice utterance.
This is an example from an access control application. In this example, the first voice utterance is the claimed reference pointer (“claim of identity”) by the data subject “speaker A”. A speaker independent automated speech recognition (ASR) system might be used to extract the content from the first utterance to determine the reference pointer. The second utterance is the “text-dependent” passphrase required to verify the claim using the stored voice model of the reference pointer. The capture process in Figure 1 would not need to change for data subjects interacting with humans (e.g., a call centre agent). Variants of capture process 1 include asking or allowing the data subject to input the reference pointer (account number) manually (e.g. using the touchtone keypad of the telephone). Prompts can be presented as audio by playing one or more sound files or by generating a TTS output for an internal string. Prompts may be presented as text displays (e.g. on PDAs, mobile, or smart devices).ISO IEC 19794-13 pdf free.