When choosing adequate technologies to be integrated in a product all alternatives must be taken into account. Security may be achieved in several ways, and voice is only one of the possibilities. We give here a brief overview of some alternative techniques.
The physical support for protecting information or access to unauthorised persons are usually classified into three main families: physical-object elements (key, badge, etc.), information elements (password, combination, etc.) and physical-personal elements (fingerprint, voice, DNA, etc.). The ensemble of systems based on this last family are called ``biometric verifier'' as they are directly tied to some biological characteristics of the (authorised) person.
The biometric family is divided into two subfamilies: one based on physical characteristics of the person that do not change (unless they are crude events) in the range of few years; the other based on behaviour characteristics that may change in relation to humour, environment, physical state, and so forth. Because of the high rate of variability of the latter subfamily, corresponding systems are quite difficult to obtain, especially in automatic mode, without expert supervision.
Just to clarify these two subfamilies of biometric verifier let us consider the list of biometric verifier shown in Table 11.7:
|genetic analysis||cardiac rhythm|
There is no unique strategy to select the most appropriate biometric verifier for a given task. However, there are a number of properties that must always be considered in designing a security system. Table 11.8 gives some important ones.
error(s) rates execution swiftness access facility
network capability number of potential users rate of test per time unit
acceptability integration facility cost
Generally speaking, if we are interested only in performance, a broad table summarising the value for different biometric verifiers may be the one reported by [Peckham (1990)] (see Table 11.9).
|MODALITY||FALSE REJECTION||FALSE ACCEPTANCE|
|voice (high quality)||1.0 %||0.1 %|
|voice (telephone quality)||3.3 %||0.4 %|
|retinal scan||2.8 %||0.0 %|
|signature||0.2 %||0.6 %|
|veincheck||< 1.0 %||< 1.0 %|
|hand shape||0.1 %||0.1 %|
The same report gives the example of field tests carried out for the US government on speech, signature and fingerprint. These resulted in a recommendation to use speech. Note also that the alternative techniques listed above are more appropriate for on-site applications and that speech remains a unique biometrical identification feature over telecommunication channels , at least until videophone and ISDN become widespread. Even so, some of the alternative techniques could only be implemented through individual sensors, an essential limitation of their applicability.