Fandom

The IT Law Wiki

Voice recognition

32,177pages on
this wiki
Add New Page
Talk0 Share

Ad blocker interference detected!


Wikia is a free-to-use site that makes money from advertising. We have a modified experience for viewers using ad blockers

Wikia is not accessible if you’ve made further modifications. Remove the custom ad blocker rule(s) and the page will load as expected.

Definition Edit

Voice recognition means

the use of voice input to give instructions or data to a computer system. Significant advances have already been made and are available, e.g., via on-line banking. The use of voice recognition in word-processing (and in other applications not capable of resolution to simple phrases) is constrained, however, by the ambiguity of language (both grammar and meaning).[1]

Historical background Edit

Subjective techniques of voice identification — listening to speakers and identifying them through familiarity with their voices — have been admissible evidence in courts of law for hundreds of years.[2] Technical developments in electronics, speech processing, and computer technology are making possible objective, automatic voice identification, with several potential security applications and important legal implications.

Overview Edit

The sound produced by the vocal tract is an acoustic signal with a phonetic and linguistic pattern that varies not only with the speaker's language and dialect, but also with personal features that can be used to identify a particular speaker.

Voice recognition technology identifies people based on the differences in the voice resulting from physiological differences and learned speaking habits. When an individual is enrolled, the system captures samples of the person's speech as the individual says certain scripted information into a microphone or telephone multiple times. This information is known as a "pass phrase." (There are also biometric systems available that can distinguish between people's voices without requiring a predefined phrase.) The pass phrase is then converted to a digital format and distinctive characteristics (e.g., pitch, cadence, tone) are extracted to create a template for the speaker. Voice recognition templates require the most data space of all the biometric templates. Voice recognition technology can be used for both identification and verification."[3]

Applications include access control for computer terminals, computer and data processing facilities, bank vaults, security systems for buildings, credit card authorization, and automatic teller machines.

References Edit

  1. The Net Result: Social Inclusion in the Information Society, at 68.
  2. Oscar Tosi, Voice Identification: Theory and Legal Applications (1979).
  3. Biometric Technologies: Security, Legal, and Policy Implications, at 5-6.

See also Edit

Also on Fandom

Random Wiki