(redirected from Speaker recognition)
Also found in: Dictionary, Thesaurus, Medical, Encyclopedia, Wikipedia.


The process of recognizing a human being using one or more inherent physical traits. For example, one may identify a criminal using his/her fingerprints. Biometric products are used for a variety of government and commercial purposes, often for security.


Increasingly popular building security system technology that relies on automated identification of physical characteristics such as fingerprints or retinal scans in order to determine access rights.The technology and the cost have both reached the point that consumer-level biometric security devices are available,such as for use in self-storage facilities and residences.Access codes, keys, and electronic cards are becoming outdated. Developers should bear this in mind when designing new construction and spend a minor amount of extra money necessary for wiring to accommodate biometric systems.

References in periodicals archive ?
Similarly in Figure (5), the HTER can be observed and compared for the number of speakers based on the four categories in speaker recognition applied in this research.
Reynolds (2000) The NIST speaker recognition evaluation - overview, methodology, systems, results, perspectives, Speech Communications, Vol.
A study regarding the suitability of Speaker Recognition Technology adapted to the inmate phone monitoring systems was tested by AFRL/IF.
To further explore the use of idiolectal characteristics of speakers in speaker recognition, a new extended data one-speaker detection task was included in this year's evaluation.
As their name implies, the Speaker Recognition APIs can be used to identify and verify speakers by comparing their voices to stored voiceprints.
Finally, some experimental results of automatic speaker recognition are presented and evaluated.
For the past 5 years, NIST has organized evaluations of text-independent speaker recognition performance on conversational telephone speech.
MegaMatcher SDK For AFIS or multi-biometric fingerprint, iris, face, and voice identification for large-scale systems; VeriLook SDK For face identification for PC, mobile, and Web solutions; VeriFinger SDK For fingerprint identification for PC, mobile, and Web solutions; VeriEye SDK For iris identification for PC, mobile, and Web solutions; VeriSpeak SDK For speaker recognition for PC, mobile, and Web applications; SentiBotics For ready-to-use robotics development kit
Systems intended to exploit this property of voice must be able to make a credible representation of the observed voice, and equipped with reliable procedures for automatic speaker recognition [1].
ANSI was the first to come out with a speech-related standard when it published INCITS 456: Speaker Recognition Format for Raw Data Interchange (SIVR-1), which governs the type and format of data that should be included with shared audio files used for speaker identification and verification (SIV).
Gazit also added, "This improvement in text-dependent speaker verification accuracy comes together with a significant breakthrough in text-independent accuracy, demonstrated by Persay's FreeSpeech(TM) product, following a successful participation in the NIST 2006 Speaker Recognition Evaluation.