NIST

National Institute of Standards and Technology

NDA

Non-Disclosure Agreement

MSRP

Manufacturer’s Suggested Retail Price

Modus

The mode is the value that appears most often in a set of data.

MINT

Meeting Asistant – Phonexia research project

MI

Military Intelligence

Median

Median – Value separating higher half of data sample from lower half.

MAE

Mean Absolute Error – In statistics, the mean absolute error (MAE) is a quantity used to measure how close forecasts or predictions are to the eventual outcomes.

LVCSR

Large Vocabulary Continuous Speech Recognition

LLR

Log-Likelihood Ratio – Logarithmic function of LR (le)

LR

Likelihood Ratio – Result from statistical test for two models comparation. It gives back number which expresses how many times more likely the data are under one model than the other. LR meets numbers in interval <-∞;+∞>

LPA

Language Print Archive – pack of language prints from the recordings spoken in the same language/dialect. Used for the language identification in LID comparison.

LP

Language Print – output data from LID technology

LM

Language Model (“vocabulary” in STT technology)

LID

Phonexia Language Identification, multiple generations available marked by version like LIDv2 or LIDv3

LEA

Law Enforcement Agency

LDC

Linguistic Data Consortium (Fisher English etc.) – Group of libraries, universities,… working with speech data.

KWS

Phonexia Keyword Spotting – acoustics based ASR, several technologies possible, language dependent

IVR

Interactive Voice Response – Process of caller authentication (typically banking segment)

iVector

iVector – Unique value representing specific group of voice tracks. Consist of 600 values, usually lowered to low dimensional vector (200 values)

ISS

Intelligence Support Systems for lawfull interception, criminal investigations, and intelligence gathering. Really important International conference, invitation only.

HPC

High Perfomance Computing

H2020

Horizon 2020 – EU program for inovations and developement

GUI

Graphical User Interface

GSM

Global system for mobile communications – Mobile phone protocol

GMM

Gausian mixture model – Statistical model for representing values.

GID

Phonexia Gender Identification

FtRT

Faster than the Real Time – processing speed on 1 instance of the speech technology. Can be described also as “X min of audio archive to be processed in Y min of the real time”.

FRR

False Rejection Ratio – Values, which were not accepted, when they were supposed to be accepted, aka ‘misses’

FEA

Features – FEA is optional output from KWS technology. Looking for keywords in FEA is faster than in original recording.