All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Statistical Based Voice Activity Detector

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F05%3APU51358" target="_blank" >RIV/00216305:26220/05:PU51358 - isvavai.cz</a>

  • Result on the web

  • DOI - Digital Object Identifier

Alternative languages

  • Result language

    angličtina

  • Original language name

    Statistical Based Voice Activity Detector

  • Original language description

    This paper deals with the method of voice activity detection. The paper aims especially to two detector types; these are the detector based on short-time signal energy and statistical model-based voice activity detector. Decision-making rules of the statistical model-based detector are derived from the LRT (Likelihood Ratio Test) by estimating unknown parameters using the ML (Maximum Likelihood) criterion. In addition there is an effective hang-over scheme based on HMM (Hidden Markov Model) principles iin the detector. There were models for these detectors created in Matlab simulation environment. Models were tested on voice signals with the white noise as well as real noises. The results were evaluated and compared for various types of noises and SNR(Signal to Noise Ratios) values.

  • Czech name

    Statistický detektor řečové aktivity

  • Czech description

    Příspěvek pojednává o možnosti využití statistických vlastností signálu pro detekci řečové aktivity. Detektor je založen na porovnání rozložení spektrální výkonové hustoty sledovaného signálu a odhadu spektrální výkonové hustoty rušení. Rozhodovací pravidlo je pak odvozeno od testu maximální podobnosti LRT (Likelihood Ratio Test), kdy neznámé parametry jsou odhadnuty metodou maximální podobnosti ML (Maximum Likelihood). Detektor je porovnán s energetickým detektorem pro různé poměry signálu od šumu a prro různé typy rušení.

Classification

  • Type

    D - Article in proceedings

  • CEP classification

    JA - Electronics and optoelectronics

  • OECD FORD branch

Result continuities

  • Project

    Result was created during the realization of more than one project. More information in the Projects tab.

  • Continuities

    Z - Vyzkumny zamer (s odkazem do CEZ)

Others

  • Publication year

    2005

  • Confidentiality

    S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Data specific for result type

  • Article name in the collection

    Proceedings of 6th International Conference Research In Telecommunications Technology 2005

  • ISBN

    80-248-0897-8

  • ISSN

  • e-ISSN

  • Number of pages

    5

  • Pages from-to

    537-541

  • Publisher name

    Technical University of Ostrava

  • Place of publication

    NEUVEDEN

  • Event location

    Hradec nad Moravicí

  • Event date

    Sep 12, 2005

  • Type of event by nationality

    WRD - Celosvětová akce

  • UT code for WoS article