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”

Evaluation of Blind Separated Signals Using Speech Recognition System

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F05%3APU51585" target="_blank" >RIV/00216305:26220/05:PU51585 - isvavai.cz</a>

  • Result on the web

  • DOI - Digital Object Identifier

Alternative languages

  • Result language

    angličtina

  • Original language name

    Evaluation of Blind Separated Signals Using Speech Recognition System

  • Original language description

    Output blind separated signals are recovered independent sources obtained from their mixtures using methods of convolutive independent component analysis. These methods have no information about the original sources and the mixing process. For the separation process we adapted and improved a method which is based on the natural gradient approach. The new concept proposed in this paper then tries to measure the hit rate of the source restoration by means of the discrete word intelligibility using an Inteernet speech recognition system. We are interested in a two-channel case, in which we observe the outputs of a 2 x 2 linear time invariant system of mixtures of speech, music and noise signals.

  • Czech name

    Vyhodnocovani sgnalu separovanych naslepo pomoci recoveho rozpoznavaciho systemu

  • Czech description

    Vystupni signaly separovane naslepo jsou obnovene nezavisle zdroje ziskane z jejich smesi pomoci metod konvolucni analyzy nezavislych komponent. Tyto metody nemaji zadnou informaci o puvodnich zdrojich a smesnem procesu. Pro separacni proces jsme upravili a vylepsili metodu, ktera je zalozena na prirozenem gradientu. Novy postup prezentovany v tomto prispevku se pak snazi 'merit' uspesnost obnoveni zdroju vyhodnocovanim srozumitelnosti jednotlivych slov promluvy pomoci Internetoveho rozpoznavaciho systeemu. Zajima nas casove invariantni system dvou pozorovanyh smesi reci, hudby a sumu.

Classification

  • Type

    D - Article in proceedings

  • CEP classification

    JA - Electronics and optoelectronics

  • OECD FORD branch

Result continuities

  • Project

    <a href="/en/project/GA102%2F04%2F1097" target="_blank" >GA102/04/1097: Enhancement of speech signal hidden in noise</a><br>

  • Continuities

    P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

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

    EUROCON 2005 - The International Conference on "Computer as a tool", R23 Signal Processing, IEEE Catalog Number: 05EX1255C

  • ISBN

    1-4244-0050-3

  • ISSN

  • e-ISSN

  • Number of pages

    4

  • Pages from-to

    1650-1653

  • Publisher name

    EUROCON

  • Place of publication

    Belgrade, Serbia and Montenegro

  • Event location

    Belgrade

  • Event date

    Nov 21, 2005

  • Type of event by nationality

    WRD - Celosvětová akce

  • UT code for WoS article