Detail publikace

Evaluation of Blind Separated Signals Using Speech Recognition System

EKSLER, V.

Originální název

Evaluation of Blind Separated Signals Using Speech Recognition System

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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 Internet 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.

Klíčová slova

Convolutive ICA, independent component analysis, microphone array, learning algorithm, natural gradient, speech enhancement, speech recognition.

Autoři

EKSLER, V.

Rok RIV

2005

Vydáno

21. 11. 2005

Nakladatel

EUROCON

Místo

Belgrade, Serbia and Montenegro

ISBN

1-4244-0050-3

Kniha

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

Strany od

1650

Strany do

1653

Strany počet

4

BibTex

@inproceedings{BUT15411,
  author="Václav {Eksler}",
  title="Evaluation of Blind Separated Signals Using Speech Recognition System",
  booktitle="EUROCON 2005 - The International Conference on {"}Computer as a tool{"}, R23 Signal Processing, IEEE Catalog Number: 05EX1255C",
  year="2005",
  pages="4",
  publisher="EUROCON",
  address="Belgrade, Serbia and Montenegro",
  isbn="1-4244-0050-3"
}