Transcription as a speech compression method in transmultiplexer system

  • Authors:

  • Mariusz Ziółko;Bartosz Ziółko;Andrzej Dziech

  • Affiliations:

  • Department of Electronics, AGH University of Science and Technology, Kraków, Poland;Faculty of Electrical Engineering, Automatics, Computer Science and Electronics, AGH University of Science and Technology, Kraków, Poland;Department of Telecommunications, AGH University of Science and Technology, Kraków, Poland

  • Venue:
  • MIV'05 Proceedings of the 5th WSEAS international conference on Multimedia, internet & video technologies
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

A very efficient method of speech compression in telecommunication systems is suggested. It uses the speech recognition system to convert the voice signal into its transcripted form. Next, a speech synthesizer is used to reconstruct speech on the receiver side. Integer filters are used to realize perfect reconstruction in the transmultiplexer system. Although such system destroys the individual speech features, it provides an extremely high compression.