Archives of Acoustics, 3, 1, pp. 3-15, 1978

The application of long-term analysis of the zero-crossing of a speech signal in automatic speaker identification

Czesław Basztura
Institute of Telecommunication and Acoustics, Technical University
Poland

Wojciech Majewski
Institute of Telecommunication and Acoustics, Technical University
Poland

This paper investigates the possibility of using long-term analysis of the zero-crossings of a speech signal for speaker identification. The applied method of identification is based on an analysis of the signal in measuring windows of a duration which should ensure the stationarity of the statical distributions of the time intervals between successive zero-crossings, in 16 pre-set time channels.
An objective method of defining the minimum length of the measuring window for a selected set of parameters is presented. It is based on the static-narity test and the orgodic theorem for stochastic processes, as is the transfor¬mation of the speech signal mentioned above.. An experiment in speaker identi-fication for 10 speakers with 10 repetitions for each speaker has been performed. The results obtained, in well exceeding 90 % correct identification for 30- and 40 second samples of the speech signal, have confirmed the practicality of the met¬hod of zero-crossing analysis for speaker identification.
Full Text: PDF


Copyright © Polish Academy of Sciences & Institute of Fundamental Technological Research (IPPT PAN)