THE IMPLEMENTATION OF SIGNAL ANALYSIS IN JAVA TO DETERMINE THE SOUND OF HUMAN VOICE AND GRAPHICAL REPRESENTATION IN STANDARD MUSIC NOTATION

Patryk Solecki, Wojciech Zabierowski

DOI Number
10.2298/FUEE1601139S
First page
139
Last page
149

Abstract


The article presents an analysis of the problems associated with signals processing, with special emphasis on the analysis of the problems of the human voice analysis. Based on the specific implementation of algorithms mark the human voice pitch, paper is showing the result in the form of standard music notation with treble and bass keys one the stave. The paper pays particular attention to the performance of the algorithms used for their implementation in Java. The same analysis
of the signals is not a challenge, but with regard to the implementation on mobile devices like smarfones, the use of Java at the same time with limited hardware resources remains a challenge. This applies to both the CPU and the memory which affects the processing speed using the Java virtual machine. It should be remebered not to skip a quality of microphone used in this type of mobile device. From this point of view presented considerations are a new approach to the well-known
problem of signal analysis implemented in computer applications such as Raven.

Keywords

Signal processing, java programming, music notation, voice analysis, java

Full Text:

PDF

References


P. Solecki, W. Zabierowski, The signal analysis of sound based on the application of guitar tabulatures for mobile devices. PRZEGLĄD ELEKTROTECHNICZNY, 2012, rocznik 88, nr 10b, p. 239-242.

V. A. Petrushin, Adaptive Algorithms for Pitch-synchronous Speech Signal Segmentation, SPECOM’2004: 9th Conference Speech and Computer St. Petersburg, Russia September 20-22, 2004.

A. S. Spanias, ―Speech coding: A tutorial review,‖ Proc. IEEE, 82, 1541–1575, October 1994.

Ch.Wendt, Athina P. Petropulu, Pitch determination and speech segmentation using the discrete wavelet transform, Electrical and Computer Engineering Department, Drexel University, Philadelphia PA 19104.

P. Mrowka, Algorytmy kompensacji warunków transmisyjnych i cech osobniczych mówcy w systemach automatycznego rozpoznawania mowy, Politechnika Wrocławska, Instytut Telekomunikacji, Teleinformatyki i Akustyki, Raport Nr I28/PRE-001/07, phd dissertation, Wrocław 2007.

A.P. Dobrowolski, E. Majda, Analiza cepstralna w systemach rozpoznania mówców, No 6/2012, Instytut Logistyki i Magazynowania, 2012.

R. G. Lyons, Understanding Digital Signal Processing, PEARSON, 2010.

B. Eckel, , 2003. Thinking in Java. Wydawnictwo ―Helion‖, Gliwice.

K. Demuynck, T. Laureys, A Comparison of Different Approaches to Automatic Speech Segmentation, http://www.esat.kuleuven.ac.be/#spch 2013.

W. P. Morozow, Isskustwo Rezonansnawo Pienija, Iskusstwo i nauka. Instytut Psychologii Rosyjskiej Akademii Nauk, Państwowe Konserwatorium im. P.I. Czajkowskiego w Moskwie, Moskwa 2002.

M. Dybowski, W. Zabierowski, 2005. Aplikacja rozpoznająca wysokość dźwięków głosu ludzkiego JAVA – w mgnieniu oka, XIII Konferencja SIS - Sieci i Systemy Informatyczne – teoria, projekty, wdrożenia, aplikacje, Łódź, p. 421-426, t. 2, Piątek Trzynastego Wydawnictwo 2005, ISBN 837415-069-6, 711 s., 2 t., 23,5 cm

A. Gersho, ―Advances in speech and audio compression‖, Proc. IEEE, 82, June 1994.

Lawreace R.Rabiner, Ronald W. Schafer, Digital Processing of Speech singlas, Prentice-Hall, Inc.Englewood Cliffs, New Jersey 07632, Bell Laboratories 1978

T. Robinson, Speech Analysis, Lent Term 1998

W. Hess. Pitch Determination of Speech Signals. Springer-Verlag, 1983.

D. Gerhard. Pitch extraction and fundamental frequency: History and currenttechniques. Technical Report TR-CS 2003-06, Department of Computer ScienceUniversity of Regina, Regina, Saskatchewan, CANADA S4S 0A2, november 2003

http://www.birds.cornell.edu/brp/raven/RavenTestimonials.html 2013


Refbacks

  • There are currently no refbacks.


ISSN: 0353-3670 (Print)

ISSN: 2217-5997 (Online)

COBISS.SR-ID 12826626