Guslar: A framework for automated singing voice correction

Author

Azarov, Elias ; Vashkevich, Maxim ; Petrovsky, Alexander

Author_Institution

Dept. of Comput. Eng., Belarusian State Univ. of Inf. & Radioelectron., Minsk, Belarus

fYear

2014

fDate

4-9 May 2014

Firstpage

7919

Lastpage

7923

Abstract

The paper presents a solution for singing voice processing that is used in a karaoke application with automated voice correction¹. The intended purpose of the application is to automatically improve user´s performance towards performance of a professional singer by implementation of voice effects such as pitch correction, artificial polyphony, time stretching and other. The proposed framework incorporates a complete processing workflow including analysis, morphing and synthesis. The framework uses an original model of voiced speech which represents each harmonic as a multicomponent function and provides high quality processing in conditions of partial glottalization.

Keywords

humanities; speech processing; speech synthesis; GUSLAR; artificial polyphony; automated singing voice correction; automatic user performance improvement; karaoke application; multicomponent function; partial glottalization; pitch correction; processing workflow; singing voice processing; speech analysis; speech synthesis; time stretching; voice effects; Artificial neural networks; Estimation; Harmonic analysis; Power harmonic filters; Robustness; Speech; Speech processing; singing voice processing; speech analysis; speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on

Conference_Location

Florence

Type

conf

DOI

10.1109/ICASSP.2014.6855142

Filename

6855142