In this paper, HNM (harmonic plus noise model) is enhanced and used to design a scheme for synthesizing Mandarin singing voice. Enhancements made include synthesizing signals with...
This paper studies the influence of n-gram language models in the recognition of sung phonemes and words. We train uni-, bi-, and trigram language models for phonemes and bi- and...
Recently, several music information retrieval (MIR) systems have been developed which retrieve musical pieces by the user’s singing voice. All of these systems use only the melo...
In this paper we present an example of the use of the singing voice as a controller for digital music synthesis. The analysis of the voice with spectral processing techniques, der...
The automatic analysis of singing from music is an important and challenging issue within the research target of content-based retrieval of music information. As part of this rese...