15-12-2012, 05:21 PM
IMPROVING MELODY EXTRACTION USING PROBABILISTIC LATENT COMPONENT ANALYSIS
IMPROVING MELODY.pdf (Size: 422.27 KB / Downloads: 31)
ABSTRACT
We propose a new approach for automatic melody extraction
from polyphonic audio, based on Probabilistic Latent Component
Analysis (PLCA).An audio signal is first divided into vocal and nonvocal
segments using a trained Gaussian Mixture Model (GMM)
classifier. A statistical model of the non-vocal segments of the signal
is then learned adaptively from this particular input music by PLCA.
This model is then employed to remove the accompaniment from the
mixture, leaving mainly the vocal components. The melody line is
extracted from the vocal components using an auto-correlation algorithm.
Quantitative evaluation shows that the new system performs
significantly better than two existing melody extraction algorithms
for polyphonic single-channel mixtures.
INTRODUCTION
Melody is one of the most basic and easily recognizable traits of musical
signals. The main melody of a song is usually defined as the
pitch sequence that a human listener is most likely to perceive and
associate with that piece of music. Knowing the melody of a song is
useful in numerous applications, including music recognition, analysis
of musical structure, and genre classification. Although humans
have a natural ability to identify and isolate the main melody from
polyphonic music, automatic extraction of melody by a machine remains
a challenging task.
In polyphonic music, there are multiple instruments and sound
sources playing simultaneously. Determining the main melody from
such an audio recording involves extracting a single dominant pitch
contour out of a mixture of concurrent spectral events. In this paper,
melody is defined as the pitch contour of the lead vocal in a song.
This is a reasonable assumption since when music contains a singing
voice, many people remember and recognize that piece of music by
the melody line of the lead vocal part.
CONCLUSION
We developed an unsupervised algorithm for melody extraction from
single channel polyphonic music. Our system assumes no prior information
on the type or the number of instruments in the mixture.
We introduce Probabilistic Latent Component Analysis to model
the accompaniment and lead vocal adaptively. Experimental results
show that the PLCA model successfully suppressed the background
music in the mixture audio. Quantitative evaluation showed our proposed
algorithm is significantly better than two other melody extraction
algorithms. The proposed system can be easily extended to
extract the melody from a lead instrument or to a singing voice separation
system. Although the proposed method does not require pretrained
instrument models, its performance indeed depends on the
performance of the singing voice detection.