Title:

Locating Singing Voice Segments within Music Signals

Author(s):

Berenzweig, Adam
Ellis, Daniel P. W.

Date:

2001

Type:

Articles

Department:

Electrical Engineering

Permanent URL:

http://hdl.handle.net/10022/AC:P:13799

Book/Journal Title:

Proceedings of the 2001 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics: October 21-24, 2001, Mohonk Mountain House, New Paltz, New York, USA

Publisher:

IEEE

Publisher Location:

Piscataway, N.J.

Abstract:

A sung vocal line is the prominent feature of much popular music. It would be useful to locate the portions of a musical track during which the vocals are present reliably, both as a 'signature' of the piece and as a precursor to automatic recognition of lyrics. We approach this problem by using the acoustic classifier of a speech recognizer as a detector for speech-like sounds. Although singing (including a musical background) is a relatively poor match to an acoustic model trained on normal speech, we propose various statistics of the classifier's output in order to discriminate singing from instrumental accompaniment. A simple HMM allows us to find a best labeling sequence for this uncertain data. On a test set of forty 15 second excerpts of randomly-selected music, our classifier achieved around 80% classification accuracy at the frame level. The utility of different features, and our plans for eventual lyrics recognition, are discussed.

Subject(s):

Electrical engineering
Artificial intelligence

DOI:

10.1109/ASPAA.2001.969557

Item views:

12

Metadata:

description

View | Download