Template-Based Vibrato Analysis of Music Signals

This is the accompanying website for the paper:

  1. Jonathan Driedger, Stefan Balke, Sebastian Ewert, and Meinard Müller
    Template-Based Vibrato Analysis of Music Signals
    In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR): 239–245, 2016. PDF Demo
    @inproceedings{DriedgerBEM16_Vibrato_ISMIR,
    author    = {Jonathan Driedger and Stefan Balke and Sebastian Ewert and Meinard M{\"u}ller},
    title     = {Template-Based Vibrato Analysis of Music Signals},
    booktitle = {Proceedings of the International Society for Music Information Retrieval Conference  ({ISMIR})},
    address   = {New York, USA},
    year      = {2016},
    pages     = {239--245},
    url-pdf   = {2016_DriedgerBEM_VibratoDetection_ISMIR_ePrint.pdf},
    url-demo = {https://www.audiolabs-erlangen.de/resources/MIR/2016-ISMIR-Vibrato}
    }

Abstract

teaser

The automated analysis of vibrato in complex music signals is a highly challenging task. A common strategy is to proceed in a two-step fashion. First, a fundamental frequency (F0) trajectory for the musical voice that is likely to exhibit vibrato is estimated. In a second step, the trajectory is then analyzed with respect to periodic frequency modulations. As a major drawback, however, such a method cannot recover from errors made in the inherently difficult first step, which severely limits the performance during the second step. In this work, we present a novel vibrato analysis approach that avoids the first error-prone F0-estimation step. Our core idea is to perform the analysis directly on a signal's spectrogram representation where vibrato is evident in the form of characteristic spectro-temporal patterns. We detect and parameterize these patterns by locally comparing the spectrogram with a predefined set of vibrato templates. Our systematic experiments indicate that this approach is more robust than F0-based strategies.

Dataset

All audio files and annotations used in our paper: [.zip]

Evaluation: Vibrato Detection

Here you find all results of our vibrato detection experiment from Section 3.1.

Example: Sound On Sound Demo - Mystery

Click the button in the middle to activate the player.

Mystery_MikeSenior_excerpt_mix_0dB

Example: Giselle - You

Click the button in the middle to activate the player.

Giselle_You_excerpt_mix_0dB

Example: Leaf - Full

Click the button in the middle to activate the player.

Leaf_Full_excerpt_mix_0dB

Example: Phre The Eon - Everybody is Falling Apart

Click the button in the middle to activate the player.

PhreTheEon_EverybodysFallinApart_excerpt_mix_0dB

Example: Secretariat - Borderline

Click the button in the middle to activate the player.

Secretariat_Borderline_excerpt_mix_0dB

Example: Sunshine Garcia Band - For I Am The Moon

Click the button in the middle to activate the player.

SunshineGarciaBand_ForIAmTheMoon_excerpt_mix_0dB

Example: Angela Thomas Wade - Milk Cow Blues

Click the button in the middle to activate the player.

AngelaThomasWade_MilkCowBlues_excerpt_mix_0dB

Example: Triviul - Dorothy

Click the button in the middle to activate the player.

Triviul_Dorothy_excerpt_mix_0dB

Example: Funny Valentines - Sleigh Ride

Click the button in the middle to activate the player.

FunnyValentines_SleighRide_excerpt_mix_0dB

Evaluation: Vibrato Analysis

Click the button in the middle to activate the player.

testSignal_vibratoAnalysis