Meinard Müller | Friedrich-Alexander-Universität Erlangen-Nürnberg (original) (raw)

Meinard  Müller

Meinard Müller studied mathematics and computer science at Bonn University, Germany. Since September 2012, he holds a professorship at the International Audio Laboratories Erlangen, a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS. His current research interests include music processing, audio signal processing, and music information retrieval. He is author of the textbook "Fundamentals of Music Processing" (www.music-processing.de).

less

Uploads

Papers by Meinard Müller

Research paper thumbnail of Towards Leitmotif Activity Detection in Opera Recordings

Transactions of the International Society for Music Information Retrieval, 2021

Research paper thumbnail of Computational Corpus Analysis: A Case Study on Jazz Solos

International Symposium/Conference on Music Information Retrieval, 2018

Research paper thumbnail of Investigating CNN-Based Instrument Family Recognition for Western Classical Music Recordings

International Symposium/Conference on Music Information Retrieval, Jun 27, 2019

Research paper thumbnail of Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond

Research paper thumbnail of Using Activation Functions for Improving Measure-Level Audio Synchronization

Zenodo (CERN European Organization for Nuclear Research), Dec 4, 2022

Research paper thumbnail of Learning Pitch-Class Representations from Score-Audio Pairs of Classical Music

Zenodo (CERN European Organization for Nuclear Research), Nov 7, 2021

Research paper thumbnail of Tutorial TUT01 "Automatisierte Methoden der Musikverarbeitung

Research paper thumbnail of A swingogram representation for tracking micro-rhythmic variation in jazz performances

Journal of New Music Research, Aug 30, 2017

Research paper thumbnail of Reverse Engineering the Amen Break — Score-Informed Separation and Restoration Applied to Drum Recordings

IEEE/ACM transactions on audio, speech, and language processing, Sep 1, 2016

Research paper thumbnail of A Review of Automatic Drum Transcription

IEEE/ACM transactions on audio, speech, and language processing, Sep 1, 2018

Research paper thumbnail of Die Oper als Multimediaszenario

GI-Jahrestagung, 2017

Musik lässt sich durch die Vielzahl an möglichen Darstellungs-und Datenformen als Multimediaszena... more Musik lässt sich durch die Vielzahl an möglichen Darstellungs-und Datenformen als Multimediaszenario auffassen: Neben der eigentlichen Musikaufnahme gibt es eine Vielzahl von weiteren Medienobjekten (z. B. Videoaufnahmen, Gesangstexte oder Notentexte), die Musik auf unterschiedliche Arten beschreiben. Im Zuge der Digitalisierung werden viele dieser Medienobjekte heutzutage frei im Internet verfügbar gemacht. Dabei werden die Objekte häufig einzeln betrachtet, obwohl sich zwischen ihnen musikalische Verknüpfungen herstellen ließen. Diese Verknüpfungen können dazu genutzt werden, um neue Arten der Navigation in der Musik zu ermöglichen, oder vorhandene Medienobjekte mit zusätzlichen Informationen anzureichern. In diesem Artikel modellieren wir exemplarisch anhand der Oper "Die Walküre" von Richard Wagner diese musikalischen Verknüpfungen mittels werkbezogener Annotationen, die in einem geeigneten Datenbankschema abgebildet werden. Basierend auf diesem Modell präsentieren wir dann einen webbasierten Demonstrator, der die wechselseitigen Verknüpfungen zwischen den Medienobjekten zusammenfügt und in einer graphischen Benutzeroberfläche für den Nutzer zugänglich macht.

Research paper thumbnail of Consecutive positive detectable matrices and group testing for consecutive positives

Discrete Mathematics, Mar 1, 2004

Research paper thumbnail of Multisensor-fusion for 3D full-body human motion capture

Research paper thumbnail of Unifying Local and Global Methods for Harmonic-Percussive Source Separation

This paper addresses the separation of drums from music recordings, a task closely related to har... more This paper addresses the separation of drums from music recordings, a task closely related to harmonic-percussive source separation (HPSS). In previous works, two families of algorithms have been prominently applied to this problem. They are based either on local filtering and diffusion schemes, or on global low-rank models. In this paper, we propose to combine the advantages of both paradigms. To this end, we use a local approach based on Kernel Additive Modeling (KAM) to extract an initial guess for the percussive and harmonic parts. Subsequently, we use Non-Negative Matrix Factorization (NMF) with soft activation constraints as a global approach to jointly enhance both estimates. As an additional contribution, we introduce a novel constraint for enhancing percussive activations and a scheme for estimating the percussive weight of NMF components. Throughout the paper, we use a real-world music example to illustrate the ideas behind our proposed method. Finally, we report promising BSS Eval results achieved with the publicly available test corpora ENST-Drums and QUASI, which contain isolated drum and accompaniment tracks.

Research paper thumbnail of Investigating style evolution of Western classical music: A computational approach

Musicae Scientiae, Mar 7, 2018

Research paper thumbnail of Towards Cross-Modal Comparison of Human Motion Data

Research paper thumbnail of Erasure-resilient codes from affine spaces

Discrete Applied Mathematics, Sep 1, 2004

Research paper thumbnail of Constant Weight Conflict-Avoiding Codes

SIAM Journal on Discrete Mathematics, 2008

Research paper thumbnail of Combinatorial problems arising from pooling designs for dna library screening

Research paper thumbnail of Towards Measuring Intonation Quality of Choir Recordings: A Case Study on Bruckner's Locus Iste

International Symposium/Conference on Music Information Retrieval, 2019

Research paper thumbnail of Towards Leitmotif Activity Detection in Opera Recordings

Transactions of the International Society for Music Information Retrieval, 2021

Research paper thumbnail of Computational Corpus Analysis: A Case Study on Jazz Solos

International Symposium/Conference on Music Information Retrieval, 2018

Research paper thumbnail of Investigating CNN-Based Instrument Family Recognition for Western Classical Music Recordings

International Symposium/Conference on Music Information Retrieval, Jun 27, 2019

Research paper thumbnail of Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond

Research paper thumbnail of Using Activation Functions for Improving Measure-Level Audio Synchronization

Zenodo (CERN European Organization for Nuclear Research), Dec 4, 2022

Research paper thumbnail of Learning Pitch-Class Representations from Score-Audio Pairs of Classical Music

Zenodo (CERN European Organization for Nuclear Research), Nov 7, 2021

Research paper thumbnail of Tutorial TUT01 "Automatisierte Methoden der Musikverarbeitung

Research paper thumbnail of A swingogram representation for tracking micro-rhythmic variation in jazz performances

Journal of New Music Research, Aug 30, 2017

Research paper thumbnail of Reverse Engineering the Amen Break — Score-Informed Separation and Restoration Applied to Drum Recordings

IEEE/ACM transactions on audio, speech, and language processing, Sep 1, 2016

Research paper thumbnail of A Review of Automatic Drum Transcription

IEEE/ACM transactions on audio, speech, and language processing, Sep 1, 2018

Research paper thumbnail of Die Oper als Multimediaszenario

GI-Jahrestagung, 2017

Musik lässt sich durch die Vielzahl an möglichen Darstellungs-und Datenformen als Multimediaszena... more Musik lässt sich durch die Vielzahl an möglichen Darstellungs-und Datenformen als Multimediaszenario auffassen: Neben der eigentlichen Musikaufnahme gibt es eine Vielzahl von weiteren Medienobjekten (z. B. Videoaufnahmen, Gesangstexte oder Notentexte), die Musik auf unterschiedliche Arten beschreiben. Im Zuge der Digitalisierung werden viele dieser Medienobjekte heutzutage frei im Internet verfügbar gemacht. Dabei werden die Objekte häufig einzeln betrachtet, obwohl sich zwischen ihnen musikalische Verknüpfungen herstellen ließen. Diese Verknüpfungen können dazu genutzt werden, um neue Arten der Navigation in der Musik zu ermöglichen, oder vorhandene Medienobjekte mit zusätzlichen Informationen anzureichern. In diesem Artikel modellieren wir exemplarisch anhand der Oper "Die Walküre" von Richard Wagner diese musikalischen Verknüpfungen mittels werkbezogener Annotationen, die in einem geeigneten Datenbankschema abgebildet werden. Basierend auf diesem Modell präsentieren wir dann einen webbasierten Demonstrator, der die wechselseitigen Verknüpfungen zwischen den Medienobjekten zusammenfügt und in einer graphischen Benutzeroberfläche für den Nutzer zugänglich macht.

Research paper thumbnail of Consecutive positive detectable matrices and group testing for consecutive positives

Discrete Mathematics, Mar 1, 2004

Research paper thumbnail of Multisensor-fusion for 3D full-body human motion capture

Research paper thumbnail of Unifying Local and Global Methods for Harmonic-Percussive Source Separation

This paper addresses the separation of drums from music recordings, a task closely related to har... more This paper addresses the separation of drums from music recordings, a task closely related to harmonic-percussive source separation (HPSS). In previous works, two families of algorithms have been prominently applied to this problem. They are based either on local filtering and diffusion schemes, or on global low-rank models. In this paper, we propose to combine the advantages of both paradigms. To this end, we use a local approach based on Kernel Additive Modeling (KAM) to extract an initial guess for the percussive and harmonic parts. Subsequently, we use Non-Negative Matrix Factorization (NMF) with soft activation constraints as a global approach to jointly enhance both estimates. As an additional contribution, we introduce a novel constraint for enhancing percussive activations and a scheme for estimating the percussive weight of NMF components. Throughout the paper, we use a real-world music example to illustrate the ideas behind our proposed method. Finally, we report promising BSS Eval results achieved with the publicly available test corpora ENST-Drums and QUASI, which contain isolated drum and accompaniment tracks.

Research paper thumbnail of Investigating style evolution of Western classical music: A computational approach

Musicae Scientiae, Mar 7, 2018

Research paper thumbnail of Towards Cross-Modal Comparison of Human Motion Data

Research paper thumbnail of Erasure-resilient codes from affine spaces

Discrete Applied Mathematics, Sep 1, 2004

Research paper thumbnail of Constant Weight Conflict-Avoiding Codes

SIAM Journal on Discrete Mathematics, 2008

Research paper thumbnail of Combinatorial problems arising from pooling designs for dna library screening

Research paper thumbnail of Towards Measuring Intonation Quality of Choir Recordings: A Case Study on Bruckner's Locus Iste

International Symposium/Conference on Music Information Retrieval, 2019

Research paper thumbnail of Beiträge zur Algorithmik verallgemeinerter diskreter Fouriertransformationen

Research paper thumbnail of Beiträge zur Algorithmik verallgemeinerter diskreter Fouriertransformationen

Log In