Matija Marolt | University of Ljubljana (original) (raw)
Papers by Matija Marolt
International Symposium/Conference on Music Information Retrieval, 2002
One of the problems encountered in music transcription is to produce an algorithm that detects wh... more One of the problems encountered in music transcription is to produce an algorithm that detects whether a note should be repeated, when a new onset is found during its duration, or not; with other words whether two or more shorter notes should be produced instead of a single longer note. The paper describes our approach to solving this problem, implemented
The paper refers to the national funded project Ethnomuse: digital storage of Slovene folk music ... more The paper refers to the national funded project Ethnomuse: digital storage of Slovene folk music and dance culture . The main scope of the project concerns the development of advanced multimedia applications for various content (folk song, music and dance) and format (image, audio, video, notation, MIDI etc.), and digitisation of the production and postproduction processes that relate to collecting, documenting and archiving of Slovene folk songs, music and dance. The objective of this paper is to discuss the latter, with focus on conceptual design of the flexible data model.
This paper presents a distance learning application currently under development atthe University ... more This paper presents a distance learning application currently under development atthe University of Ljubljana in Slovenia. The basic idea of the application is to joinlearning materials on various topics and written by many teachers in a digitallibrary of courseware. Such digital library provides a basis for creating courses onspecific topics. Our application is based on WWW and Java programminglanguage and
MELECON - IEEE Mediterranean Electrotechnical Conference, 1998
This article presents an architecture of a system for automated transcription of solo piano music... more This article presents an architecture of a system for automated transcription of solo piano music. The final goal is to build a system that will correctly transcribe digital recordings of polyphonic piano music without any additional end-user interaction. The transcription consists of two basic consecutive steps. The first step carries out time-frequency analysis and can be related to low-level auditory
This paper presents our system for transcription of polyphonic piano music - SONIC. SONIC takes a... more This paper presents our system for transcription of polyphonic piano music - SONIC. SONIC takes an audio signal of a piano performance and tries to determine which notes were played by the performer, thus producing a list of notes and note onset times approximately matching the performance. SONIC is composed of three main parts: partial extractor, onset detector and note
As folk songs live largely through oral transmission, there usually is no standard form of a song... more As folk songs live largely through oral transmission, there usually is no standard form of a song - each performance of a folk song may be unique. Different interpretations of the same song are called song variants, all variants of a song belong to the same variant type. In the paper, we explore how various melody-based features relate to folk
Massive multi-agent systems with emergent global behavior represent a new paradigm in designing a... more Massive multi-agent systems with emergent global behavior represent a new paradigm in designing and building program systems for handling complex problems. Emergence, nonlinearity and self-organization of global behavior underpin robustness, flexibility and autonomy of massive multi-agent systems. On the other hand, this makes the traditional design approach difficult, if not impossible. In this paper we will focus on the construction
MELECON - IEEE Mediterranean Electrotechnical Conference, 2002
This paper presents an overview of our researches in the use of connectionist systems for transcr... more This paper presents an overview of our researches in the use of connectionist systems for transcription of polyphonic piano music and concentrates on the issue of onset detection in musical signals. We propose a new technique for detecting onsets in a piano performance. The technique is based on a combination of a bank of auditory filters, a network of integrate-and-fire
This paper presents a brief overview of our researches in the use of connectionist systems for tr... more This paper presents a brief overview of our researches in the use of connectionist systems for transcription of polyphonic piano music and concentrates on the issue of onset detection in musical signals. We propose a technique for detecting onsets in a piano performance, based on a combination of a bank of auditory filters, a network of integrate-and-fire neurons and a
MELECON '98. 9th Mediterranean Electrotechnical Conference. Proceedings (Cat. No.98CH36056), 1998
11th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.02CH37379), 2002
Emergent behavior results in complex systems. Emergent behavior can be observed in various system... more Emergent behavior results in complex systems. Emergent behavior can be observed in various systems a colony of ants, an economy, a brain or a large network of computersthese are all systems with complex emergent behavior. The behavior of a complex y s t m as a whole emerges in a highly nonlinear manner from the behaviors of the low levcl constituent elementary units. This makes traditional linear analysis difficult, if not impossible. In this paper we will focus on emergent properties of massive multiagent systems. we will present how thcsc properties can be utilized to model global behavior of the system.
11th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.02CH37379), 2002
AIenka Kavcic, Marko Privosnik, Matija Marolt and Sasa .Divjak ... Faculty of Computer and Inform... more AIenka Kavcic, Marko Privosnik, Matija Marolt and Sasa .Divjak ... Faculty of Computer and Information Science University of Ljubljana Trzaska 25, 1000 Ljubljana, Slovenia Tel. (+386 1) 47 68 483 Fax. (+386 1) 42 64 647 Email alenka.kavcic@fn.uni-lj.si
The paper presents the development of EthnoMuse: multimedia digital library of Slovenian folk mus... more The paper presents the development of EthnoMuse: multimedia digital library of Slovenian folk music and dance culture. The main scope of the project concerns the digitization of production and post-production processes that relate to collecting, documenting and archiving of folk heritage and development of multimedia applications for various content types (folk song, music and dance) and formats (image, audio, video,
life
Abstract: - Massive multi-agent systems with emergent global behavior represent a new paradigm in... more Abstract: - Massive multi-agent systems with emergent global behavior represent a new paradigm in designing and building program systems for handling complex problems. Emergence, nonlinearity and self-organization of global behavior underpin robustness, flexibility and autonomy of ...
… , 2002. MELECON 2002. …, 2002
On Detecting Note Onsets in Piano Music ... Matija Marolt, Alenka Kavcic, Marko Privosnik, Sasa D... more On Detecting Note Onsets in Piano Music ... Matija Marolt, Alenka Kavcic, Marko Privosnik, Sasa Divjak Faculty of Computer and Information Science, University of Ljubljana Trzaska 25,1000 Ljubljana, Slovenia Phone:(386) 1 4768483: Fax: (386) 1 4264647 ma tij a .mar01 @si. ...
This paper presents a biologically-inspired compositional hierarchical model for MIR. The model c... more This paper presents a biologically-inspired compositional hierarchical model for MIR. The model can be treated as a deep learning model, and poses an alternative to deep architectures based on neural networks. Its main features are generativeness and transparency that allow clear in-sight into concepts learned from the input music signals. The model consists of multiple layers, each is composed of a number of parts. The hierarchical nature of the model corresponds well with the hierarchical structures in music. Parts in lower layers correspond to low-level concepts (e.g. tone partials), while parts in higher layers combine lower-level representations into more complex concepts (tones, chords). The layers are unsupervisedly learned one-by-one from music signals. Parts in each layer are compositions of parts from previous layers based on statistical co-occurrences as the driving force of the learning process. We present the model's structure and compare it to other deep architectu...
International Symposium/Conference on Music Information Retrieval, 2002
One of the problems encountered in music transcription is to produce an algorithm that detects wh... more One of the problems encountered in music transcription is to produce an algorithm that detects whether a note should be repeated, when a new onset is found during its duration, or not; with other words whether two or more shorter notes should be produced instead of a single longer note. The paper describes our approach to solving this problem, implemented
The paper refers to the national funded project Ethnomuse: digital storage of Slovene folk music ... more The paper refers to the national funded project Ethnomuse: digital storage of Slovene folk music and dance culture . The main scope of the project concerns the development of advanced multimedia applications for various content (folk song, music and dance) and format (image, audio, video, notation, MIDI etc.), and digitisation of the production and postproduction processes that relate to collecting, documenting and archiving of Slovene folk songs, music and dance. The objective of this paper is to discuss the latter, with focus on conceptual design of the flexible data model.
This paper presents a distance learning application currently under development atthe University ... more This paper presents a distance learning application currently under development atthe University of Ljubljana in Slovenia. The basic idea of the application is to joinlearning materials on various topics and written by many teachers in a digitallibrary of courseware. Such digital library provides a basis for creating courses onspecific topics. Our application is based on WWW and Java programminglanguage and
MELECON - IEEE Mediterranean Electrotechnical Conference, 1998
This article presents an architecture of a system for automated transcription of solo piano music... more This article presents an architecture of a system for automated transcription of solo piano music. The final goal is to build a system that will correctly transcribe digital recordings of polyphonic piano music without any additional end-user interaction. The transcription consists of two basic consecutive steps. The first step carries out time-frequency analysis and can be related to low-level auditory
This paper presents our system for transcription of polyphonic piano music - SONIC. SONIC takes a... more This paper presents our system for transcription of polyphonic piano music - SONIC. SONIC takes an audio signal of a piano performance and tries to determine which notes were played by the performer, thus producing a list of notes and note onset times approximately matching the performance. SONIC is composed of three main parts: partial extractor, onset detector and note
As folk songs live largely through oral transmission, there usually is no standard form of a song... more As folk songs live largely through oral transmission, there usually is no standard form of a song - each performance of a folk song may be unique. Different interpretations of the same song are called song variants, all variants of a song belong to the same variant type. In the paper, we explore how various melody-based features relate to folk
Massive multi-agent systems with emergent global behavior represent a new paradigm in designing a... more Massive multi-agent systems with emergent global behavior represent a new paradigm in designing and building program systems for handling complex problems. Emergence, nonlinearity and self-organization of global behavior underpin robustness, flexibility and autonomy of massive multi-agent systems. On the other hand, this makes the traditional design approach difficult, if not impossible. In this paper we will focus on the construction
MELECON - IEEE Mediterranean Electrotechnical Conference, 2002
This paper presents an overview of our researches in the use of connectionist systems for transcr... more This paper presents an overview of our researches in the use of connectionist systems for transcription of polyphonic piano music and concentrates on the issue of onset detection in musical signals. We propose a new technique for detecting onsets in a piano performance. The technique is based on a combination of a bank of auditory filters, a network of integrate-and-fire
This paper presents a brief overview of our researches in the use of connectionist systems for tr... more This paper presents a brief overview of our researches in the use of connectionist systems for transcription of polyphonic piano music and concentrates on the issue of onset detection in musical signals. We propose a technique for detecting onsets in a piano performance, based on a combination of a bank of auditory filters, a network of integrate-and-fire neurons and a
MELECON '98. 9th Mediterranean Electrotechnical Conference. Proceedings (Cat. No.98CH36056), 1998
11th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.02CH37379), 2002
Emergent behavior results in complex systems. Emergent behavior can be observed in various system... more Emergent behavior results in complex systems. Emergent behavior can be observed in various systems a colony of ants, an economy, a brain or a large network of computersthese are all systems with complex emergent behavior. The behavior of a complex y s t m as a whole emerges in a highly nonlinear manner from the behaviors of the low levcl constituent elementary units. This makes traditional linear analysis difficult, if not impossible. In this paper we will focus on emergent properties of massive multiagent systems. we will present how thcsc properties can be utilized to model global behavior of the system.
11th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.02CH37379), 2002
AIenka Kavcic, Marko Privosnik, Matija Marolt and Sasa .Divjak ... Faculty of Computer and Inform... more AIenka Kavcic, Marko Privosnik, Matija Marolt and Sasa .Divjak ... Faculty of Computer and Information Science University of Ljubljana Trzaska 25, 1000 Ljubljana, Slovenia Tel. (+386 1) 47 68 483 Fax. (+386 1) 42 64 647 Email alenka.kavcic@fn.uni-lj.si
The paper presents the development of EthnoMuse: multimedia digital library of Slovenian folk mus... more The paper presents the development of EthnoMuse: multimedia digital library of Slovenian folk music and dance culture. The main scope of the project concerns the digitization of production and post-production processes that relate to collecting, documenting and archiving of folk heritage and development of multimedia applications for various content types (folk song, music and dance) and formats (image, audio, video,
life
Abstract: - Massive multi-agent systems with emergent global behavior represent a new paradigm in... more Abstract: - Massive multi-agent systems with emergent global behavior represent a new paradigm in designing and building program systems for handling complex problems. Emergence, nonlinearity and self-organization of global behavior underpin robustness, flexibility and autonomy of ...
… , 2002. MELECON 2002. …, 2002
On Detecting Note Onsets in Piano Music ... Matija Marolt, Alenka Kavcic, Marko Privosnik, Sasa D... more On Detecting Note Onsets in Piano Music ... Matija Marolt, Alenka Kavcic, Marko Privosnik, Sasa Divjak Faculty of Computer and Information Science, University of Ljubljana Trzaska 25,1000 Ljubljana, Slovenia Phone:(386) 1 4768483: Fax: (386) 1 4264647 ma tij a .mar01 @si. ...
This paper presents a biologically-inspired compositional hierarchical model for MIR. The model c... more This paper presents a biologically-inspired compositional hierarchical model for MIR. The model can be treated as a deep learning model, and poses an alternative to deep architectures based on neural networks. Its main features are generativeness and transparency that allow clear in-sight into concepts learned from the input music signals. The model consists of multiple layers, each is composed of a number of parts. The hierarchical nature of the model corresponds well with the hierarchical structures in music. Parts in lower layers correspond to low-level concepts (e.g. tone partials), while parts in higher layers combine lower-level representations into more complex concepts (tones, chords). The layers are unsupervisedly learned one-by-one from music signals. Parts in each layer are compositions of parts from previous layers based on statistical co-occurrences as the driving force of the learning process. We present the model's structure and compare it to other deep architectu...