Pub Date : 2019-01-24DOI: 10.1109/MMRP.2019.8665373
Guillaume Doras, P. Esling, G. Peeters
Estimation of dominant melody in polyphonic music remains a difficult task, even though promising breakthroughs have been done recently with the introduction of the Harmonic CQT and the use of fully convolutional networks. In this paper, we build upon this idea and describe how U-Net- a neural network originally designed for medical image segmentation - can be used to estimate the dominant melody in polyphonic audio. We propose in particular the use of an original layer-by-layer sequential training method, and show that this method used along with careful training data conditioning improve the results compared to plain convolutional networks.
{"title":"On the Use of U-Net for Dominant Melody Estimation in Polyphonic Music","authors":"Guillaume Doras, P. Esling, G. Peeters","doi":"10.1109/MMRP.2019.8665373","DOIUrl":"https://doi.org/10.1109/MMRP.2019.8665373","url":null,"abstract":"Estimation of dominant melody in polyphonic music remains a difficult task, even though promising breakthroughs have been done recently with the introduction of the Harmonic CQT and the use of fully convolutional networks. In this paper, we build upon this idea and describe how U-Net- a neural network originally designed for medical image segmentation - can be used to estimate the dominant melody in polyphonic audio. We propose in particular the use of an original layer-by-layer sequential training method, and show that this method used along with careful training data conditioning improve the results compared to plain convolutional networks.","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126673666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Workshop Organization MMRP 2019","authors":"","doi":"10.1109/mmrp.2019.00006","DOIUrl":"https://doi.org/10.1109/mmrp.2019.00006","url":null,"abstract":"","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117267264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.1109/MMRP.2019.8665380
L. Turchet, P. Kudumakis
Smart musical instruments are an emerging category of musical instruments characterized by sensors, actuators, wireless connectivity, and embedded intelligence. To date, a topic that has received remarkably little attention in smart musical instruments research is that of defining an interoperable file format for the exchange of content produced by this class of instruments. In this paper we preliminary investigate the design of a format specific to smart musical instruments but that at the same time enables interoperability with other devices. We adopted a participatory design methodology consisting of a set of interviews with studio producers. The purpose of such interviews was that of identifying a set of use cases for a format encoding data generated by smart musical instruments, with the end goal of gathering requirements for its design.
{"title":"Requirements for a File Format for Smart Musical Instruments","authors":"L. Turchet, P. Kudumakis","doi":"10.1109/MMRP.2019.8665380","DOIUrl":"https://doi.org/10.1109/MMRP.2019.8665380","url":null,"abstract":"Smart musical instruments are an emerging category of musical instruments characterized by sensors, actuators, wireless connectivity, and embedded intelligence. To date, a topic that has received remarkably little attention in smart musical instruments research is that of defining an interoperable file format for the exchange of content produced by this class of instruments. In this paper we preliminary investigate the design of a format specific to smart musical instruments but that at the same time enables interoperability with other devices. We adopted a participatory design methodology consisting of a set of interviews with studio producers. The purpose of such interviews was that of identifying a set of use cases for a format encoding data generated by smart musical instruments, with the end goal of gathering requirements for its design.","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127590520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.1109/MMRP.2019.8665369
M. Queiroz, Rodrigo Borges
This paper introduces a novel chroma-based harmonic feature called Chroma Interval Content (CIC), which extends Directional Interval Content (DIC) vectors to audio data. This feature represents key-independent harmonic progressions, but unlike the Dynamic Chroma feature vector it represents pitch-class energy motions based on a symbolic voice-leading approach, and can be computed more efficiently (in time $mathcal{O}(Nlog N)$ as opposed to $mathcal{O}(N^{2}))$. We present theoretical properties of Chroma Interval Content vectors and explore the expressive power of CIC both in representing isolated chord progressions, establishing links to its symbolic counterpart DIC, as well as in specific harmony-related MIR tasks, such as key-independent search for chord progressions and classification of music datasets according to harmonic diversity.
{"title":"Chroma Interval Content as a Key-Independent Harmonic Progression Feature","authors":"M. Queiroz, Rodrigo Borges","doi":"10.1109/MMRP.2019.8665369","DOIUrl":"https://doi.org/10.1109/MMRP.2019.8665369","url":null,"abstract":"This paper introduces a novel chroma-based harmonic feature called Chroma Interval Content (CIC), which extends Directional Interval Content (DIC) vectors to audio data. This feature represents key-independent harmonic progressions, but unlike the Dynamic Chroma feature vector it represents pitch-class energy motions based on a symbolic voice-leading approach, and can be computed more efficiently (in time $mathcal{O}(Nlog N)$ as opposed to $mathcal{O}(N^{2}))$. We present theoretical properties of Chroma Interval Content vectors and explore the expressive power of CIC both in representing isolated chord progressions, establishing links to its symbolic counterpart DIC, as well as in specific harmony-related MIR tasks, such as key-independent search for chord progressions and classification of music datasets according to harmonic diversity.","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126526922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.1109/MMRP.2019.8665379
R. Swaminathan, Alexander Lerch
Singing Voice Separation (SVS) attempts to separate the predominant singing voice from a polyphonic musical mixture. In this paper, we investigate the effect of introducing attribute-specific information, namely, the frame level vocal activity information as an augmented feature input to a Deep Neural Network performing the separation. Our study considers two types of inputs, i.e, a ground-truth based ‘oracle’ input and labels extracted by a state-of-the-art model for singing voice activity detection in polyphonic music. We show that the separation network informed of vocal activity learns to differentiate between vocal and nonvocal regions. Such a network thus reduces interference and artifacts better compared to the network agnostic to this side information. Results on the MIR1K dataset show that informing the separation network of vocal activity improves the separation results consistently across all the measures used to evaluate the separation quality.
{"title":"Improving Singing Voice Separation Using Attribute-Aware Deep Network","authors":"R. Swaminathan, Alexander Lerch","doi":"10.1109/MMRP.2019.8665379","DOIUrl":"https://doi.org/10.1109/MMRP.2019.8665379","url":null,"abstract":"Singing Voice Separation (SVS) attempts to separate the predominant singing voice from a polyphonic musical mixture. In this paper, we investigate the effect of introducing attribute-specific information, namely, the frame level vocal activity information as an augmented feature input to a Deep Neural Network performing the separation. Our study considers two types of inputs, i.e, a ground-truth based ‘oracle’ input and labels extracted by a state-of-the-art model for singing voice activity detection in polyphonic music. We show that the separation network informed of vocal activity learns to differentiate between vocal and nonvocal regions. Such a network thus reduces interference and artifacts better compared to the network agnostic to this side information. Results on the MIR1K dataset show that informing the separation network of vocal activity improves the separation results consistently across all the measures used to evaluate the separation quality.","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131811416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Federico Avanzini, University of Milan, Italy Adriano Baratè, University of Milan, Italy Isabel Barbancho, Universidad de Malaga, Spain Emilios Cambouropoulos, Aristotle University of Thessaloniki, Greece Michael Cohen, University of Aizu, Japan Shlomo Dubnov, University of California San Diego, USA Douglas Keislar, Computer Music Journal, USA Luca Andrea Ludovico, University of Milan, Italy Alan Marsden, Lancaster University, United Kingdom Davide Andrea Mauro, Marshall University, USA Stavros Ntalampiras, University of Milan, Italy Stephen Travis Pope, HeavenEverywhere Media, Birdentifier LLC, USA Giorgio Presti, University of Milan, Italy Curtis Roads, University of California Santa Barbara, USA Antonio Rodà, University of Padova, Italy Perry Roland, Music Encoding Initiative Stefania Serafin, Aalborg University, Denmark Federico Simonetta, University of Milan, Italy Bob Sturm, Royal Institute of Technology KTH, Sweden
{"title":"Reviewers MMRP 2019","authors":"A. Baratè, I. Barbancho","doi":"10.1109/mmrp.2019.00008","DOIUrl":"https://doi.org/10.1109/mmrp.2019.00008","url":null,"abstract":"Federico Avanzini, University of Milan, Italy Adriano Baratè, University of Milan, Italy Isabel Barbancho, Universidad de Malaga, Spain Emilios Cambouropoulos, Aristotle University of Thessaloniki, Greece Michael Cohen, University of Aizu, Japan Shlomo Dubnov, University of California San Diego, USA Douglas Keislar, Computer Music Journal, USA Luca Andrea Ludovico, University of Milan, Italy Alan Marsden, Lancaster University, United Kingdom Davide Andrea Mauro, Marshall University, USA Stavros Ntalampiras, University of Milan, Italy Stephen Travis Pope, HeavenEverywhere Media, Birdentifier LLC, USA Giorgio Presti, University of Milan, Italy Curtis Roads, University of California Santa Barbara, USA Antonio Rodà, University of Padova, Italy Perry Roland, Music Encoding Initiative Stefania Serafin, Aalborg University, Denmark Federico Simonetta, University of Milan, Italy Bob Sturm, Royal Institute of Technology KTH, Sweden","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114429290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.1109/MMRP.2019.8665381
A. Baratè, G. Haus, L. A. Ludovico
This paper aims to provide an analytical comparison among the most relevant representation formats that support multi-layer descriptions of music content, namely IEEE 1599, Music Encoding Initiative, and MusicXML/MNX. After remarking the technical characteristics of such formats and highlighting their similarities and differences, we will try to shed light on their future, so as to understand the current trends in digital representation of music and multimedia.
{"title":"State of the Art and Perspectives in Multi-Layer Formats for Music Representation","authors":"A. Baratè, G. Haus, L. A. Ludovico","doi":"10.1109/MMRP.2019.8665381","DOIUrl":"https://doi.org/10.1109/MMRP.2019.8665381","url":null,"abstract":"This paper aims to provide an analytical comparison among the most relevant representation formats that support multi-layer descriptions of music content, namely IEEE 1599, Music Encoding Initiative, and MusicXML/MNX. After remarking the technical characteristics of such formats and highlighting their similarities and differences, we will try to shed light on their future, so as to understand the current trends in digital representation of music and multimedia.","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114180046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.1109/MMRP.2019.8665367
Filippo Carnovalini, A. Rodà
When analyzing scores, musicologists often use multilayered representations to describe different importance levels of notes and chords, according to hierarchical musical structures. These structures are believed to represent the composer's mental representation as well as the listeners' perception of the piece. Thus, in the context of automated music generation, this kind of information can be of great use to model both the composition itself and its expressive performance. In this paper one computational method to perform this kind of analysis is described. Its implementation is then used to generate short musical phrases according to a hierarchical structure that is also used to model the performance of these melodies.
{"title":"A Multilayered Approach to Automatic Music Generation and Expressive Performance","authors":"Filippo Carnovalini, A. Rodà","doi":"10.1109/MMRP.2019.8665367","DOIUrl":"https://doi.org/10.1109/MMRP.2019.8665367","url":null,"abstract":"When analyzing scores, musicologists often use multilayered representations to describe different importance levels of notes and chords, according to hierarchical musical structures. These structures are believed to represent the composer's mental representation as well as the listeners' perception of the piece. Thus, in the context of automated music generation, this kind of information can be of great use to model both the composition itself and its expressive performance. In this paper one computational method to perform this kind of analysis is described. Its implementation is then used to generate short musical phrases according to a hierarchical structure that is also used to model the performance of these melodies.","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131923117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Workshop Support MMRP 2019","authors":"","doi":"10.1109/mmrp.2019.00009","DOIUrl":"https://doi.org/10.1109/mmrp.2019.00009","url":null,"abstract":"","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129632956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gérard Assayag, IRCAM Research Lab, France Isabel Barbancho, Universidad de Málaga, Spain Emilios Cambouropoulos, Aristotle University of Thessaloniki, Greece Antonio Camurri, University of Genoa, Italy Michael Cohen, University of Aizu, Japan Shlomo Dubnov, University of California San Diego, USA Goffredo Haus, University of Milan, Italy Douglas Keislar, Computer Music Journal, MIT Press, USA Marc Leman, Ghent University, Belgium Alan Marsden, Lancaster University, United Kingdom Davide Andrea Mauro, Marshall University, USA Stavros Ntalampiras, University of Milan, Italy Stephen Trevis Pope, HeavenEverywhere, CA, USA Curtis Roads, University of California Santa Barbara, USA Perry Roland, Music Encoding Initiative Stefania Serafin, Aalborg University Copenhagen, Denmark Bob Sturm, Royal Institute of Technology KTH, Sweden
{"title":"Scientific Committee MMRP 2019","authors":"I. Barbancho","doi":"10.1109/mmrp.2019.00007","DOIUrl":"https://doi.org/10.1109/mmrp.2019.00007","url":null,"abstract":"Gérard Assayag, IRCAM Research Lab, France Isabel Barbancho, Universidad de Málaga, Spain Emilios Cambouropoulos, Aristotle University of Thessaloniki, Greece Antonio Camurri, University of Genoa, Italy Michael Cohen, University of Aizu, Japan Shlomo Dubnov, University of California San Diego, USA Goffredo Haus, University of Milan, Italy Douglas Keislar, Computer Music Journal, MIT Press, USA Marc Leman, Ghent University, Belgium Alan Marsden, Lancaster University, United Kingdom Davide Andrea Mauro, Marshall University, USA Stavros Ntalampiras, University of Milan, Italy Stephen Trevis Pope, HeavenEverywhere, CA, USA Curtis Roads, University of California Santa Barbara, USA Perry Roland, Music Encoding Initiative Stefania Serafin, Aalborg University Copenhagen, Denmark Bob Sturm, Royal Institute of Technology KTH, Sweden","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132408792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：