BEGIN:VCALENDAR VERSION:2.0 PRODID:-//MCAA//Marie Curie Alumni//EN CALSCALE:GREGORIAN METHOD:PUBLISH BEGIN:VEVENT UID:event-23971@www.mariecuriealumni.eu DTSTAMP:20260922T203205Z DTSTART:20210513T220000Z DTEND:20210514T215959Z SUMMARY:Meet My lab: 'Mathematics and Music - A Synergetic Duo for Automati c Music Generation' DESCRIPTION:In its more than 60 year history\, music generation systems hav e never been more popular than today. In this talk\, Prof. Dorien Herrema ns will give a brief history of the unique field of algorithmic compositi on. While there are a number of systems out there\, two main challenges r emain: how do we integrate emotion as well as ensure long term structure in musical pieces. It should come at no surprise that music and emotion a re intrinsically connected. Yet\, computer systems still struggle to trul y capture emotion. Secondly\, while many systems can compose short fragme nts that sound well\, the real challenge is to create complete\, longer p ieces of music with patterns and themes. The MorpheuS system\, a hybrid m achine learning system developed by Prof. Dorien during her MSCA fellowsh ip with Prof. Elaine Chew\, tackles these two challenges. In this talk we will dive into the inner workings of MorpheuS\, as well as listen to a n umber of generated fragments performed by Prof. Elaine Chew. Finally\, we will discuss some recent advances in the field and what respective labs are currently working on.What is this?‘Meet my Lab’ is a virtual meet ing point profiling researchers and their work. The presenters will share their research work and present opportunities for collaboration. The foc us is on interactivity - audience members can ask questions and engage wi th the presenter(s) and with each other.Who can participate?Meet my Lab†™ is explicitly open to the world! We welcome researchers at all career s tages and of all nationalities.Participants should have an interest in in ternational research collaboration!Participation is free of charge. Seats will be allocated on a first come first served basis.***Short synopsis o f respective work and collaborative workDorien Herremans'\; recent wo rk has focused on creating controllable music generation systems using de ep learning technologies. One challenge in particular - generating music with steerable emotion - has been central in her research. When it comes to affect and emotion\, computer models still do not compare to humans. U sing affective computing techniques and deep learning\, Dorien'\;s te am has built models that learn to predict perceived emotion from music. T hese models are then used to generate new fragments in a controllable man ner\, so that users can steer the desired arousal/valence level or tensio n in newly generated music. Other challenges tackled by Dorien'\;s te am include ensuring repeated themes in music\, automatic music transcript ion\, and novel music representations.Elaine Chew&\;nbsp\;is known for inventing the spiral array model\, a geometric representation for tonali ty. Her research focuses on the mathematical and computational modelling of musical structures in music\, with special interest in expressive perf ormance\, and electrocardiographic sequences. Applications include modell ing of music performance\, AI music generation\, music-heart-brain intera ctions\, and computational arrhythmia research. She is author of numerous academic publications and centre of one of 9 publication clusters having ≥5 women in the international Music Information Retrieval community (I SMIR 2016 infometric study). As a pianist\, she integrates her research i nto concert-conversations that showcase scientific visualisations and lab -grown compositions.Together\, Herremans and Chew worked on the MorpheuS automatic music composition system. To guide MorpheuS'\; music genera tion\, they designed and implemented a harmonic tension model based on th e spiral array. The system learns rhythms and harmonic tension profiles f rom a template piece to generate music with long term structure. MorpheuS '\; creations have been featured on Channel News Asia'\;s televis ion program on "\;Algorithms: Part 1 - Rage Against The Machine"\ ;\, where it was pitted against a human composer and had its output (base d on the first of Three Pieces for String Quartet by Stravinsky) performe d by members of the Singapore Symphony Orchestra. Chew has also performed MorpheuS pieces at concerts in venues in Cambridge (MA)\, London\, San F rancisco\, and Stanford.&\;nbsp\;\nRead more: https://www.mariecurieal umni.eu/events/meet-my-lab-mathematics-and-music-synergetic-duo-automatic -music-generation X-ALT-DESC;FMTTYPE=text/html:In its more than 60 year history, music generation systems have never been more popular than today. In this talk, Prof. Dorien Herremans will give a brief history of the unique field of algorithmic composition. While there are a number of systems out there, two main challenges remain: how do we integrate emoti on as well as ensure long term structure in musical pieces. It should com e at no surprise that music and emotion are intrinsically connected. Yet, computer systems still struggle to truly capture emotion. Secondly, whil e many systems can compose short fragments that sound well, the real chal lenge is to create complete, longer pieces of music with patterns and the mes. The MorpheuS system, a hybrid machine learning system developed by P rof. Dorien during her MSCA fellowship with Prof. Elaine Chew, tackles th ese two challenges. In this talk we will dive into the inner workings of MorpheuS, as well as listen to a number of generated fragments performed by Prof. Elaine Chew. Finally, we will discuss some recent advances in th e field and what respective labs are currently working on.What is this?†˜Meet my Lab’ is a virtual meeting point profiling researchers and thei r work. The presenters will share their research work and present opportu nities for collaboration. The focus is on interactivity - audience member s can ask questions and engage with the presenter(s) and with each other. Who can participate?Meet my Lab’ is explicitly open to the world! We we lcome researchers at all career stages and of all nationalities.Participa nts should have an interest in international research collaboration!Parti cipation is free of charge. Seats will be allocated on a first come first served basis.***Short synopsis of respective work and collaborative work Dorien Herremans' recent work has focused on creating controllab le music generation systems using deep learning technologies. One challen ge in particular - generating music with steerable emotion - has been cen tral in her research. When it comes to affect and emotion, computer model s still do not compare to humans. Using affective computing techniques an d deep learning, Dorien's team has built models that learn to pr edict perceived emotion from music. These models are then used to generat e new fragments in a controllable manner, so that users can steer the des ired arousal/valence level or tension in newly generated music. Other cha llenges tackled by Dorien's team include ensuring repeated theme s in music, automatic music transcription, and novel music representation s.Elaine Chew is known for inventing the spiral array model, a geometric representation for tonality. Her research focuses on the mat hematical and computational modelling of musical structures in music, wit h special interest in expressive performance, and electrocardiographic se quences. Applications include modelling of music performance, AI music ge neration, music-heart-brain interactions, and computational arrhythmia re search. She is author of numerous academic publications and centre of one of 9 publication clusters having ≥5 women in the international Music I nformation Retrieval community (ISMIR 2016 infometric study). As a pianis t, she integrates her research into concert-conversations that showcase s cientific visualisations and lab-grown compositions.Together, Herremans a nd Chew worked on the MorpheuS automatic music composition system. To gui de MorpheuS' music generation, they designed and implemented a h armonic tension model based on the spiral array. The system learns rhythm s and harmonic tension profiles from a template piece to generate music w ith long term structure. MorpheuS' creations have been featured on Channel News Asia's television program on "Algorithm s: Part 1 - Rage Against The Machine", where it was pitted again st a human composer and had its output (based on the first of Three Piece s for String Quartet by Stravinsky) performed by members of the Singapore Symphony Orchestra. Chew has also performed MorpheuS pieces at concerts in venues in Cambridge (MA), London, San Francisco, and Stanford.&amp ;nbsp;
Read more URL:https://www.mariecuriealumni.eu/events/meet-my-lab-mathematics-and-music-synergetic-duo-automatic-music-generation END:VEVENT END:VCALENDAR