What is generative music
This is a podcast with content creators. Guest release - Alexey Kochetkov, CEO Mubert , with a story about generative music and his vision of future audio content.
Alexey Kochetkov, CEO Mubert
alinatestova : Since we are talking not only about text and spoken content, naturally, we have not ignored music. In particular, quite a new direction in this area. Alexey, you are the CEO of the Mubert project. This is a streaming service that generates generative music. Tell me how it works?
')
Alexey: Generative music is created in real time by algorithms. This is music that can be adapted, applied in any sphere, personalized, and so on. It is collected in real time from a certain number of samples.
A sample is a piece of music that every musician has the ability to record. That is, generative music is created from, as they say in English, human-made samples [samples created by man]. The algorithm analyzes them and creates stream only for you.
Alina: Super. Music is created by the algorithm, the algorithm - by people.
It makes sense to talk a little about the background of this project, about its beginning. Why did you decide to do it? Was it related to your musical interests?
Alexey: As they say, startups are born out of pain. I was running, and I constantly had a pain in my side from switching music. At that moment, an idea occurred to me: why not create an application in which the samples will line up in an infinite composition that corresponds to the pace of my run. Thus was born the first idea of ​​Mubert.
The team was assembled on the same day and began to create a product, which later, of course, made several pivots. But the concept itself is the same that was created on the first day.
Alina: Did your musical past somehow influence your choice or certain steps that were taken during the development of the application?
Alexey: No. I have a musical jazz education, and here it helps a little. I know the notes, I know how to play the double bass and what the music consists of.
I was always in charge of the bass. In all the bands I attended, I always took the lowest frequencies and played the double bass, the bass guitar, the bass synthesizers. This does not help in working on Mubert. I just know about how the music works, I listen to a lot of it, and I have a long time ago the belief that there is no bad music or bad taste.
There is a personal taste and personal approach to music. Each person has his own, and each person has the right to choose music and so show their taste.
It helps me a little knowledge of notes, harmonies and other things. But on the whole Mubert works, besides me, about fifty more musicians who actively participate in the development of the interface, music ranking systems and artificial intelligence systems. These are people who constantly give advice and influence the way Mubert sounds today.
Alina: Is it possible to say that, in essence, generative is the type of music that harmonizes with other activities as harmoniously as possible?
For example, usually writing text or working with music is a pleasure for an amateur. Someone may get used to it, but someone may not. Can algorithmic music give a synergistic effect, which, on the contrary, will allow to enter the stream state?
Alexey: This is a hypothesis, and we are trying to test it.
Under generative music will soon be read - we are doing a joint application with Bookmate. Under generative music, people run marathons, and this is the only application that makes it possible to run and not change their pace for four, eight, sixteen hours, and so on. Under this music work, learn. This is probably a cool approach to music - to be a sponsor of your hobbies. But this is a hypothesis.
Alina: And you check it with collaborations?
Alexey: It is confirmed by subscriptions and auditions that occur every day in Mubert. For example, meditation is the most purchased channel from us.
Alina: And High for which states, if not literally take it? (laughs)
Alexey: To have a rest, relax, feel some connection and so on.
Alina: Super. Tell me, please, in your opinion, generative music - algorithmic, repetitive, long - is it something fundamentally new or some kind of continuation of ethnic, shamanic and meditative music?
Alexey: This is something like a repit.
Mubert started in 2000 actually when I was re-recording Bomfunk MC's with Monte Carlo [track] radio. As soon as it sounded on the radio, I continued recording on the tape until I recorded a whole side with this track. Then I did the same with the other side. As a result, I had a whole tape on which only Bomfunk MC's was recorded - Freestyler.
Mubert returns to these times. A bunch of people use music to play. They include a track and work under it all day or play sports for a while.
Generative music in its current state does not fully have all the drama that a DJ can give. He realizes in real time that now you need to raise BPM , now lower, expand harmony or narrow. Generative music only seeks this.
And we are pioneers in creating drama in generative music, which we have learned to create infinitely long, smooth and understandable. Now we are learning to create drama in it.
As we recently showed in the adidas store. We created a DJ set without a DJ, and a lot of people danced beautifully to this music. It sounded at the level of German DJs, who in principle were the authors of the samples. But the set was created by Mubert.
Alina: How does the algorithm work?
Alexey: The algorithm analyzes a variety of parameters: melody, rhythm, saturation, “fatness” of sound, instrument. His pace, pitch and so on. A bunch of parameters that are objective. Next, the subjective parameters begin. This is a genre, activity, your taste. There may be parameters associated with geodata. When you want to collect, for example, city stream - to understand how the city of Berlin sounds.
The AI ​​system here is a companion to ensure that subjective parameters are executed. In order for you at the moment of some kind of activity to receive music that is based on your taste and on those things that you have already managed to show on this system.
Soon we will release an application in which you can like, dizlikat, "favorite" music and influence your own style. This will be the first application in the world in which there is no common chart. We don’t even have in the database such a thing as a general chart of popularity or unpopularity of samples and artists. Each has its own chart, which contains combinations of parameters. On their basis, the system learns and creates your own soundtrack.
Alina: In fact, we are talking about the fact that for each Mubert user, a lot of soundtracks to different aspects of his life appear.
Alexey: Yes. This is the first real personal streaming.
Alina: Super. You have already started to talk about the collaboration with adidas, and please tell us about collaboration with brands in general. How do they look?
Alexey: Music is the closest kind of creativity to a person. Accordingly, if a brand wants to get closer to a person, it needs to be done through music. Few know about it yet, but those brands that know are already starting to do it.
For example, adidas holds pop-up parties that occur suddenly in some of their stores. They are not advertised. Other brands sponsor theme parties.
To whom should they move, if not to new technologies? They have two options: they either take a top DJ or top technology. If it is possible to combine this - as we did with adidas, when we had samples provided by one of the top producers in Berlin Atom TM - the person who created the electronics. Then the brightest spark is born, which sparkles so that the brand can declare itself.
Alina: If we are talking about parties ... Of course, there are a lot of people there. How does Mubert understand what music to make? How does personalization work in this case?
Aleksey: Party is customized for party, city is for city. It's all…
Alina: Essence.
Alexey: Yes, an entity under which we can be customized. Personalization goes from your time of day and day to some global things. As I have already explained: there are objective parameters, there are subjective ones. The set of subjective parameters is a genre, a city, you, morning. Anything. Objective - the saturation of sound, its tempo, tone, gamma, and so on. All those things that can be measured objectively.
Alina: How do you think, how will generative music and music in general develop? Does the algorithm of the human composer or DJ replace in the future?
Alexey: No way. DJ selector will remain. You can’t collect music better than DJ, whether it be track or sample music. Earlier DJs were called selectors, and this work will remain because they collect the most "fat".
The development of generative music will lead to the fact that it will appear in each phone, because it gives slightly different possibilities for the adaptation and personalization of this music. It will also present the author's collections. We, for example, will be able to exchange some generations and understand how you trained your Mubert, and how you did it yourself. It’s just like today with playlists, only on a deeper level.
Alina: It turns out that the future of generative music is a symbiosis of the human creator and the algorithm that analyzes everything that happens more deeply and accurately?
Alexey: Absolutely.
Alina: Super. And finally, our blitz of two questions. Music helps ...
Aleksey: Live, breathe.
Alina: The best track is the one ...
Alexey: Which "inserts".
Alina: Class, thank you very much.
- listen to telegram or web player
- subscribe to podcast in iTunes or on Habré
Alexey Kochetkov, CEO Mubertalinatestova : Since we are talking not only about text and spoken content, naturally, we have not ignored music. In particular, quite a new direction in this area. Alexey, you are the CEO of the Mubert project. This is a streaming service that generates generative music. Tell me how it works?
')
Alexey: Generative music is created in real time by algorithms. This is music that can be adapted, applied in any sphere, personalized, and so on. It is collected in real time from a certain number of samples.
A sample is a piece of music that every musician has the ability to record. That is, generative music is created from, as they say in English, human-made samples [samples created by man]. The algorithm analyzes them and creates stream only for you.
Alina: Super. Music is created by the algorithm, the algorithm - by people.
It makes sense to talk a little about the background of this project, about its beginning. Why did you decide to do it? Was it related to your musical interests?
Alexey: As they say, startups are born out of pain. I was running, and I constantly had a pain in my side from switching music. At that moment, an idea occurred to me: why not create an application in which the samples will line up in an infinite composition that corresponds to the pace of my run. Thus was born the first idea of ​​Mubert.
The team was assembled on the same day and began to create a product, which later, of course, made several pivots. But the concept itself is the same that was created on the first day.
This is music that has no beginning, end, pauses and inter-song transitions.
Alina: Did your musical past somehow influence your choice or certain steps that were taken during the development of the application?
Alexey: No. I have a musical jazz education, and here it helps a little. I know the notes, I know how to play the double bass and what the music consists of.
I was always in charge of the bass. In all the bands I attended, I always took the lowest frequencies and played the double bass, the bass guitar, the bass synthesizers. This does not help in working on Mubert. I just know about how the music works, I listen to a lot of it, and I have a long time ago the belief that there is no bad music or bad taste.
There is a personal taste and personal approach to music. Each person has his own, and each person has the right to choose music and so show their taste.
It helps me a little knowledge of notes, harmonies and other things. But on the whole Mubert works, besides me, about fifty more musicians who actively participate in the development of the interface, music ranking systems and artificial intelligence systems. These are people who constantly give advice and influence the way Mubert sounds today.
Alina: Is it possible to say that, in essence, generative is the type of music that harmonizes with other activities as harmoniously as possible?
For example, usually writing text or working with music is a pleasure for an amateur. Someone may get used to it, but someone may not. Can algorithmic music give a synergistic effect, which, on the contrary, will allow to enter the stream state?
Alexey: This is a hypothesis, and we are trying to test it.
Under generative music will soon be read - we are doing a joint application with Bookmate. Under generative music, people run marathons, and this is the only application that makes it possible to run and not change their pace for four, eight, sixteen hours, and so on. Under this music work, learn. This is probably a cool approach to music - to be a sponsor of your hobbies. But this is a hypothesis.
Alina: And you check it with collaborations?
Alexey: It is confirmed by subscriptions and auditions that occur every day in Mubert. For example, meditation is the most purchased channel from us.
In total there are three paid channels: Meditate, Sleep and High. High is dub, reggae. The most bought is meditation, because in the process of meditation the music should not stop or change. Mubert does this.
Alina: And High for which states, if not literally take it? (laughs)
Alexey: To have a rest, relax, feel some connection and so on.
Alina: Super. Tell me, please, in your opinion, generative music - algorithmic, repetitive, long - is it something fundamentally new or some kind of continuation of ethnic, shamanic and meditative music?
Alexey: This is something like a repit.
Mubert started in 2000 actually when I was re-recording Bomfunk MC's with Monte Carlo [track] radio. As soon as it sounded on the radio, I continued recording on the tape until I recorded a whole side with this track. Then I did the same with the other side. As a result, I had a whole tape on which only Bomfunk MC's was recorded - Freestyler.
Mubert returns to these times. A bunch of people use music to play. They include a track and work under it all day or play sports for a while.
Generative music in its current state does not fully have all the drama that a DJ can give. He realizes in real time that now you need to raise BPM , now lower, expand harmony or narrow. Generative music only seeks this.
And we are pioneers in creating drama in generative music, which we have learned to create infinitely long, smooth and understandable. Now we are learning to create drama in it.
As we recently showed in the adidas store. We created a DJ set without a DJ, and a lot of people danced beautifully to this music. It sounded at the level of German DJs, who in principle were the authors of the samples. But the set was created by Mubert.
Answering the question, generative music takes its origins from repit and ends up with something that we still cannot imagine.
Alina: How does the algorithm work?
Alexey: The algorithm analyzes a variety of parameters: melody, rhythm, saturation, “fatness” of sound, instrument. His pace, pitch and so on. A bunch of parameters that are objective. Next, the subjective parameters begin. This is a genre, activity, your taste. There may be parameters associated with geodata. When you want to collect, for example, city stream - to understand how the city of Berlin sounds.
The AI ​​system here is a companion to ensure that subjective parameters are executed. In order for you at the moment of some kind of activity to receive music that is based on your taste and on those things that you have already managed to show on this system.
Soon we will release an application in which you can like, dizlikat, "favorite" music and influence your own style. This will be the first application in the world in which there is no common chart. We don’t even have in the database such a thing as a general chart of popularity or unpopularity of samples and artists. Each has its own chart, which contains combinations of parameters. On their basis, the system learns and creates your own soundtrack.
Alina: In fact, we are talking about the fact that for each Mubert user, a lot of soundtracks to different aspects of his life appear.
Alexey: Yes. This is the first real personal streaming.
Alina: Super. You have already started to talk about the collaboration with adidas, and please tell us about collaboration with brands in general. How do they look?
Alexey: Music is the closest kind of creativity to a person. Accordingly, if a brand wants to get closer to a person, it needs to be done through music. Few know about it yet, but those brands that know are already starting to do it.
For example, adidas holds pop-up parties that occur suddenly in some of their stores. They are not advertised. Other brands sponsor theme parties.
To whom should they move, if not to new technologies? They have two options: they either take a top DJ or top technology. If it is possible to combine this - as we did with adidas, when we had samples provided by one of the top producers in Berlin Atom TM - the person who created the electronics. Then the brightest spark is born, which sparkles so that the brand can declare itself.
For any brand, music is an information guide.
Alina: If we are talking about parties ... Of course, there are a lot of people there. How does Mubert understand what music to make? How does personalization work in this case?
Aleksey: Party is customized for party, city is for city. It's all…
Alina: Essence.
Alexey: Yes, an entity under which we can be customized. Personalization goes from your time of day and day to some global things. As I have already explained: there are objective parameters, there are subjective ones. The set of subjective parameters is a genre, a city, you, morning. Anything. Objective - the saturation of sound, its tempo, tone, gamma, and so on. All those things that can be measured objectively.
Alina: How do you think, how will generative music and music in general develop? Does the algorithm of the human composer or DJ replace in the future?
Alexey: No way. DJ selector will remain. You can’t collect music better than DJ, whether it be track or sample music. Earlier DJs were called selectors, and this work will remain because they collect the most "fat".
The development of generative music will lead to the fact that it will appear in each phone, because it gives slightly different possibilities for the adaptation and personalization of this music. It will also present the author's collections. We, for example, will be able to exchange some generations and understand how you trained your Mubert, and how you did it yourself. It’s just like today with playlists, only on a deeper level.
Alina: It turns out that the future of generative music is a symbiosis of the human creator and the algorithm that analyzes everything that happens more deeply and accurately?
Alexey: Absolutely.
Alina: Super. And finally, our blitz of two questions. Music helps ...
Aleksey: Live, breathe.
Alina: The best track is the one ...
Alexey: Which "inserts".
Alina: Class, thank you very much.
Our content marketing microformat:What do you have for such an office?
Archetypes: why stories work
PS In the profile of glphmedia - links to all releases of our podcast.
Source: https://habr.com/ru/post/445014/
All Articles