When composing a song, I find it sometimes difficult or impossible to find a style that I really want. At times, this is a benefit because the composed song moves in an unplanned, surprising and good direction. Other times, I give up and claim defeat.
I think BiaB could benefit from AI by building custom styles in real-time that meet the user's needs. One of two types of user inputs could be used to accomplish this.
1. An audio file of a song whose style you want to replicate could be imported in MP3 or WAV format.
2. A pull-down menu containing hundreds of song titles would allow you to select a specific song.
[Note that option 1 would be a much more elegant and complete solution and wouldn't require humans to continually update a song title list.]
With AI assistance, once the desired audio file is imported or song title selected, the algorthm would analyze it and return all of the instruments and other musical qualities that define that song in the form of a style. The user could then use that custom-built style just like you use any of the currently available styles; add a chord progression to it, swap out instruments, etc.
In other words, rather than scrolling thru dozens and dozens of pre-built styles and forcing one of them into the song you are creating, it would build, from scratch and return the best style that matches the song you are interested in. Icing on the cake would be for the 5 or 10 best fitting styles to be returned for you to audition.
Taken to a logical conclusion, this could eliminate pre-built styles altogether. Everytime you want to create a song, the style would be built for you in real-time based on user inputs. Another benefit might be a reduction of the footprint size of the program since the rules to create a style would replace a database of styles.
The goal here is for no one ever to "claim defeat" because they couldn't find a style that matches what they hear in their head.
No doubt, this would be a large software effort but smaller than what Microsoft has invested to create Bing. And the skeleton of an AI module to accomplish this may very well be commercially available; if not I'm sure 20-something grad students would love to work on something like this, especially if their names are associated with the end product.
On a technical note, AI, and more specifically, artificial neural networks are very good at classification. I'm thinking that this is a classification problem. So the neural net would have to be trained on several songs in every genre and sub-genre for which coverage is desired. Blues, country, hard rock, light rock, reggae, the various flavors of jazz, etc. would need to be tackled one by one.
https://soundcloud.com/user-646279677 BiaB 2024 Windows For me there’s no better place in the band than to have one leg in the harmony world and the other in the percussive. Thank you Paul Tutmarc and Leo Fender.
A simple thing Biab could be made to do is Random Style creation that creates a unique style rather than an out of the box style that someone else is using for their song also or replicating:
I suggested finders in Biab like EZDrummer and EZBass using a midi source
I don't know anything about MIDI but upon a little research it appears that a team has almost accomplished what I expressed above. This company's approach seems to use AI to generate a non-editable piece of music. They use the term "Influences".
"Use temp tracks to control the composition process If you need to create an original score that has a similar emotional impact as another existing score, you can upload your own MIDI file to influence AIVA's composition process"
Perhaps someone can investigate this further and comment if this could be a stepping stone to advance BiaB.
https://soundcloud.com/user-646279677 BiaB 2024 Windows For me there’s no better place in the band than to have one leg in the harmony world and the other in the percussive. Thank you Paul Tutmarc and Leo Fender.
I post a lot of simple things PG can do to improve Biab/RealBand/BBPlugin and they seem to have a hard time with them. I remember they were going to implement Rewire but that turned out to be too complex let alone the complexities of implementing AI.
The random style creator is a simple thing and can give some great unique results rather than a out of the box style that others are using for their songs, there are good ideas and there are GOD ideas that can come through "random" actions, so you may get something better.
You have all the RT RD demo wma files maybe you could find a 3rd party AI app that can catalog them then choose the best RTs and RD to replicate as close as possible the source sample ?
The best thing about Biab by far is the content, the sooner you get that content out of Biab the more creative control and ease of use you will have, not tomorrow not the next day or year but right now.
There are apps that will split audio into separate instruments like Spleeter then you could match each instrument from RT RD solo wma demos to choose something close then add these to create a new style.
You just need to search and you might find an app that will do all this, maybe even a plugin to work in Biab ??
Here is an outline of just one of several approaches one could (in principle) use to produce a custom style in BiaB. The psuedo code is written in a non-AI or traditional form that would guide how I would tackle this problem. FWIW, for me, it's irrelevant whether AI or traditional means are used to deliver this functionality because it's all under the hood. My original thought would be to use AI simply because in my mind this appears to be a technically challenging computer code to write and an AI approach may be simpler to implement when all is said and done.
The main technical challenge I see in using a traditional computing approach would be in computing the Error (Line 30). This would seem to require a very deep understanding of music theory and perhaps music psychology at a fundamental level.
Does anyone know how the mathematical code could be written to determine the musical distance there is between the guitar styles of Stevie Ray Vaughn and David Gilmore, for example? Clearly there are differences we all can hear between these two artists. But how would one code in FORTRAN, C++, Java, or Phython to accomplish this?
I'd be interested to hear the opinion of any expert in this field as to whether the math and theory exists to do this traditionally.
Whether AI or traditional, in engineering we would call this a juicy problem dripping with opportunity.
https://soundcloud.com/user-646279677 BiaB 2024 Windows For me there’s no better place in the band than to have one leg in the harmony world and the other in the percussive. Thank you Paul Tutmarc and Leo Fender.
I don't think I'd be interested in a 3rd party software to do this for me. But if PG Music added this functionality to BiaB I'd probably use it for every song I work on.
That said, it looks like Jamahook and perhaps others have already blazed this trail which is good news.
https://soundcloud.com/user-646279677 BiaB 2024 Windows For me there’s no better place in the band than to have one leg in the harmony world and the other in the percussive. Thank you Paul Tutmarc and Leo Fender.
My limited experience is that the styles suggested, based on a song title/band/performer etc., are usually quite far from the actual style desired. I've given up on the Style Picker and start with one of a very few "styles" I know well enough as a starting point and, inevitably, replace almost everything from Realtracks to tempo. Bass is the most common problem, I've found, in matching "Styles" with a sound/song/artist. Sorry, no answers from me.
Cheers rayc "What's so funny about peace, love & understanding?" - N.Lowe
A limited search on this subject yielded some interesting results. First, I found a paper written by some folks in Spain.
"Methods based on probabilistic approaches such as Cope’s Experiments in Musical Intelligence (EMI) [18], [19] also focus on the creation of an automatic music composition framework. Both EMI framework and the proposed system are based on probabilistic models (for pattern selection) and the training data stored in the database comes from musical features extracted from MIDI files (rhythm, pitch, dynamics,…)."
The reference to Cope's Experiments in Musical Intelligence, got my attention, and this is what I found on it.
"While some of the music composed using this approach did prove fairly successful, most of its output was equally uninteresting and unsatisfying. Having an intermediary - myself - form abstract sets of rules for composition seemed artificial and unnecessarily premeditative. As well, having to code new sets of rules for each new style encountered proved daunting. I therefore revised the program to create new output from music stored in a database. My idea was that every work of music contains a set of instructions for creating different but highly related replications of itself. These instructions, interpreted correctly, can lead to interesting discoveries about musical structure as well as, hopefully, create new instances of stylistically-faithful music."
While both of these references don't deal directly with creating a desired style from a menu of tracks (RTs) it does show me that some quite capable people are working on pushing the limits of music generation. David Cope in particular seems well-credentialed in the areas of music composition and computer science. I'm convinced that at some point a team, somewhere, is going to produce, commercialize and market the wish expressed in this thread. I hope it's PG Music.
https://soundcloud.com/user-646279677 BiaB 2024 Windows For me there’s no better place in the band than to have one leg in the harmony world and the other in the percussive. Thank you Paul Tutmarc and Leo Fender.
Ci siamo dati da fare e abbiamo aggiunto oltre 50 nuove funzionalità e una straordinaria raccolta di nuovi contenuti, tra cui 222 RealTracks, nuovi RealStyles, MIDI SuperTracks, Instrumental Studies, "Songs with Vocals" Artist Performance Sets, Playable RealTracks Set 3, Playable RealDrums Set 2, due nuovi set di "RealDrums Stems", XPro Styles PAK 6, Xtra Styles PAK 17 e altro ancora!
Band-in-a-Box® 2024 apporte plus de 50 fonctions nouvelles ainsi qu'une importante de contenus nouveaux à savoir : 222 RealTracks, des RealStyles nouveaux, des SuperTracks MIDI, des Etudes d'Instruments, des Prestations d'Artistes, des "Morceaux avec Choeurs", un Set 3 de Tracks Jouables, un Set 2 de RealDrums Jouables, deux nouveaux Sets de "RealDrums Stems", des Styles XPro PAK 6, des Xtra Styles PAK 17 et bien plus encore!
Video: Making a Song with Band-in-a-Box®, ChatGPT, and Synth V
Take your Band-in-a-Box® project to a whole new level when you incorporate ChatGPT and Synth V to add lyrics and vocals to your song!
We wanted to demonstrate how this is done with our video, where we show you how to go from nothing to a finished "radio ready" modern pop song by combining the features of Band-in-a-Box®, ChatGPT, and Synth V!
User Video: Next-Level AI Music Editing with ACE Studio and Band-in-a-Box®
The Bob Doyle Media YouTube channel is known for demonstrating how you can creatively incorporate AI into your projects - from your song projects to avatar building to face swapping, and more!
His latest video, Next-Level AI Music Editing with ACE Studio and Band-in-a-Box, he explains in detail how you can use the Melodist feature in Band-in-a-Box with ACE Studio. Follow along as he goes from "nothing" to "something" with his Band-in-a-Box MIDI Melodist track, using ACE Studio to turn it into a vocal track (or tracks, you'll see) by adding lyrics for those notes that will trigger some amazing AI vocals!
Wir waren fleißig und haben über 50 neue Funktionen und eine erstaunliche Sammlung neuer Inhalte hinzugefügt, darunter 222 RealTracks, neue RealStyles, MIDI SuperTracks, Instrumental Studies, "Songs with Vocals" Artist Performance Sets, abspielbare RealTracks Set 3, abspielbare RealDrums Set 2, zwei neue Sets von "RealDrums Stems", XPro Styles PAK 6, Xtra Styles PAK 17 und mehr!
Add updated printing options, enhanced tracks settings, smoother use of MGU and SGU (BB files) within PowerTracks, and more with the latest PowerTracks Pro Audio 2024 update!
One of our representatives will be happy to help you over the phone. Our hours of operation are from
6:00AM to 6:00PM PST (GMT -8) Monday thru Friday, and 8:00AM to 4:00PM PST Saturday. We are closed Sunday. You can also send us your questions via email.
One of our representatives will be happy to help you on our Live Chat or by email. Our hours of operation are from
6:00AM to 6:00PM PST (GMT -8) Monday thru Friday; 8:00AM to 4:00PM PST (GMT -8) Saturday; Closed Sunday.