I'll go one step farther and say which stem program works best depends on your goal. This thread is based on stem separation for bass and IMHO that is not the main goal for a single sound separation for many people. Separating the vocal I would surmise is the main goal for many and the free Ultimate Vocal Remover does an excellent job on that task. YMMV
Yeah, I've got O.C.D, Old, Cranky, and Dangerous.
64 bit Win 10 Pro, the latest BiaB/RB, Roland Octa-Capture audio interface, a ton of software/hardware
It has been mentioned: "our conclusions are based on the information available at the time. " I unfortunately don't have one to offer, as I haven't used these applications. But I've followed this thread with interest and I'm intrigued to know what the O/P's conclusions are at this point in time. Inquiring minds need to know
BIAB & RB2024 Win.(Audiophile), Sonar Platinum, Cakewalk by Bandlab, Izotope Prod.Bundle, Roland RD-1000, Synthogy Ivory, Kontakt, Focusrite 18i20, KetronSD2, NS40M Monitors, Pioneer Active Monitors, AKG K271 Studio H'phones
So if a conclusion was reached now, what would it be?
AudioTrack, this is easy. I gave 2 conclusions in my response to Cerio.
But two (obvious to me) points need to be made 1. These are my conclusions based on the evidence I observe, to be sure, others will draw their own conclusions. My conclusions may not be your conclusions. 2. Most conclusions are temporary and subject to be updated as conditions change, be it wind direction for the lioness, and unforeseen high pressure system for the weather man or a new software company that comes on the scene.
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.
Ok, using that line of thinking, I have made a preliminary conclusion that I cannot yet conclude one program is better than the other when comparing stem separation of Studio One Pro (7) and Song Master Pro. Was that helpful?
Matt, you are certainly entitled to draw that conclusion or any other that you deem appropriate.
For me, I don't have the luxury of time to be indecisive. Based on the evidence I have observed, my conclusions are different than yours. That is, S1 is top shelf and other stem separation tools will waste my time in comparison, or I have no need to research other tools. If this changes in the future . . . great!
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.
Separating the vocal I would surmise is the main goal for many and the free Ultimate Vocal Remover does an excellent job on that task. YMMV
Not only do I agree, I will add that its free!
More power to you. Right now I have no need to separate vocals, this thread was intended to explore bass separation.
PS> S1 may also be strong in separating vocals but I have no such observation.
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.
Ok, using that line of thinking, I have made a preliminary conclusion that I cannot yet conclude one program is better than the other when comparing stem separation of Studio One Pro (7) and Song Master Pro. Was that helpful?
Matt, you are certainly entitled to draw that conclusion or any other that you deem appropriate.
For me, I don't have the luxury of time to be indecisive. Based on the evidence I have observed, my conclusions are different than yours. That is, S1 is top shelf and other stem separation tools will waste my time in comparison, or I have no need to research other tools. If this changes in the future . . . great!
As I wrote, my preliminary test gave better results for bass with Studio One Pro. I have other uses for stem separation and have a need for the six-track separation of Song Master Pro. I will continue to test both tools.
BIAB 2024 Win Audiophile. Software: Studio One 6.5 Pro, Swam horns, Acoustica-7, Notion 6; Win 11 Home. Hardware: Intel i9, 32 Gb; Roland Integra-7, Presonus Studio 192, Presonus Faderport 8, Royer 121, Adam Sub8 & Neumann 120 monitors
Great! And I hope you report your results so we can all continue to learn. We are talking about and ever-changing landscape and the wind doesn't always blow in the direction the lioness wants
As for SongMaster Pro, the performance I got from it, as I mentioned, was pitiful. You can't expect glowing customer reviews if a product produces gaping holes in the seperated bass stem, even if the source audio is compressed. I've worked on software product development and you have to do your requisite homework to be successful as determined by the marketplace.
The good news is that Mr. Schnurrenberger and his team appear to be motivated and engaged, which is precisely why I asked Dan to consider forwarding a link to my SoundCloud file for him to observe my result using S1. Negative (but honest feedback) is a valuable commodity indeed.
But better yet, Mr. Schnurrenberger could join this forum and observe feedback on SMP first hand . . . that's what I would do.
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.
As for SongMaster Pro, the performance I got from it, as I mentioned, was pitiful. You can't expect glowing customer reviews if a product produces gaping holes in the seperated bass stem, even if the source audio is compressed. I've worked on software product development and you have to do your requisite homework to be successful as determined by the marketplace.
This is not a fair statement. I don't have Studio One 7 to test, but I'm 300% sure that it will also fail to separate bass (or any other track) sooner or later, just like any other similar program in the market. Try maybe a 1940s old jazz tune, a Cuban song recorded with a baby bass, a funky song mixing lots of slap bass notes with fingerstyle, an 80s tune with a doubled synth bass, or maybe a 60s song with a tic-tac bass line extremely panned to the right (let alone flamenco, modern Indian / African music and other world music styles) and you'll probably see by yourself.
Would you say then that Studio One performance is pitful? You shouldn't, at this stage of development, this is simply how these algorithms work, they have been trained on certain types of material and they are designed to work well in most cases, but they cannot be expected to work perfectly well in any possible scenario.
It’s not just Dan. I had a nice dialog with the developer and requested a tempo map function, which was added.
Here is a screenshot of page 1 of the process I captured for doing this in S1. Kudos to Gregor and his "PreSonus Starship". Capturing this in written form was a worthwhile exercize. It allowed me to tempo-map several songs, gave me a good appreciation of the programming progress made in this area and it was another opportunity to keep my wetware nice and wet.
As it turns out, I've been asked to give a talk on one example of the intersection of AI and music. My initial conclusion was to talk about the appendix in the White Paper. But now I have an even better subject; AI-enabled bass separation using S1. Now I need to down-select and buy a laptop that is Win11 ready.
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.
This is not a fair statement. I don't have Studio One 7 to test . . . It's entirely fair to express my opinion based on my test results. Rather than state that you don't have Studio One 7, why don't you purchase it for yourself? That way you could post and report your results including how it compares to SMP.
Would you say then that Studio One performance is pitful? You shouldn't, at this stage of development, this is simply how these algorithms work, they have been trained on certain types of material and they are designed to work well in most cases, but they cannot be expected to work perfectly well in any possible scenario. S1 has not reached perfection but if it produced unacceptable results and didn't meet my needs I would so state. The quality of the algorithms are proportional to the quantity and quality of the data used to train them.
Make no mistake and don't cross-confuse my dissapointment with one aspect of SMP with my view of the program in general. I actually like most of SMP. The GUI is clean, it does a good job in identifying chords, it has a small footprint and I like how it detects and displays tempo as it progresses thru the song.
Their programmers however, in my opinion need improve its performance on audio like You've Got Your Troubles converted from a YouTube; probably by training on lower resolution, compressed audio. It could be said that relative to online tools that YouTube may be second only to email in usage. That makes YouTube pretty important; so important that this very forum has a Best of YouTube sub-forum. I'm interested in a full-bodied seperator, not one limited to high resolution, uncompressed files, and I've found 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.
It’s not just Dan. I had a nice dialog with the developer and requested a tempo map function, which was added.
Here is a screenshot of page 1 of the process I captured for doing this in S1. Kudos to Gregor and his "PreSonus Starship". Capturing this in written form was a worthwhile exercize. It allowed me to tempo-map several songs, gave me a good appreciation of the programming progress made in this area and it was another opportunity to keep my wetware nice and wet.
As it turns out, I've been asked to give a talk on one example of the intersection of AI and music. My initial conclusion was to talk about the appendix in the White Paper. But now I have an even better subject; AI-enabled bass separation using S1. Now I need to down-select and buy a laptop that is Win11 ready.
In V7 you don't need to go into all those steps to create a tempo map no more or use Melodyne. You simply right click on the track that you want to create the tempo map and select create tempo map. Then just drag that track to the temp track and you are done.
In V7 you don't need to go into all those steps to create a tempo map no more or use Melodyne. You simply right click on the track that you want to create the tempo map and select create tempo map. Then just drag that track to the temp track and you are done.
Yes and that is the main reason I purchased V7. On a couple of tests that I ran the results are more accurate than Melodyne. This is a big plus for me when BobH and I jam without a click track.
{Edit} plus it is faster and easier to use than Melodyne.
Last edited by MarioD; 10/16/2405:26 AM.
Yeah, I've got O.C.D, Old, Cranky, and Dangerous.
64 bit Win 10 Pro, the latest BiaB/RB, Roland Octa-Capture audio interface, a ton of software/hardware
In V7 you don't need to go into all those steps to create a tempo map no more or use Melodyne. You simply right click on the track that you want to create the tempo map and select create tempo map. Then just drag that track to the temp track and you are done.
Yes, I'm aware of this improvement in V7 but haven't tried it yet. Needless to say, I'm impressed with the engineering, programming and management at PreSonus; a well-run, customer-focused company. It wouldn't surprise me at all to hear that they acquired a well known competitor.
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.
Steve, for your talk on AI powered bass track separation, have you found any research that explains anything about how AI is being used by Studio One Pro 7 when no other stem separation programs mention AI? I realize that Presonus isn’t going to publish trade secrets, but I found one review who said the Zplane plugin gave the same results.
I’m not disputing that stem separation in Studio One works pretty well for me so far, but marketing companies are putting ‘AI’ in so many product descriptions now with no details, just because it sounds cool. How is this not just a good computer algorithm doing what it is programmed to do? What is it choosing to do that makes it simulate being intelligent?
By the way, I’m a beta tester for the notation program Notion, which is also a Presonus product. Presonus was bought by Fender. In some areas this resulted in amazing developments, including improvements to Notion Mobile that is free and runs on most platforms. Notion 6 for desktop use however is quite stalled and in my opinion overdue for attention. It works great but we are ready for the next version. Who knows, maybe Notion 7 “now with AI” will do wonders. For example, maybe it could look at my four trombone parts and tell me how I could voice them better. Now that would be intelligent.
BIAB 2024 Win Audiophile. Software: Studio One 6.5 Pro, Swam horns, Acoustica-7, Notion 6; Win 11 Home. Hardware: Intel i9, 32 Gb; Roland Integra-7, Presonus Studio 192, Presonus Faderport 8, Royer 121, Adam Sub8 & Neumann 120 monitors
Steve, for your talk on AI powered bass track separation, have you found any research that explains anything about how AI is being used by Studio One Pro 7 when no other stem separation programs mention AI? I realize that Presonus isn’t going to publish trade secrets, but I found one review who said the Zplane plugin gave the same results. No, I haven’t found any info regarding how S1 does its stem separation; and I’ve done some looking. As you point out, this is a highly competitive domain with guarded trade secrets. In my mind, as I’ve mentioned before, the companies that will be successful will be those that have the foresight to engage with strong partners in the field. Developing this technical expertise in-house is all well and good until you find how long it can take. But collaborating with SMEs (Subject Matter Experts) doesn’t come cheap either, unless you can find a few 20-something grad students to join the team that are well connected to the IEEE Signal Processing Society or similar technical organization.
I’m not disputing that stem separation in Studio One works pretty well for me so far, but marketing companies are putting ‘AI’ in so many product descriptions now with no details, just because it sounds cool. How is this not just a good computer algorithm doing what it is programmed to do? What is it choosing to do that makes it simulate being intelligent? This is a BIG question but for starters it’s about the number of parameters in your model. I’m hearing some good things about Banquet. This model has over 24 million parameters and is described as stem-agnostic as opposed to the 4 stem VDBO (Vocals, Drums, Bass, Other) that most separation models are limited to. I’m also hearing about better SNR performances compared to say, Spleeter.
Who knows, maybe Notion 7 “now with AI” will do wonders. For example, maybe it could look at my four trombone parts and tell me how I could voice them better. Now that would be intelligent. This would be sweet with a capital S. It “just” takes good model development.
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.
In V7 you don't need to go into all those steps to create a tempo map no more or use Melodyne. You simply right click on the track that you want to create the tempo map and select create tempo map. Then just drag that track to the temp track and you are done.
Yes and that is the main reason I purchased V7. On a couple of tests that I ran the results are more accurate than Melodyne. This is a big plus for me when BobH and I jam without a click track.
{Edit} plus it is faster and easier to use than Melodyne.
Amen to that Mario. One of the main reasons for me as well. I already have stem separation with Rip X DAW which also separates the piano. I have not compared the two of them. I also like the new global transpose feature. This is a quote from Presonus about stem separation. "Stem Separation as a technology is still in its infancy, so further performance/quality improvements and feature additions are planned in the near future."
In theory, if something is learnable, AI will eventually find a method of learning it.
For the purposes of AI training, audio needs to be converted into something that computers can deal with. That's typically FFT, which then is split into frequency bands to better simulate human hearing.
Audio compression also takes psychoacoustics into account, deciding which frequencies in the audio you aren't likely miss because they're being masked by other frequencies, and discarding those frequencies so there's less information to encode. Because transients require more information to encode, they are also often simplified. High frequencies may be replaced by bands of noise.
So there is certainly a loss of information by the encoding process.
But I also suspect that there's a lot of audio information from the bass that's hard to pull out of the audio because it's simply not there - especially in cases where the bass and kick drum are locked together.
If that's the case, getting "missing" audio data and filling in holes is a matter of extrapolation for the neural network.
We do that all the time, and we often get it wrong.
I suspect there's a fine line between a neural network successfully guessing what a partially masked bass line might be, and it hallucinating a statistically probable but incorrect bass line.
That may be the reason why the quality has only progressed to where it currently is - it's better to be incomplete but accurate, than more complete, but wrong.
New! XPro Styles PAK 7 for Band-in-a-Box 2024 for Mac!
We've just released XPro Styles PAK 7 with 100 brand new RealStyles, plus 50 RealTracks and RealDrums that are sure to delight!
With XPro Styles PAK 7 you can expect 25 rock & pop, 25 jazz, and 25 country styles, as well as 25 of this year's wildcard genre: Celtic!
Here's a small sampling of what XPro Styles PAK 7 has to offer: energetic rock jigs, New Orleans funk, lilting jazz waltzes, fast Celtic punk, uptempo train beats, gritty grunge, intense jazz rock, groovy EDM, soulful R&B, soft singer-songwriter pop, country blues rock, and many more!
Special Pricing! Until September 30, 2024, all the XPro Styles PAKs 1 - 7 are on sale for only $29 ea (Reg. $49 ea)! Supercharge your Band-in-a-Box 2024® with XPro Styles PAK 7! Order now!
XPro Styles PAKs require Band-in-a-Box® 2024 or higher and are compatible with ANY package, including the Pro, MegaPAK, UltraPAK, UltraPAK+, and Audiophile Edition.
New! Xtra Styles PAK 18 for Band-in-a-Box 2024 for Mac!
Xtra Styles PAK 18 for Band-in-a-Box version 2024 is here with 200 brand new styles to take for a spin!
Along with 50 new styles each for the rock & pop, jazz, and country genres, we’ve put together a collection of styles using sounds from the SynthMaster plugin!
In this PAK you'll find: dubby reggae grooves, rootsy Americana, LA jazz pop, driving pop rock, mellow electronica, modern jazz fusion, spacey country ballads, Motown shuffles, energetic EDM, and plenty of synth heavy grooves! Xtra Style PAK 18 features these styles and many, many more!
Special Pricing! Until September 30, 2024, all the Xtra Styles PAKs 1 - 18 are on sale for only $29 ea (Reg. $49 ea)! Expand your Band-in-a-Box 2024® library with Xtra Styles PAK 18! Order now!
Learn more and listen to demos of the Xtra Styles PAK 18 here.
Note: The Xtra Styles require the UltraPAK, UltraPAK+, or Audiophile Edition of Band-in-a-Box®. (Xtra Styles PAK 18 requires the 2024 UltraPAK/UltraPAK+/Audiophile Edition. They will not work with the Pro or MegaPAK version because they need the RealTracks from the UltraPAK, UltraPAK+, or Audiophile Edition.
New! Xtra Styles PAK 18 for Band-in-a-Box 2024 for Windows!
Xtra Styles PAK 18 for Band-in-a-Box version 2024 is here with 200 brand new styles to take for a spin!
Along with 50 new styles each for the rock & pop, jazz, and country genres, we’ve put together a collection of styles using sounds from the SynthMaster plugin!
In this PAK you'll find: dubby reggae grooves, rootsy Americana, LA jazz pop, driving pop rock, mellow electronica, modern jazz fusion, spacey country ballads, Motown shuffles, energetic EDM, and plenty of synth heavy grooves! Xtra Style PAK 18 features these styles and many, many more!
Special Pricing! Until September 30, 2024, all the Xtra Styles PAKs 1 - 18 are on sale for only $29 ea (Reg. $49 ea)! Expand your Band-in-a-Box 2024® library with Xtra Styles PAK 18! Order now!
Learn more and listen to demos of the Xtra Styles PAK 18 here.
Note: The Xtra Styles require the UltraPAK, UltraPAK+, or Audiophile Edition of Band-in-a-Box®. (Xtra Styles PAK 18 requires the 2024 UltraPAK/UltraPAK+/Audiophile Edition. They will not work with the Pro or MegaPAK version because they need the RealTracks from the UltraPAK, UltraPAK+, or Audiophile Edition.
New! XPro Styles PAK 7 for Band-in-a-Box 2024 for Windows!
We've just released XPro Styles PAK 7 with 100 brand new RealStyles, plus 50 RealTracks and RealDrums that are sure to delight!
With XPro Styles PAK 7 you can expect 25 rock & pop, 25 jazz, and 25 country styles, as well as 25 of this year's wildcard genre: Celtic!
Here's a small sampling of what XPro Styles PAK 7 has to offer: energetic rock jigs, New Orleans funk, lilting jazz waltzes, fast Celtic punk, uptempo train beats, gritty grunge, intense jazz rock, groovy EDM, soulful R&B, soft singer-songwriter pop, country blues rock, and many more!
Special Pricing! Until September 30, 2024, all the XPro Styles PAKs 1 - 7 are on sale for only $29 ea (Reg. $49 ea)! Supercharge your Band-in-a-Box 2024® with XPro Styles PAK 7! Order now!
XPro Styles PAKs require Band-in-a-Box® 2024 or higher and are compatible with ANY package, including the Pro, MegaPAK, UltraPAK, UltraPAK+, and Audiophile Edition.
Video - Band-in-a-Box® DAW Plugin Version 6 for Mac®: New Features for Reaper
Band-in-a-Box® 2024 includes built-in specific support for the Reaper® DAW API, allowing direct transfer of Band-in-a-Box® files to/from Reaper tracks, including tiny lossless files of instructions which play audio instantly from disk.
Already grabbed your copy of Band-in-a-Box® 2024 for Mac®? Head to our Support Page to download build 803 and update your Band-in-a-Box® 2024 installation with the latest version developed by our team!
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.
Dansk
Deutsch - Windows
Español
Français - Windows
Italiano - Windows
Nederlands
Polski
Português
Svenskt
русский
Japanese
Simplified Chinese
Traditional Chinese
Korean