|
Log in to post
|
Print Thread |
|
|
|
|
|
User Showcase
|
Joined: Sep 2010
Posts: 8,326
Veteran
|
OP
Veteran
Joined: Sep 2010
Posts: 8,326 |
When I posted a song a while back recorded using Sinsy, Don Gaynor had expressed hope that with this sort of technology he'd be able to sing again. While the fine folk at DynaVox haven't gotten back to him yet, I thought I might have a go at solving the problem. You may have noticed I've been a bit absent from the board since then.  Here's the result: Loch Lomond (with harmony)It's "state of the art" 1980's formant synthesis. It's not the technology I'd intended to use, but that's a rather long story. I'm still working out the bugs in the code. It's not ready for end users, but it's finally "singing." There's a bit of post-processing on the vocals. I used the PG Vinyl plugin to reduce some of the popping on consonants, and a low-pass filter to kill some of the high-end noise. I've also run things through EZ Mix to add some reverb and compression. Most of the phonemes are fairly acceptable, but there's an /H/ and /L/ that seem to have gone missing. I've only tweaked one of the phonemes. At 0:15 there's what sounds like a breath noise. It's actually a bug, so I lowered the volume there. (I intend to add support for breaths at some point). The accompaniment is PJONPBA.STY (PopBalladPiano & Ac.Guitar[85RS]). I guessed at the chords from the sheet music, so there may be some clinkers in there. The harmony is just thirds above the melody, so there may be some clinkers there, too.
-- David Cuny My virtual singer development blogVocal control, you say. Never heard of it. Is that some kind of ProTools thing?BiaB 2025 | Windows 11 | Reaper | Way too many VSTis.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Dec 2003
Posts: 8,987
Veteran
|
|
Veteran
Joined: Dec 2003
Posts: 8,987 |
I love it David! Thanki, mate!
Now you may understand the difficulty I ran into trying to overcome inertia and reluctance to change on the part of Corporations, especially from ootsiders. Very frustrating and disheartening. It's extremely difficult to keep on slugging when we see no progress. I have several dead-end projects that I am stymied on including "The iPod Project" (qv).
Last edited by Don Gaynor; 05/29/13 03:48 PM. Reason: To make a semblance of cents to Canadian readers and moderators.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Sep 2010
Posts: 8,326
Veteran
|
|
OP
Veteran
Joined: Sep 2010
Posts: 8,326 |
Hopefully, I can shape it into something useful. I've taken a couple of days off work in an effort to get this into shape, and I've just found a major portion of the code that needs to be rewritten. Once this is stable, I still need to set up some sort of front end for it. The current plan is to have it read MusicXML files. I've got some code I've written for a different project I should be able to re-purpose. I also need to write some code to do dictionary lookup. I've got a nice hyphenated phonetic dictionary, so hopefully the majority of that work is already done. But... I still need to stabilize this code. If you're really lucky, this will give incentive to DynaVox to finish up their project, and you'll get some real voice synthesis. 
-- David Cuny My virtual singer development blogVocal control, you say. Never heard of it. Is that some kind of ProTools thing?BiaB 2025 | Windows 11 | Reaper | Way too many VSTis.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Dec 2005
Posts: 4,047
Veteran
|
|
Veteran
Joined: Dec 2005
Posts: 4,047 |
David,
This effort you have made into this cutting edge technology is outstanding.
I've spent thousands of hours since the 70's working on coding projects that
had never been done before. Can really appreciate the efforts you have put into
this.
Hang in there and continuing good efforts on your "projects". Note didn't say
good luck. Patience and stamina, be with you.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Sep 2010
Posts: 8,326
Veteran
|
|
OP
Veteran
Joined: Sep 2010
Posts: 8,326 |
This effort you have made into this cutting edge technology is outstanding. Yes, cutting edge 1980's technology at it's best. This is about four generations removed from current voice synthesis technology. You might recall S.A.M. (Software Automatic Mouth), which was the basis of MacInTalk. If you play with the demo on that page (decompiled from assembly into C, and then converted into JavaScript!), you can hear the familial resemblance. Interestingly, the company that put out S.A.M. is still in business as SoftVoice, Inc., and it was their demo of Twinkle, Twinkle Little Star that convinced me that while formant synthesis might not create realistic results, it might be "good enough" for my purposes. Since they've been doing this for the last 30 years, I think their example is probably as good as this technology gets.
-- David Cuny My virtual singer development blogVocal control, you say. Never heard of it. Is that some kind of ProTools thing?BiaB 2025 | Windows 11 | Reaper | Way too many VSTis.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Jun 2012
Posts: 2,888
Veteran
|
|
Veteran
Joined: Jun 2012
Posts: 2,888 |
Hi David,
a milestone in your efforts. Following your blog I know
what a lot of work this was and still is.
Guenter
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Sep 2010
Posts: 8,326
Veteran
|
|
OP
Veteran
Joined: Sep 2010
Posts: 8,326 |
The next step it to make this usable. I'd like to write a UI that displays the music on a staff, and integrates with the CMU phonetic dictionary. Nothing terribly complex - just good enough to "get the job done." It'll output a .wav file, which BiaB can load. The rest is up to Don. 
-- David Cuny My virtual singer development blogVocal control, you say. Never heard of it. Is that some kind of ProTools thing?BiaB 2025 | Windows 11 | Reaper | Way too many VSTis.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Aug 2012
Posts: 13,010
Veteran
|
|
Veteran
Joined: Aug 2012
Posts: 13,010 |
David,
I commend you on the effort that this must require. Standing ovation for that, alone. Bravo.
floyd
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: May 2008
Posts: 5,086
Veteran
|
|
Veteran
Joined: May 2008
Posts: 5,086 |
Kudos David. What a thoughtful thing to do - not to mention all the time and effort involved. I'm sure it will bring Don and others lots of fun in making their music when you're done.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Sep 2010
Posts: 8,326
Veteran
|
|
OP
Veteran
Joined: Sep 2010
Posts: 8,326 |
Thanks! 
-- David Cuny My virtual singer development blogVocal control, you say. Never heard of it. Is that some kind of ProTools thing?BiaB 2025 | Windows 11 | Reaper | Way too many VSTis.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Oct 2008
Posts: 20,663
Veteran
|
|
Veteran
Joined: Oct 2008
Posts: 20,663 |
Hi David, This is amazing! I can't even begin to comprehend the amount of effort that must have been involved. You realize that you'll have to change your signature's saying now! "Loch Lomond" is all about 'voice control' at it's absolute cleverest Regards, Noel
MY SONGS...Audiophile BIAB 2026
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Oct 2008
Posts: 8,109
Veteran
|
|
Veteran
Joined: Oct 2008
Posts: 8,109 |
David,
I've got to be honest and say that my (very) first impression of this was that the timing of your presentation couldn't have been worse, considering the fact that Guenter has recently posted some excellent projects using a more advance synthetic voice. Comparisons are inevitable, and you are at a disadvantage being a single developer working for free without any kind of subsidy.
But the more I listen and compare your synth voice to the one Guenter is using, the more impressed I am with yours.
The biggest difference to my ear is that yours has a pronounced artifact where the syllables are joined together, whereas the other engine has figured out a way to blend the syllables more smoothly... which, in a song environment is definitely more musical.
Having dealt with artifacts when blending snippets in a DAW, I have to wonder if it would help to fade each of your separate syllables on both ends so the sharp edge that causes the artifact is less pronounced when they are joined together.
In the final analysis, all comparisons aside, what you have accomplished here is PHENOMEnal! (pun intended)
I wish you much luck with further development and I look forward to hearing more examples as time goes on.
Last edited by Pat Marr; 06/01/13 12:24 PM.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Dec 2011
Posts: 16,292
Veteran
|
|
Veteran
Joined: Dec 2011
Posts: 16,292 |
The patience of Job must have gone into that. I can't imagine the code (and I used to do a little programming). Gonna be fascinating to see how it plays out. Thanks.
Our albums and singles are on Spotify, Apple Music, Amazon Music, YouTube Music, Pandora and more. If interested search on Janice Merritt. Thanks! A few of our videos are here on our website: https://www.janiceandbud.com/our-music.html
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Sep 2010
Posts: 8,326
Veteran
|
|
OP
Veteran
Joined: Sep 2010
Posts: 8,326 |
Hi, Pat. Thanks for the your response. Before getting into details, I should clarify: this project is just re-implementing what others have already done, and much better than me. From text to speech: The MITalk system (Allen) was a great resource for me. The technology is essentially abandoned for other, better approaches. I'll give an explanation why I was unable to go down that route. Also, my immediate goal is to get Don something usable. If DynaVox finally gets him a better synthesis program, then, Hurrah!. No need for this program. I'm aware of the Vocaloid software - I've got the Avanna as well, because it's probably got the best English accent of all the current Vocaloids. I've also spent a lot of time looking at UTAU, a free synthetic singer written along the lines of Vocaloid. In fact, my initial approach was exactly what you suggested: record various phonemes (using Vowel/Consonant/Vowel patterns), cross-fade them together, and use pitch shifting. I've actually written a number of tools to do this. The stumbling block was the pitch shifting. The pitch shifting needs to shift some frequencies (the glottal pulse) and keep others fixed (the formants) or you get the "Mickey Mouse" effect. BiaB uses the astonishingly good elastiq algorithm. I couldn't find any free libraries that gave decent results - even the RubberBand library, which has formant preservation, didn't do an acceptable job. I tried FFT-based pitch shifting, but didn't have much luck. I got better results with PSOLA (Pitch Synchronous Overlap and Add), but there were significant artifacts: Here's an example. The examples I'd heard of formant-based synthesis convinced me that while it lacked realism, it was capable of creating intelligible and musical synthesis. I think you'll agree that, with some tuning, this synthesizer may not create realistic voices, but they can be understandable. And to be honest, I've been focused on just getting the code to work. I've spent very little time on fine-tuning the phonemes. This is alpha-software, and there's lots of room for improvement. That said, in Text-to-Speech Synthesis, Paul Taylor argues that formant-based synthesis is intrinsically un-natural because it can't capture the details of real speech, so I don't hold high hopes for it. I've considered mixing pre-recorded audio with synthesized sounds like eSpeak, but that raises plenty of issues. And there's still the issue of handling sounds like /B/, /D/ and /G/, which are voiced and consonants. So for the moment, I'm sticking with "pure" synthesis. I hope that somewhat explains that approach I've taken. Despite the many flaws, I figured it was time to move ahead with the project. For the moment, I'll be focusing on creating a UI.
-- David Cuny My virtual singer development blogVocal control, you say. Never heard of it. Is that some kind of ProTools thing?BiaB 2025 | Windows 11 | Reaper | Way too many VSTis.
|
|
|
|
|
|
|
|
|
|
|
|
|
User Showcase
|
Joined: Mar 2013
Posts: 4,497
Veteran
|
|
Veteran
Joined: Mar 2013
Posts: 4,497 |
Hi, David !
I am no expert on these matters
which maybe makes me better judging
the end result from a listeners point of view ?
I am referring to the tune. Maybe I am
partial as this tune has a special meaning
for me. You see, once I sang this song to my
dear wife Beni at the shore of this Loch and little
did I know then, that the words held a prophecy
as "me and my true love would never be allowed
to meet again on the bonnie, bonnie banks of Loch Lomond" !
She died of cancer on October the 26 th 2011 !
I think you have done a marvellous job David !
Keep on the good work !
Cheers
Dani
|
|
|
|
|
|
|
|
|
|
|
|
Ask sales and support questions about Band-in-a-Box using natural language.
ChatPG's knowledge base includes the full Band-in-a-Box User Manual and sales information from the website.
|
|
|
|
|
|
|
|
|
|
|
Peter Gannon Talks Band-in-a-Box with zplane
zplane recently interviewed Peter Gannon, the founder and creator of Band-in-a-Box, about the software's early days, what sets it apart from AI, how zplane's audio algorithms are used in Band-in-a-Box, and more!
Special thanks to the team at zplane for their continued support.
Check out the full interview here: https://products.zplane.de/blog/peter-gannon-interview-pg-music
Last Chance! The Band-in-a-Box® 2026 for Mac® Special Ends Today (May 31, 2026) at 11:59pm PDT!
Time really is running out! Save up to 50% on Band-in-a-Box® 2026 for Mac® upgrades and receive a FREE Bonus PAK—only when you order by 11:59 PM PDT today!
We've added many major new features and new content in a redesigned Band-in-a-Box® 2026 for Mac®!
Version 2026 introduces a modernized GUI redesign across the program, with updated toolbars, refreshed windows, smoother workflows, and a new Dark Mode option. There’s also a new side toolbar for quicker access to commonly used windows, and the new Multi-View feature lets you arrange multiple windows as layered panels without overlap, making it easier to customize your workspace.
Another exciting new addition is the amazing new AI-Notes feature, which can transcribe polyphonic audio into MIDI. View the results in notation or play them back as MIDI, and choose whether to transcribe an entire track or transcribe specific parts like drums, bass, guitars/piano, or vocals. There's over 100 new features in Band-in-a-Box® 2026 for Mac®.
There's an amazing collection of new content too, including 202 RealTracks, new RealStyles, MIDI SuperTracks, Instrumental Studies, “Songs with Vocals” Artist Performance Sets, Playable RealTracks Set 5, two RealDrums Stems sets, and much more!
Upgrade your Band-in-a-Box for Mac® to save up to 50% on most Band-in-a-Box® 2026 upgrade packages!
Plus, when you order your Band-in-a-Box® 2026 Mac upgrade during our special, you'll receive a Free Bonus PAK of exciting new add-ons.
If you need any help deciding which package is the best option for you, just let us know. We are here to help!
Band-in-a-Box® 2026 Mac Special Offers Extended Until May 31st!
Good news- we've extended our Band-in-a-Box® 2026 for Mac® special offers until May 31, 2026!
Band-in-a-Box® 2026 is packed with major new features, enhancements, and an incredible lineup of new content! The program now sports a sleek, modern GUI redesign across the entire interface, including updated toolbars, refreshed windows, smoother workflows, a new dark mode option, and more. The brand-new side toolbar provides quicker access to key windows, while the new Multi-View feature lets you arrange multiple windows as layered panels without overlap, creating a flexible, clutter-free workspace. We have an amazing new “AI-Notes” feature. This transcribes polyphonic audio into MIDI so you can view it in notation or play it back as MIDI. You can transcribe an entire track (all pitched instruments and drums) or focus on individual parts like drums, bass, guitars/piano, or vocals. There's an amazing collection of new content too, including 202 RealTracks, new RealStyles, MIDI SuperTracks, Instrumental Studies, “Songs with Vocals” Artist Performance Sets, Playable RealTracks Set 5, two RealDrums Stems sets, and much more!
There are over 100 new features in Band-in-a-Box® 2026 for Mac®.
When you order purchase Band-in-a-Box® 2026 before 11:59 PM PDT on May 31st, you'll also receive a Free Bonus PAK packed with exciting new add-ons.
Check out the Band-in-a-Box® for Mac packages page to find the best package for you.
Holiday Weekend Hours
It's Victoria Day Long Weekend in Canada. Our Customer Service hours are:
Saturday, May 16: Closed
Sunday, May 17: Closed
Monday, May 18: 8:00am - 4:00pm
Regular hours resume Tuesday, May 19th!
Today's the Last Day of the Band-in-a-Box 2026® for Mac Special!
Order before 11:59pm PDT today (May 15, 2026) to save up to 50% off your Band-in-a-Box® 2026 for Mac® upgrade and receive a FREE Bonus PAK loaded with great new Add-ons to use with this new version!
Don't wait - order today!
Check out all the new features in the redesigned Band-in-a-Box® 2026 for Mac®!
Band-in-a-Box® 2026 for Mac - Special Offers End at 11:59pm PDT on Friday, May 15th, 2026!
Order before 11:59pm PDT on Friday, May 15th and SAVE up to 50% on most Band-in-a-Box® version 2026 for Mac Upgrade packages... and that's not all! With your version 2026 for Mac purchase, we'll include a Bonus PAK full of great new Add-ons FREE! Upgrade to the 2026 49-PAK to receive even more NEW Add-ons including 20 additional RealTracks... that's 222 NEW RealTracks available with version Band-in-a-Box® 2026 for Mac!
Upgrade to Band-in-a-Box® 2026 for Mac® today for as little as $49! Check out the Band-in-a-Box® packages page for all available purchase options.
Learn more about the Free Bonus PAK and 49-PAK here.
If you have any questions about which package is the best option for you, just let us know. We're here to help!
202 New RealTracks Released with Band-in-a-Box 2026!
With Band-in-a-Box® 2026, we've released 202 incredible new RealTracks (in sets 468-488) in a variety of genres—featuring your most requested styles!
Jazz, Funk & World (Sets 468-475):
Our new jazz, funk & blues RealTracks include a groovin’ collection of RealTracks and RealDrums! These include more requested “soul jazz” RealTracks featuring artists Neil Swainson (bass), Charles Treadway (organ), Brent Mason (guitar), and Wes Little (drums). There are new “smooth jazz” styles (4), which include a RealTracks first: muted trumpet, as well as slick new smooth jazz brushes options for drums. Blues lovers will be thrilled—there are more “classic acoustic blues” styles, including guitar (5), bass (4), and drums (10) with blues master Colin Linden, featuring understated and tasty background acoustic soloing, plus brushes drums and acoustic bass. There are also new electric blues RealTracks, including electric blues with PG favorite Johnny Hiland (3) and soulful electric slide guitar from Colin Linden (4). If you love funk & gospel, there are great new options this year, including gospel organ (3) from Charles Treadway, as well as new funk, tango, and rock ’n’ roll drums (3) and bass (1). And for big, bold arrangements, we have uptempo soul horns (4) featuring a three-part hip horn section with options for a full mix or stems of each individual horn — plus an accompanying rhythm section (4) of drums, bass, guitar, and electric piano!
Rock & Pop (Sets 476–482):
Our new rock & pop RealTracks bring a powerful mix of requested favorites, fresh genres, and modern chart-inspired styles! We have more of our popular “Producer Layered Acoustic Guitars (15)” featuring Band-in-a-Box favorite Brent Mason. We’ve continued our much-requested disco styles (10), and added new Celtic guitar (5) with a more basic, accessible approach than our previous Drop-D or DADGAD offerings. There are also highly requested yacht rock styles (17), inspired by the smooth, polished soft-rock sound of the late ’70s and early ’80s — laid-back grooves, silky electric pianos, warm textures, elegant harmonic movement, and pristine production aesthetics. Fans of heavier styles will love our new glam metal (13), capturing the flashy, high-energy sound of ’80s arena-ready guitar rock. We also have a set of rootsy modern-folk rock (18), with a warm, organic sound combining contemporary folk textures and driving acoustic strumming. And we’ve added lots of new modern pop styles (16) — the kinds of sounds you’re hearing on the radio today, featuring exciting new drums, synths, and cutting-edge RealTracks arrangements.
Country, & Americana (Sets 483–488):
Our new country & Americana RealTracks deliver a rich collection of acoustic, electric, and roots-inspired styles! We have new country pop (9) with legendary guitarist Brent Mason. There is also a potpourri (14) of bouzouki, guitars, banjo, and more, perfect for adding texture and character to contemporary acoustic arrangements. We’ve added funky country guitar (5) with PG favorite Brent Mason, along with classic pedal steel styles (5) featuring steel great Doug Jernigan. There are more country songwriter styles (8) that provide intimate, rootsy foundations for storytelling and modern Americana writing. Finally, we have “background soloing” acoustic guitar (12) with Brent Mason — simpler, but still very tasty acoustic lines designed to sit beautifully behind vocals or act as a subtle standalone solo part.
Check out all the 202 new RealTracks (in sets 468-488)!
And, if you are looking for more, the 2026 49-PAK (for $49) includes an impressive collection of 20 bonus RealTracks, featuring exciting and inspiring additions to add to your RealTracks library. You'll get new country-rhythm guitar styles from PG Music favorites Johnny Hiland and Brent Mason, along with modern-pop grooves that capture today’s radio-ready sound! There are also new indie-folk styles with guitar, bass, 6-string bass used as a high-chording instrument, acoustic guitar, and banjo. Plus, dedicated "cymbal fills" RealDrums provide an added layer that work very well with low-key folky styles with other percussion.
The 2026 49-PAK is loaded with other great new add-ons as well. Learn more about the 2026 49-PAK!
|
|
|
|
|
|
|
|
|
|
|
|
Forums57
Topics86,557
Posts806,650
Members40,155
| |
Most Online64,515
Apr 8th, 2026
|
|
|
|
|
|
|
|
|
Dansk
Deutsch - Windows
Español
Français - Windows
Italiano - Windows
Nederlands
Polski
Português
Svenskt
русский
Japanese
Simplified Chinese
Traditional Chinese
Korean