Hatsune Miku V6 English Phoneme Guide

 

 BEFORE YOU START

Hatsune Miku V6 is not intended to be realistic, automatically perfect out of the box, or anything akin to modern AI Vocalsynth engines. This is why they didn't put AI in her Voicebank name.

However, her ease of use, tuneability and potential for expression is MUCH higher than any of her previous NT or VOCALOID Voicebanks. In this guide I'll be showing you how to make the most of her English Cross-Lingual capabilities specifically. 

VOWEL CONVERSION

Hatsune Miku is voiced by Saki Fujita, who is NOT a native English speaker. This voicebank relies heavily on VOCALOID6's AI converting her Japanese phonetics into English, even with the supplemental (speculative) Miku V4 English data added in there she still has a certain amount of trouble producing fluent English sounds.

This also is not intended to be a "fix" or an "improvement" as keeping her Japanese accent fully intact is an equally appealing process that already sounds pretty good in the first place. 

I will add spaces [ ] on the phoneme table to indicate which phoneme should take up the most space on the note. If a conversion is unneeded I'll notate it as such. There will also be points where you'll need to use Japanese phonetics to exaggerate certain dipthongs that become unclear at higher BPMs.

And finally this list is NOT comprehensive, fitting for every situation/song, or treated as "the law". I'm still learning how to use this Voicebank and I will happily take any suggestions or criticisms of this list as they come up & update it accordingly.

[Phoneme(X-SAMPA/ARPABET)]  
[Conversion]
[V]/[ah] Mostly Unneeded, but [Q] can sound more open at high ranges.
[e]/[eh] Unneeded
[I]/[ih] [I][e  ]
[i:]/[iy] Unneeded 
[{]/[ae] [e][{ ][@] 
[O:]/[ao] [O:][Q ] 
[Q]/[aa] [U][Q ] 
[U]/[uh] [U ][e] or [u: ][e] 
[u:]/[uw] Unneeded 
[@r]/[er] Mostly Unneeded, but [@r ][r] or [U][@r ] can work sometimes. 
[eI]/[ey] With Japanese phonemes: [e ][i] 
[aI]/[ay] With Japanese phonemes: [a ][e][i] 
[OI]/[oy] With Japanese phonemes: [o ][i] 
[@U]/[ow] Mostly Unneeded, but [O: ][w] can sound more open at high ranges. 
[idk what this one is in x-sampa]/[ix] [I][@] 
[I@]/[iy r] [i: ][@r] 
[e@]/[eh r] [e ][@r] 
[O@]/[ao r] [O: ][@r] 
[Q@]/[aa r]

[Q ][@r] 

 

 

CONSONANT CONVERSION

These are mostly fine, but you can get a bit more emphasis/attack out of them if you do a little tinkering.

There is one phoneme that has a labelling quirk at the end, but once you figure out how it works it's pretty easy to take advantage of.


[Phoneme(X-SAMPA/ARPABET)]  
[Conversion]
[r]/[r] Unneeded, but a [@r] in the leadup to an [r] always helps.
[l0]/[l] Unneeded but [@][l ] works as a replacement for [@l]
[v]/[v] Unneeded
[T]/[th] Unneeded
[D]/[dh] Unneeded
[Z]/[zh] Unneeded
[t]/[t] [t ][s]

[d]/[d]

[4][dx] 

[d ][z]

This one's weird, they labeled [t] as a [th] when the consonant is large and a [4] when it's timed to be small, so edit the phoneme timing and make it barely take up any space and it'll sound out a [4] 

Comments

Post a Comment

Popular posts from this blog

Basic Vocal Mixing tutorial

Image
For this basic tutorial I'll try to only use the most default plugins in a DAW so that this method can be accessible to everyone. If you want a version more advanced I will make an update later detailing my regular process!! Plugins and Their Order 1. EQ (for cutting frequencies) 2. Multiband Compressor (for compressing the low-mid frequencies only) 3. Compressor (for making the vocal stand out above the instrumental) 4. EQ (for boosting frequencies) 5. Limiter (for catching what the compressor couldn't) 6. a De-esser of some sort (for de-essing, duh!) 7. Reverb (for making the vocals sound less dry) it's very important to place them specifically in this order, as the plugins affect eachother as long as they're *ABOVE* one another (took me a while to realize this ^^;)   1. EQ This EQ Will be used for cutting low frequencies, try not to use more than 3 points/bands unless you absolutely have to! Remember, the tip to good EQing is that less is usually more.  The most cruc...
Read more

How to make Hatsune Miku NT1.0 sing in somewhat fluent english

Image
 BEFORE YOU START This guide will only teach you how to correct pronunciation, there aren't really any concrete rules on pitch or whatever else tuning you'll be using this for. Hatsune Miku NT is a Japanese voice library that doesn't have any English capabilities whatsoever and this is a pretty involved process since you'll have to fully tune your main vocals in two separate engines, but I think the end result is definitely worth it. If you're down with all that, let's get started.
Read more

Basic VOCALOID Tuning Tip (But A Little Bit More Advanced Than Usual)

Image
  Notebending VS Pitch bending (and what that means) Have you ever seen people tune something like either of these two examples? A) Notebending B) Pitch Bending Allow me to explain the reasoning behind the methods. "Notebending" is when you move the notes to alter the pitch by splitting one note into several and moving the start or end of it around, you can get SUPER creative with this and there are a lot of examples of super unique sounding tuning that's not *quite* realistic and not *quite* robotic by pretty much only doing this for the whole track. when people notebend they usually either use it alongside a vibrato Job Plugin like Expressive Vibrato , or they just use it to stabilize the VOCALOID pitch. more on that some other time. You don't have to use the [-] phoneme for this technique, honestly I avoid using it most of the time. it works if you double up on vowels, too, like this. This is my usual process: you can also "notebend" consonants! (sort of,...
Read more