Help with German?

So make a long story short I’m wanting to make a Solaria Cover of Ode to Joy in German, the issue being I don’t speak German. I’m aware of the dictionary, but it’s imperfect and a lot of words didn’t get properly transcribe when I tried to use it. They were missing. And apparently a lot of the words it did fix doesn’t sound right, at least according to my German Friends.

So I’m looking for help or pointers.

Maybe something like this could help: Automatic Phonemic Transcriber ?

When I bought Saros from Eclipsed Sounds, it came with a German dictionary, but I didn’t really test it … just had a short look, which looked quite ok.

But this dictionary is huge and causes a delayed start of Synth V.

Which words do you have issues with?

I can confirm that, I live in Germany.
The “ENG-GER1.0_EclipsedSounds.json” dictionary provided by Eclipsed Sound is very comprehensive, but does not reflect many words in the best possible way.

An example is the simple sentence “Ich freue mich” (= I’m happy).
With the dictionary mentioned you get:

image

You can get closer to the German pronunciation with the following phonemes, although of course you can still hear a clear English accent

image

I randomly chose the example with Solaria, but with another VoiceDB it could be completely different.

In this respect, it would be difficult for a non-native speaker to immediately find suitable phonemes for a German text.

The phoneme generator from the website http://tom.brondsted.dk/text2phoneme/?vieweval&l=German is not suitable for Synth V at all.

I fear, that’s something we need to live with, because Weina for example also has a Chinese accent, when singing English.

It’s also worth noting, that Saros is the only voice, that can sing in Spanish, but you’ll need the current Beta of SynthV.

Conclusion: It seems we need an update to both the voice DB and SynthV to get full support for German singing?

1 Like

:+1:
An update that improves German pronunciation would be worth a lot to me!
For example, I use Synth V pro to create demo versions for a choir. Many pieces from the repertoire are in German.

For me it’s not very interesting, but in a German music production forum are many people, that would be interested … keyword: “Schlager” :wink:

I hate this kind of music.

But for Dreamtonics and Eclipsed Sounds it might be worth it … German language is pretty hip for example in the USA.

PS: Drop them a feature request by mail. Maybe German comes next after Spanish?

1 Like

The German dictionary provided by Eclipsed Sounds is automatically generated. That is to say, they likely cross-referenced a list of German words and their respective IPA pronunciations with the English phonemes in SynthV Studio on a “closest similar sound” basis. This is why the dictionary is so large, but makes somewhat naive assumptions about German pronunciation.


For a new language to be supported, there’s a significant amount of R&D work that needs to be done, as shown by the time and effort that has gone into the introduction of Cantonese by Dreamtonics and Spanish by Eclipsed Sounds.

I expect we’ll slowly see more languages added, but it’s probably a rather unique challenge to find partners with the necessary expertise to make it a reality and accelerate the process, and as more languages are added there’s the added challenge that the next language may not be spoken by any of the existing staff, requiring additional consultation or partnerships.

3 Likes

AI may also speed up the process here. Thanks to the stem separation software available on the market, a large number of solo singing pieces can now be made available that should be suitable for training the new language. In any case, I’m excited to see what happens in this area in the near future.

Not for this use case though. Commercial vocal synths only use recordings they have the rights to in the dataset, and the added noise or artifacts in the source material would make for a poor quality product (cleaning the samples is already a big part of the work that goes into making a voice database, and that’s with studio recordings).

Using isolated vocals from songs they don’t have the rights to could very easily end up with Dreamtonics in legal trouble. Image generators get away with it because independent artists largely don’t have the means to defend their copyright; the same cannot be said for music labels.

3 Likes

How did text-to-speech programs achieve their incredible authenticity? Certainly not with a speaker who has read out every conceivable combination of words, but by evaluating a huge number of spoken audio recordings. :thinking:

This is how I (in my simplicity) wanted to imagine Synth V: an AI model is trained with a large number of anonymized vocal recordings and the pronunciation is then “imprinted” on a specific voice. But it doesn’t seem to be that simple… :roll_eyes:

Ahaaa … so the first step would be to correct it … a job for German users :wink: … and a lot of work.

Be patient, my friends. I just finished the German Schlager Hit “Wahnsinn” by Wolfgang Petry and used Kevin as singer. Needs a little bit of tweaking but then I will upload it on Youtube and see what happens.

1 Like

Unless a native German singer is used to build the voice library, you will never capture the German accent no matter which phonemes you use.
Same with French.
Unless Dreamtonics believe it is commercially viable to produce a German voice library you’ll only ever get an English or Chinese pronunciation of German words (or whatever the native language of the original singer)
I would love to have a UK English voice but I doubt it will happen.
You can tame the American accent to a degree but ‘r’ for example, will always sound American despite being English.

That’s more likely than a German singer. Don’t forget that Ninezero is Australian. AND … British Pop & Rock is a huge market.

True. Ninezero is one I don’t have as I didn’t really want a low voice, or Australian. :grinning:
Fingers crossed for loads more in 2024.

His voice isn’t low, but rough, comparable to Ozzy.

As discussed in another forum, I would like a Rock voice in the style of Chris Robertson of Black Stone Cherry … rough and a bit lower. Ninezero’s voice is pretty high for a Rock voice … as I said very similar to Ozzy.

Fact is, I don’t like all other male voices being available, except Saros, which is the most versatile IMO. Asterian is something for Black Music and the others sound like a boygroup … LOL.

Ich habe nun dies ausprobiert und es kam dem hörbaren Resultat am nächsten.
I have now tried this and it came closest to the audible result.
Screenshot 2024-02-04 alle 12.18.22
Screenshot 2024-02-04 alle 12.18.55
Screenshot 2024-02-04 alle 12.23.49

2 Likes

With which Voice DB?

With Hayden