Introducing Arpasing for English UTAUloids

A few months ago I uploaded a document proposing a new English UTAU recording script with detailed specifications. As an attempt to basically replicate a unit-selection based speech synthesizer in UTAU, the new standard was named Arpasing. Thanks to a few users who recorded the very first Arpasing voicebanks in spite of the lack of clear instructions, we're now able to further explore the uncharted land with Moresampler 0.8.0's built-in support for Arapsing oto generation. Here I'm launching another tool, and this time for actually creating USTs with Arpasing.

Please keep in mind that Arpasing is an experiment, and we don't yet know if it's going to work well, until more efforts are made to revise the tools & voicebanks.

Moresampler 0.8.0 Release

Here is the long-awaited Moresampler 0.8.0.

Moresampler 0.7.2 Release

Moresampler 0.7.2 is in the transition between 0.7.x and 0.8.x - Arpasing is not supported yet but some oto-generation features such as loading files from index.csv are implemented. There are some code refactoring & bug fixes as well.

The oto generator now is able to generate CVVC oto entries. Regardless of the format of input (hiragana/romaji), it outputs in any format you want. Once a voicebank is loaded there will be a prompt in the command line window asking for output format.

In response to feedback that Moresampler's oto generator creates a lot of redundant (in a diphone synthesis sense) unit aliases, I've added an option that only updates the existing entries in a given oto.ini file, but not creating any new entry. Note that to enable this feature you need to have a "vanilla" oto.ini under the voicebank directory first.

Initial Results & Facts on Arpasing

Shortly after the release of Arpasing proposal, Adlez recorded a test voicebank and sent back to me in almost no time. I'd like to thank Uchuu and BagHeadChan for their contribution as well. Those data really helped me to work out a roughly working solution to voicebank labeling so I could start actually making songs with Arpasing voicebanks.

Here are two short samples I've created with Adlez's voicebank,

Unravel (English ver, lyrics by Lucy)

("Oh won't you tell me, please just tell me, explain how this should work. I fear who could it be, that lives inside of me. My conscience cracking, mind reacting, surrounded by the world. But here you're smiling bright, completely blind to life.")

Tokio Funka (English ver, lyrics by Jayn)

("In a hazy town with deception all around, there's a dusty cloud that drifts downward to the ground.")

Proposal of Arpasing, English UTAU Reclist & Specs

At the end of this two-month initial design phase, I proudly present Arpasing, a scientifically-designed English recording script and naming standard for UTAU.

Followed immediately after Moresampler 0.7.0's release, people were asking me if the oto generation feature would ever support English. I said yes, but later found the method for Japanese wasn't directly applicable for English, because of the myriad of different recording schemes each with its own phonetic notation. Writing wrappers for each of them seems to be a quite troublesome business, so I began to try if it's possible to unify the existing solutions into one.

And I also tried to tailor and apply the corpus design methods in academic publications on this very specific problem. The result may appear a bit bizarre and intimidating at a first glance, but much more concise than ever before. It achieves 96% diphone coverage in 120 tri-syllable utterances, and 42% triphone coverage in another 100 utterances.

Looking for someone to join Moresampler development

Within a year Moresampler has grown from a small project with frequent crashes to something fast and robust built on the top of 10 libraries; latest research outcomes from the academia of audio and speech processing have been implemented, bringing synthesis quality up to an unprecedented level.

Up to this date Moresampler is designed, developed and maintained by a single person (me), but it's getting increasingly harder to keep up with the growing number of feature requests & bug reports while on the other hand, there are ideas and areas I would like to explore but are beyond the reach of a single developer (or may take tremendous time/efforts to accomplish). To make Moresampler even better, I'm looking for a collaborator to join the R&D.

Moresampler 0.7.1 Release

(Oct. 26, 2016 - Moresampler 0.7.2 is released!)

This summer I traveled a lot so Moresampler was halted for 2 months, sorry guys. The good thing is that I'm now back with full energy and motivation!

Moresampler 0.7.1 comes with mostly bug fixes and feature improvements. Though there's no new feature added, it puts some really annoying things (e.g. glitches at the end of a note) to an end. In addition the codes have been refactored so as to make it easier to add new features in the next release; by then Moresampler will support CVVC-style oto generation. By the way the current version already supports romaji voicebanks for oto generation.

Another important thing to announce is that I'm looking for someone to help me with developing and maintaining Moresampler. More information is posted here.

I'm currently on vacation

Sorry guys I'm currently on a trip to Japan and later to attend a summer school in Europe, so I have to stop maintaining/updating Moresampler for a few weeks until mid August. Thanks for your understanding.

p.s. If anyone wanna meet up please ping me back. I'll be in Tokyo from Jul 14 to Jul 19.

Moresampler 0.7.0 Release

(Aug. 23, 2016 - Moresampler 0.7.1 is released!)

If you've seen the readme of Moresampler you probably are familiar with this line which exists since the first version (0.1.5),

Moresampler is a synthesis backend for singing voice synthesis program UTAU. Literally the name suggests that Moresampler is not only a UTAU resampler. In fact, it is a resampler and wavtool combined in one executable.

And now Moresampler even takes a step further - it's a resampler, a wavtool and an automatic voicebank configurator combined in one executable. By simply dragging a folder of wave files onto Moresampler, you can get a machine-generated oto.ini within 2 minutes.

Moresampler 0.6.4 Release

(Jun. 7, 2016 - Moresampler 0.7.0 is released!)

This is a minor revision which fixes several bugs reported to occur on previous version (0.6.3).

Download Moresampler 0.6.4 here

For bug reporting, please go to Moresampler Bug Report Page.