SynthV Wiki
Advertisement
This article is still a work in progress

This article is slowly being improved for the benefit of all visitors. Please bear with us while improvements are being made. We apologise for the inconvenience this may cause in the meantime.
(What's Being worked on: Spelling/usage/type of Japanese romanization/Romaji, recording scripts, etc.)

(Inspired by VW page of the same name.)

About[]

The origin of the language is mostly unknown, including when it first appeared in Japan. Its main influences are Chinese and Old Japanese. More modern decades have seen many European influences on the language, especially many English loanwords having been adopted into the Japanese phonetic system. However, the lack of influence from other languages, in addition Japan's isolation from the rest of the world, has contributed much to the precision of the Japanese phonetic system.

Far less new sounds entered the language for many centuries, in comparison to other ones such as English which had heavy influences from other languages.

Synthesizer V and the Japanese language[]

(We can talk about the spelling, usage, and type of Romaji –Hepburn, Kunrei-Shiki, Nihon-Shiki, etc.–, and other technical stuffs)

Japanese recording scripts[]

(Not fully unveiled but on AHS Stream #169, they showed the glimpse of it. Actual words to ease the recording effort while also to cover as much phoneme transitions as possible <-- it's for "standard" voice databases, and likely the standard recording scripts. AI one, the collection of songs and other stuffs is yet to be known.)

Notes on accents[]

Despite the general belief that singers completely lose their accents when they sing, this is not the case in every instance, and an accent is possible to be heard even in singing vocals.

However, the reason many are led to believe this is that there are several methods of training singers to disguise or otherwise hide their natural accents—they may even adopt an accent that isn't their own for singing. Samples include genres such as western or country, black music such as jazz or soul. Singing also uses different muscles to speech, resulting in difference of air pressure and way the throat moves. Genres such as opera are most likely to make a accent appear almost entirely absent thanks to the impact of the opera vibrato.[1][2]

Synthesizer V will capture any form of accent quite easily at times. It depends on the recording method used by the voice provider, type of sound being recorded per sample (accent impact varies per sample and language) and –for the case of Standard voice databases– overall number of samples that make up the voice database (the more samples, the more chance of it slipping in). (Types of voice database produced: "Standard" concatenative by "chanting" the scripts contains almost all possible phoneme transitions in particular pitches and tempos; or AI-based by actually sing, apparently also impact the accent.)

Native accented[]

Non-native accented[]

Synthesizer V Studio version 1.5.0 introduced the Cross-Lingual Singing Synthesis feature, which allows all AI voice databases to sing in all languages supported by the software, regardless of the language(s) in which they're recorded. All voice databases recorded in languages other than Japanese are considered to be non-native accented, due to a deliberate decision to leave subtle accents in place.[3]

  • Xingchen: Confirmed to be recorded with Japanese training material to enhance Cross-lingual Singing Synthesis capabilities, though Xingchen Infinity was not considered to be a Japanese voice database by Beijing Photek S&T Development Co., Ltd., labelling and categorizing her as a Mandarin Chinese voice library only.[4] Her voice provider, Chalili, is a Chinese singer who was known to have lived abroad in Japan.
  • JUN: Confirmed to be recorded with Japanese training material to enhance Cross-lingual Singing Synthesis capabilities, though JUN was not considered to be a Japanese voice database by AUDIOLOGIE Co., Ltd., labelling him as an English voice library only.[5] He also has a Vocal Mode ("Tsubaki") specifically designed to improve his Japanese pronunciation and accent. Information about Lavy, JUN's voice provider, is largely unknown, including his proficiency in Japanese.
  • ANRI Arcane: Unlike ANRI's original voice database, ANRI Arcane was confirmed to be recorded with Japanese training material to enhance Cross-lingual Singing Synthesis capabilities, though ANRI Arcane was not considered to be a Japanese voice database by AUDIOLOGIE Co., Ltd., labelling her as an English voice library only.[6] She also has a Vocal Mode ("Sumire") specifically designed to improve her Japanese pronunciation and accent. Information about kurapichu, ANRI's voice provider, is largely unknown, including her proficiency in Japanese.

Accent unknown[]

  • Topaz: Her voice provider Elley, of Korean origin, is able to sing well in three languages, including Japanese (which is Topaz's base voice-database language).

Phonetic system's characteristics[]

Phonetic list[]

Symbol Classification IPA symbol/name Example Notes Related phonemes
a vowel ä open central unrounded vowel a
i vowel i close front unrounded vowel i y (glide)
u vowel ɯᵝ or ɯ͡β close back compressed vowel u The Japanese "u" is neither rounded u nor unrounded ɯ, but compressed. w (glide)
e vowel mid front unrounded vowel e
o vowel mid back rounded vowel o
N syllabic consonant n Realizations are dependent on phonological contexts. See Japanese phonology#Moraic nasal for more info. m (onset consonant)
n (onset consonant)
cl gemination or consonant Elongate the following consonant. Act as a /ʔ/ glottal stop intervocalic. Works poorly in the older Synthesizer V editor.
t consonant t voiceless alveolar plosive ta ty (palatalized)
ch (affricated)
d consonant d voiced alveolar plosive da t (voiceless)
dy (palatalized)
s consonant s voiceless alveolar sibilant sa z (voiced)
sh (palatalized)
ts (affricated)
sh consonant ɕ or ʃʲ voiceless alveolo-palatal sibilant しゃ sha Palatalized /s/. ch (affricated)
s (depalatalized)
j consonant ʥ voiced alveolo-palatal affricative
ʑ or ʒʲ voiced alveolo palatal sibilant
ji Palatalized /z/, /dz/ or /d/. sh (voiceless)
z (depalatalized)
ch (voiceless)
d (deaffricated)
z consonant z voiced alveolar sibilant za s (voiceless)
j (palatalized)
ts consonant ʦ voiceless alveolar affricate tsu z (voiced)
t (deaffricated)
s (spirantized)
k consonant k voiceless velar plosive ka g (voiced)
ky (palatalized)
g consonant ɡ voiced velar plosive ga Some Japanese singers often nasalize this consonant. The Synthesizer V engine also mimics this phenomenon by nazalizing the consonant depending on the voice database, taking a guess based on context. k (voiceless)
gy (palatalized)
h consonant h voiceless glottal fricative ha hy (palatalized)
f (labialized)
b consonant b voiced bilabial plosive ba Some Japanese singers often weaken this consonant. The Synthesizer V engine also mimics this phenomenon by weakening the consonant depending on the voice database, taking a guess based on context. p (voiceless)
by (palatalized)
p consonant p voiceless bilabial plosive pa b (voiced)
py (palatalized)
f consonant ɸ voiceless bilabial fricative ふぁ fa h (debuccalized)
p (spirantized)
ch consonant ʨ voiceless alveolo palatal affricate ちゃ cha Palatalized /t/. j (voiced)
ts (palatalized)
t or ty (deaffricated)
sh (spirantized)
ry consonant Typically:
ɾʲ palatalized alveolar tap
りゃ rya Palatalized r. r (depalatalized)
ky consonant palatalized voiceless velar plosive きゃ kya Palatalized /k/. gy (voiced)
k (depalatalized)
py consonant palatalized voiceless bilabial plosive ぴゃ pya Palatalized /p/. by (voiced)
p (depalatalized)
dy consonant palatalized voiced alveolar plosive でゃ dya Palatalized /d/. ty (voiceless)
d (depalatalized)
ty consonant palatalized voiceless alveolar plosive てゃ tya Palatalized /t/. dy (voiced)
t (depalatalized)
ny consonant ɲ or nʲ palatal nasal にゃ nya Palatalized /n/. n (depalatalized)
hy consonant ç voiceless palatal fricative ひゃ hya In Japanese it is perceived as a palatalized /h/. h (depalatalized)
my consonant palatalized bilabial nasal みゃ mya Palatalized /m/. m (depalatalized)
ny (delabialized)
gy consonant ɡʲ palatalized voiced velar plosive ぎゃ gya Palatalized /ɡ/. ky (voiced)
g (non-palatalized)
by consonant palatalized voiced bilabial plosive びゃ bya Palatalized /b/. py (voiceless)
b (depalatalized)
n consonant n alveolar nasal na ny (palatalized)
m (labialized)
m consonant m bilabial nasal ma my (palatalized)
n (delabialized)
r consonant Typically:
ɾ Apical alveolar tap
ra See Japanese phonology#Consonants for more info. ry (palatalized)
v consonant vu What is this phoneme supposed to be? Is this the real /v/, just the same with the weakened b, or something else?
w consonant w͍ or wᵝ compressed labio-velar approximant wa Similar to /u/, the Japanese /w/ is compressed. u (syllabic)
y consonant j palatal approximant ya i (syllabic)
kw consonant labialized voiceless velar plosive くゎ kwa Labialized /k/. Introduced new in Synthesizer V Studio. Works poorly in early voice databases. (Currently unknown if subsequent updates –especially for AI voice databases– have already fixed this.) gw (voiced)
k (delabialized)
gw consonant ɡʷ labialized voiced velar plosive ぐゎ gwa Labialized /ɡ/. Introduced new in Synthesizer V Studio. Works poorly in early voice databases. (Currently unknown if subsequent updates –especially for AI voice databases– have already fixed this.) kw (voiceless)
g (delabialized)

References[]

See also[]

Navigation[]


Advertisement