Anthony C. Bartman
Here's what the raw data of the unit selection db file for SpeakEasy sounds like. It gives you a good idea on how unit selection synthesis works.
Mar 13 at 4:57amWeb
Show threadJake GrossMar 13
@rommix0 If my theory about the engine using MBROLA as a backend is correct, what we are actually hearing are the building blocks for a diphone based voice. When I listened to the clip you posted, it sounded familiar, and after listening to the clip of the synth itself, I remembered listening to the raw data of EN1 a while back.
Show threadAnthony C. BartmanMar 13
@datajake1999 in a way, yeah. It's like MBROLA, but not actually MBROLA since speakeasy is proprietary.
Show threadAlex Chapman (moved to new account)Mar 13
@rommix0 @datajake1999 Yeah I definitely recognise that as diphone based synthesis.
Show threadBorrisMar 13
@rommix0 is that 8-bit linear PCM?
Show threadAnthony C. BartmanMar 13
@BorrisInABox nah, it's 16 bit. I'm sure the data has subheaders.
Show threadBorrisMar 13
@rommix0 Wow, really? Sounds very 8-bit or less in that clip.
Show threadAnthony C. BartmanMar 13
@BorrisInABox you would think that
Show threadx0Mar 13
@rommix0 @BorrisInABox Or some kind of compressed.
Show threadAnthony C. BartmanMar 13
@x0 @BorrisInABox yeah like adpcm
Show threadSpacedogMar 13
@rommix0 i think it's diphone, specifically, the embrola en1 database
Show threadAnthony C. BartmanMar 13
@spacepup Nah. en1 is english but with a foreign speaker. The speaker used for SpeakEasy is not a foreigner.
Show threadAlanMar 14
@rommix0 sounds like a fucked up vocal warmup
Show threadKeao WrightMar 14
@rommix0 what is speak easy?
Show threadAnthony C. BartmanMar 14
@keao tts synth