From avasiliev@kiae.su Tue Oct 22 05:55:24 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!kiae!avasiliev From: avasiliev@kiae.su (Aiko Vasiliev) Newsgroups: alt.music.synth-pop Subject: [SPECULATION] The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1996Oct22.055524.4817@kiae.su> Date: Tue, 22 Oct 1996 05:55:24 GMT Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? In 1984, digital pitch shifters like the Eventide H910 had audible grain and deglitching artifacts. Nova's voice has ZERO splicing glitches. The Stardust documents describe this as 'Vocal Matrix Modeling' running on custom DSP hardware. How did they program the subtle emotional cracks in her voice? Was it a neural weight matrix or manual automation? -- Aiko Vasiliev *PLONK* filter active for trolls. Mac IIci / 68882 FPU - NetBSD 1.0 From goliveira@cern.ch Thu Oct 24 03:15:24 1996 Path: ashpoly!cascade!transat!eunet-fr!teletel!cern!goliveira From: goliveira@cern.ch (Graham Oliveira) Newsgroups: alt.music.synth-pop Subject: Re: [SPECULATION] The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1996Oct24.031524.1751@cern.ch> Date: Thu, 24 Oct 1996 03:15:24 GMT References: <1996Oct22.055524.4817@kiae.su> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1996Oct22.055524.4817@kiae.su>, avasiliev@kiae.su (Aiko Vasiliev) writes: > Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? > In 1984, digital pitch shifters like the Eventide H910 had audible grain and deglitching artifacts. That's why it hits you in the uncanny valley. Your ears tell you it's a real woman singing her heart out, but your brain detects the mechanical precision. -- Graham Oliveira | goliveira@cern.ch PGP Key fingerprint: 547B C292 B50E 21FF "Keep the channels open." From jkang@cern.ch Thu Oct 24 15:40:24 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!cern!jkang From: jkang@cern.ch (Ji-woo Kang) Newsgroups: alt.music.synth-pop Subject: Re: [SPECULATION] The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1996Oct24.154024.3125@cern.ch> Date: Thu, 24 Oct 1996 15:40:24 GMT References: <1996Oct22.055524.4817@kiae.su> <1996Oct24.031524.1751@cern.ch> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: Netscape 1.1N Lines: 9 In article <1996Oct24.031524.1751@cern.ch>, goliveira@cern.ch (Graham Oliveira) writes: > That's why it hits you in the uncanny valley. Your ears tell you it's a real woman singing her heart out, but your brain detects the mechanical precision. That's why it hits you in the uncanny valley. Your ears tell you it's a real woman singing her heart out, but your brain detects the mechanical precision. -- Ji-woo Kang | jkang@cern.ch PGP Key fingerprint: 2821 1981 A87D 3672 "Keep the channels open." From atakahashi@berkeley.edu Fri Oct 25 04:27:24 1996 Path: ashpoly!cascade!brgate!saturno!berkeley!atakahashi From: atakahashi@berkeley.edu (Anton Takahashi) Newsgroups: alt.music.synth-pop Subject: Re: [SPECULATION] The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1996Oct25.042724.4033@berkeley.edu> Date: Fri, 25 Oct 1996 04:27:24 GMT References: <1996Oct22.055524.4817@kiae.su> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1996Oct22.055524.4817@kiae.su>, avasiliev@kiae.su (Aiko Vasiliev) writes: > Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? > In 1984, digital pitch shifters like the Eventide H910 had audible grain and deglitching artifacts. They weren't using off-the-shelf Eventide gear. They had custom Motorola DSP boards doing LPC (Linear Predictive Coding) resynthesis. -- Anton Takahashi Opinions expressed are solely my own and not those of UC Berkeley Department of EECS. ------------------------------------------------------------