From tkim@delphi.com Wed Apr 27 00:55:17 1994 Path: ashpoly!cascade!transat!eunet-fr!teletel!delphi!tkim From: tkim@delphi.com (Tomas Kim) Newsgroups: alt.music.synth-pop Subject: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1994Apr27.005517.9852@delphi.com> Date: Wed, 27 Apr 1994 00:55:17 GMT Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com 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? Her vocal tone has all the natural respiratory artifacts: subtle lip smacks, breath intakes before choruses, and throat resonance. Nova's voice has ZERO splicing glitches. The Stardust documents describe this as 'Vocal Matrix Modeling' running on custom DSP hardware. Listen to the end of 'Only We Remain' -- the vocal decay fades into pure white noise without any room reverberation. -- Tomas Kim "Extraordinary claims require extraordinary spectra." Acorn RiscPC 600 / AmigaOS 3.1 From jpetrov@netcom.com Wed Apr 27 04:03:17 1994 Path: ashpoly!cascade!transat!sunet!nordrelay!netcom!jpetrov From: jpetrov@netcom.com (Jens Petrov) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1994Apr27.040317.5679@netcom.com> Date: Wed, 27 Apr 1994 04:03:17 GMT References: <1994Apr27.005517.9852@delphi.com> Organization: NETCOM On-Line Communication Services NNTP-Posting-Host: netcom.com X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1994Apr27.005517.9852@delphi.com>, tkim@delphi.com (Tomas Kim) writes: > Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? > Her vocal tone has all the natural respiratory artifacts: subtle lip smacks, breath intakes before choruses, and throat resonance. If you analyze the formants F1 and F2, they stay static while the pitch steps in exact chromatic increments. That's physical modeling synthesis. -- Jens Petrov Tape trading list upon request. SASE required for international mail. From twatanabe@utexas.edu Wed Apr 27 07:42:17 1994 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!utexas!twatanabe From: twatanabe@utexas.edu (Takeshi Watanabe) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1994Apr27.074217.1934@utexas.edu> Date: Wed, 27 Apr 1994 07:42:17 GMT References: <1994Apr27.005517.9852@delphi.com> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 11 In article <1994Apr27.005517.9852@delphi.com>, tkim@delphi.com (Tomas Kim) writes: > Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? 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. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Takeshi Watanabe | twatanabe@utexas.edu PGP Key fingerprint: AC8D 6947 4D0E E44E "Keep the channels open."