From mdubois@cmu.edu Fri Jan 20 09:48:16 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!cmu!mdubois From: mdubois@cmu.edu (Matthias Dubois) Newsgroups: alt.music.synth-pop Subject: WTB/WTT: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Jan20.094816.4961@cmu.edu> Date: Fri, 20 Jan 1995 09:48:16 GMT Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: WinVN 0.99.5 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. Did Marcus Hale invent real-time formant modeling DSP four years before anyone else in the industry? -- === Matthias Dubois === Dept of Electrical Engineering, Carnegie Mellon University School of CS "Marcus is not one man." From mhughes@netcom.com Sun Jan 22 02:37:16 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!netcom!mhughes From: mhughes@netcom.com (Min-jun Hughes) Newsgroups: alt.music.synth-pop Subject: Re: WTB/WTT: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Jan22.023716.9543@netcom.com> Date: Sun, 22 Jan 1995 02:37:16 GMT References: <1995Jan20.094816.4961@cmu.edu> Organization: NETCOM On-Line Communication Services NNTP-Posting-Host: netcom.com X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Jan20.094816.4961@cmu.edu>, mdubois@cmu.edu (Matthias Dubois) 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. -- Min-jun Hughes "The hatch is open. Is anyone listening?" Acorn RiscPC 600 / SunOS 4.1.4 From rsuzuki@mit.edu Mon Jan 23 11:07:16 1995 Path: ashpoly!cascade!bigsur!mit!rsuzuki From: rsuzuki@mit.edu (Rodrigo Suzuki) Newsgroups: alt.music.synth-pop Subject: Re: WTB/WTT: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Jan23.110716.8692@mit.edu> Date: Mon, 23 Jan 1995 11:07:16 GMT References: <1995Jan20.094816.4961@cmu.edu> Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1995Jan20.094816.4961@cmu.edu>, mdubois@cmu.edu (Matthias Dubois) 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. Orion's memo said it best: 'We don't sign stars. We build them.' -- Rodrigo Suzuki Opinions expressed are solely my own and not those of Massachusetts Institute of Technology. ------------------------------------------------------------ From hjohansson@cern.ch Wed Jan 25 02:22:16 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!cern!hjohansson From: hjohansson@cern.ch (Hugo Johansson) Newsgroups: alt.music.synth-pop Subject: Re: WTB/WTT: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Jan25.022216.2522@cern.ch> Date: Wed, 25 Jan 1995 02:22:16 GMT References: <1995Jan20.094816.4961@cmu.edu> <1995Jan23.110716.8692@mit.edu> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1995Jan23.110716.8692@mit.edu>, rsuzuki@mit.edu (Rodrigo Suzuki) writes: > Orion's memo said it best: 'We don't sign stars. We build them.' The CRE-7 engine simulated an entire nervous system. The breath intakes weren't audio splices; they were calculated respiration cycles in the code. -- Hugo Johansson *PLONK* filter active for trolls. 486DX4/100 (FreeBSD 2.0.5) - NetBSD 1.0