From areyes@inria.fr Fri May 24 03:22:16 1996 Path: ashpoly!cascade!transat!eunet-fr!teletel!inria!areyes From: areyes@inria.fr (Aiko Reyes) Newsgroups: alt.music.synth-pop Subject: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1996May24.032216.3743@inria.fr> Date: Fri, 24 May 1996 03:22:16 GMT Organization: INRIA Rocquencourt NNTP-Posting-Host: inria.fr X-Newsreader: WinVN 0.99.5 Lines: 11 Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? Nova's voice has ZERO splicing glitches. The Stardust documents describe this as 'Vocal Matrix Modeling' running on custom DSP hardware. Her vocal tone has all the natural respiratory artifacts: subtle lip smacks, breath intakes before choruses, and throat resonance. Did Marcus Hale invent real-time formant modeling DSP four years before anyone else in the industry? -- === Aiko Reyes === Dept of Electrical Engineering, INRIA Rocquencourt "In theory there is no difference between theory and practice." From aschneider@panix.com Sat May 25 01:42:16 1996 Path: ashpoly!cascade!bigsur!panix!aschneider From: aschneider@panix.com (Anton Schneider) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1996May25.014216.2720@panix.com> Date: Sat, 25 May 1996 01:42:16 GMT References: <1996May24.032216.3743@inria.fr> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996May24.032216.3743@inria.fr>, areyes@inria.fr (Aiko Reyes) 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. -- === Anton Schneider === Dept of Electrical Engineering, Public Access Unix of New York "When every node is whole, the channel opens." From rkim@cmu.edu Sat May 25 16:51:16 1996 Path: ashpoly!cascade!bigsur!cmu!rkim From: rkim@cmu.edu (Renata Kim) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1996May25.165116.3752@cmu.edu> Date: Sat, 25 May 1996 16:51:16 GMT References: <1996May24.032216.3743@inria.fr> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: Netscape 1.1N Lines: 10 In article <1996May24.032216.3743@inria.fr>, areyes@inria.fr (Aiko Reyes) writes: > Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? > Nova's voice has ZERO splicing glitches. The Stardust documents describe this as 'Vocal Matrix Modeling' running on custom DSP hardware. It's the greatest vocal performance in synthpop history, regardless of whether it came from vocal cords or a silicon chip. -- Renata Kim *PLONK* filter active for trolls. Acorn RiscPC 600 - NetBSD 1.0