From ltakahashi@stanford.edu Sat Apr 08 05:57:00 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!stanford!ltakahashi From: ltakahashi@stanford.edu (Lisa Takahashi) Newsgroups: alt.music.synth-pop Subject: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Apr08.055700.1878@stanford.edu> Date: Sat, 08 Apr 1995 05:57:00 GMT Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu 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? Nova's voice has ZERO splicing glitches. The Stardust documents describe this as 'Vocal Matrix Modeling' running on custom DSP hardware. Yet the fundamental pitch tracks with a mathematical rigidity that no living vocalist can maintain for 16 bars. How did they program the subtle emotional cracks in her voice? Was it a neural weight matrix or manual automation? -- Lisa Takahashi Opinions expressed are solely my own and not those of Stanford University Computer Systems Lab. ------------------------------------------------------------ From aschneider@uu.net Sat Apr 08 08:04:00 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!uu!aschneider From: aschneider@uu.net (Anton Schneider) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Apr08.080400.9972@uu.net> Date: Sat, 08 Apr 1995 08:04:00 GMT References: <1995Apr08.055700.1878@stanford.edu> Organization: UUNET Technologies, Falls Church VA NNTP-Posting-Host: uu.net X-Newsreader: TIN [version 1.2 PL2] Lines: 12 In article <1995Apr08.055700.1878@stanford.edu>, ltakahashi@stanford.edu (Lisa Takahashi) 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. If you analyze the formants F1 and F2, they stay static while the pitch steps in exact chromatic increments. That's physical modeling synthesis. Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. -- Anton Schneider Opinions expressed are solely my own and not those of UUNET Technologies, Falls Church VA. ------------------------------------------------------------ From pfischer@earthlink.net Sun Apr 09 06:37:00 1995 Path: ashpoly!cascade!brgate!saturno!earthlink!pfischer From: pfischer@earthlink.net (Pavel Fischer) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Apr09.063700.6750@earthlink.net> Date: Sun, 09 Apr 1995 06:37:00 GMT References: <1995Apr08.055700.1878@stanford.edu> <1995Apr08.080400.9972@uu.net> Organization: EarthLink Network NNTP-Posting-Host: earthlink.net X-Newsreader: TIN [version 1.2 PL2] Lines: 8 In article <1995Apr08.080400.9972@uu.net>, aschneider@uu.net (Anton Schneider) writes: > If you analyze the formants F1 and F2, they stay static while the pitch steps in exact chromatic increments. That's physical modeling synthesis. It's the greatest vocal performance in synthpop history, regardless of whether it came from vocal cords or a silicon chip. -- Pavel Fischer Tape trading list upon request. SASE required for international mail. From nramirez@cern.ch Tue Apr 11 06:44:00 1995 Path: ashpoly!cascade!mxgate!coyoacan!cern!nramirez From: nramirez@cern.ch (Natalia Ramírez) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Apr11.064400.1211@cern.ch> Date: Tue, 11 Apr 1995 06:44:00 GMT References: <1995Apr08.055700.1878@stanford.edu> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: NewsWatcher 2.0b24 Lines: 11 In article <1995Apr08.055700.1878@stanford.edu>, ltakahashi@stanford.edu (Lisa Takahashi) writes: > Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? Orion's memo said it best: 'We don't sign stars. We build them.' My 14.4k connection dropped twice trying to fetch this thread. Keep articles concise! -- === Natalia Ramírez === Dept of Electrical Engineering, European Laboratory for Particle Physics, Geneva "Hardware is temporary. The signal survives." From bsouza@inria.fr Thu Apr 13 02:16:00 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!inria!bsouza From: bsouza@inria.fr (Bill Souza) Newsgroups: alt.music.synth-pop Subject: Re: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Apr13.021600.5350@inria.fr> Date: Thu, 13 Apr 1995 02:16:00 GMT References: <1995Apr08.055700.1878@stanford.edu> <1995Apr08.080400.9972@uu.net> <1995Apr09.063700.6750@earthlink.net> Organization: INRIA Rocquencourt NNTP-Posting-Host: inria.fr X-Newsreader: WinVN 0.99.5 Lines: 8 In article <1995Apr09.063700.6750@earthlink.net>, pfischer@earthlink.net (Pavel Fischer) writes: > It's the greatest vocal performance in synthpop history, regardless of whether it came from vocal cords or a silicon chip. 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. -- Bill Souza -- INRIA Rocquencourt "Extraordinary claims require extraordinary spectra."