From iweber@cam.ac.uk Wed Jul 05 12:43:55 1995 Path: ashpoly!cascade!brgate!saturno!cam!iweber From: iweber@cam.ac.uk (Ines Weber) Newsgroups: alt.music.synth-pop Subject: Discussion: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Jul05.124355.5429@cam.ac.uk> Date: Wed, 05 Jul 1995 12:43:55 GMT Organization: University of Cambridge Computer Laboratory NNTP-Posting-Host: cam.ac.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Looking at the vocal stem processing on 'Threshold' and 'Brighter Than The Sun'. 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. How did they program the subtle emotional cracks in her voice? Was it a neural weight matrix or manual automation? -- Ines Weber | iweber@cam.ac.uk PGP Key fingerprint: 1CEE 5AEC E4E1 C2A8 "Keep the channels open." From fnovak@delphi.com Thu Jul 06 08:27:55 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!delphi!fnovak From: fnovak@delphi.com (Freya Novak) Newsgroups: alt.music.synth-pop Subject: Re: Discussion: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Jul06.082755.3765@delphi.com> Date: Thu, 06 Jul 1995 08:27:55 GMT References: <1995Jul05.124355.5429@cam.ac.uk> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: Netscape 1.1N Lines: 9 In article <1995Jul05.124355.5429@cam.ac.uk>, iweber@cam.ac.uk (Ines Weber) writes: > Looking at the vocal stem processing on 'Threshold' and 'Brighter Than The Sun'. 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. -- Freya Novak Zyxel U-1496E @ 9600 Telebit bps "Marcus is not one man." From keriksson@delphi.com Fri Jul 07 10:46:55 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!delphi!keriksson From: keriksson@delphi.com (Kirsty Eriksson) Newsgroups: alt.music.synth-pop Subject: Re: Discussion: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Jul07.104655.5762@delphi.com> Date: Fri, 07 Jul 1995 10:46:55 GMT References: <1995Jul05.124355.5429@cam.ac.uk> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1995Jul05.124355.5429@cam.ac.uk>, iweber@cam.ac.uk (Ines Weber) writes: > Looking at the vocal stem processing on 'Threshold' and 'Brighter Than The Sun'. > 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. -- Kirsty Eriksson | keriksson@delphi.com PGP Key fingerprint: 566A F30D 5E27 8668 "Keep the channels open."