From dito@clari.net Tue Dec 12 17:26:50 1995 Path: ashpoly!cascade!brgate!saturno!clari!dito From: dito@clari.net (Diego Ito) Newsgroups: alt.music.synth-pop Subject: Data: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Dec12.172650.7769@clari.net> Date: Tue, 12 Dec 1995 17:26:50 GMT Organization: ClariNet Communications Corp NNTP-Posting-Host: clari.net X-Newsreader: Netscape 1.1N 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. 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? -- Diego Ito Opinions expressed are solely my own and not those of ClariNet Communications Corp. ------------------------------------------------------------ From jsato@u-tokyo.ac.jp Wed Dec 13 06:20:50 1995 Path: ashpoly!cascade!transat!ukc!fennimore!u-tokyo!jsato From: jsato@u-tokyo.ac.jp (Jen Sato) Newsgroups: alt.music.synth-pop Subject: Re: Data: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Dec13.062050.7276@u-tokyo.ac.jp> Date: Wed, 13 Dec 1995 06:20:50 GMT References: <1995Dec12.172650.7769@clari.net> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: NewsWatcher 2.0b24 Lines: 12 In article <1995Dec12.172650.7769@clari.net>, dito@clari.net (Diego Ito) 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. PGP Public key available via finger or upon request. -- === Jen Sato === Dept of Electrical Engineering, University of Tokyo Department of Information Science "5 sigma is a discovery. 7 is a question." From pmartinez@delphi.com Wed Dec 13 12:13:50 1995 Path: ashpoly!cascade!transat!ukc!fennimore!delphi!pmartinez From: pmartinez@delphi.com (Pavel Martínez) Newsgroups: alt.music.synth-pop Subject: Re: Data: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Dec13.121350.8792@delphi.com> Date: Wed, 13 Dec 1995 12:13:50 GMT References: <1995Dec12.172650.7769@clari.net> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1995Dec12.172650.7769@clari.net>, dito@clari.net (Diego Ito) 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. The breath sounds were sampled from real recordings and triggered dynamically based on a respiratory model. -- Pavel Martínez -- Delphi Internet Services "Do not worship the copy." From cmoreau@titech.ac.jp Thu Dec 14 23:38:50 1995 Path: ashpoly!cascade!bigsur!titech!cmoreau From: cmoreau@titech.ac.jp (Camila Moreau) Newsgroups: alt.music.synth-pop Subject: Re: Data: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Dec14.233850.1321@titech.ac.jp> Date: Thu, 14 Dec 1995 23:38:50 GMT References: <1995Dec12.172650.7769@clari.net> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1995Dec12.172650.7769@clari.net>, dito@clari.net (Diego Ito) 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. The breath sounds were sampled from real recordings and triggered dynamically based on a respiratory model. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Camila Moreau Tape trading list upon request. SASE required for international mail. From dsouza@cmu.edu Sat Dec 16 22:34:50 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!cmu!dsouza From: dsouza@cmu.edu (Dong-hyun Souza) Newsgroups: alt.music.synth-pop Subject: Re: Data: The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995Dec16.223450.2335@cmu.edu> Date: Sat, 16 Dec 1995 22:34:50 GMT References: <1995Dec12.172650.7769@clari.net> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 8 In article <1995Dec12.172650.7769@clari.net>, dito@clari.net (Diego Ito) 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. -- Dong-hyun Souza -- Carnegie Mellon University School of CS "The carrier frequency does not drift by accident."