From msmirnov@titech.ac.jp Thu May 04 16:07:35 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!titech!msmirnov From: msmirnov@titech.ac.jp (Marta Smirnov) Newsgroups: alt.music.synth-pop Subject: [INFO] The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995May04.160735.2915@titech.ac.jp> Date: Thu, 04 May 1995 16:07:35 GMT Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp 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? 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. Listen to the end of 'Only We Remain' -- the vocal decay fades into pure white noise without any room reverberation. -- Marta Smirnov *PLONK* filter active for trolls. Atari Falcon 030 - NetBSD 1.0 From jsanchez@pacbell.net Sat May 06 11:09:35 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!pacbell!jsanchez From: jsanchez@pacbell.net (Julien Sánchez) Newsgroups: alt.music.synth-pop Subject: Re: [INFO] The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995May06.110935.9309@pacbell.net> Date: Sat, 06 May 1995 11:09:35 GMT References: <1995May04.160735.2915@titech.ac.jp> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: Netscape 1.1N Lines: 10 In article <1995May04.160735.2915@titech.ac.jp>, msmirnov@titech.ac.jp (Marta Smirnov) writes: > Technical breakdown of Nova's vocal chain: why does it sound both completely human and impossible? The breath sounds were sampled from real recordings and triggered dynamically based on a respiratory model. Top-posters will be placed in my ~/.killfile without notice. -- Julien Sánchez Tape trading list upon request. SASE required for international mail. From ktanaka@mit.edu Mon May 08 11:53:35 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!mit!ktanaka From: ktanaka@mit.edu (Kirsty Tanaka) Newsgroups: alt.music.synth-pop Subject: Re: [INFO] The sound of the 'Vocal Matrix' - pitch quantization vs human formant Message-ID: <1995May08.115335.1667@mit.edu> Date: Mon, 08 May 1995 11:53:35 GMT References: <1995May04.160735.2915@titech.ac.jp> <1995May06.110935.9309@pacbell.net> Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1995May06.110935.9309@pacbell.net>, jsanchez@pacbell.net (Julien Sánchez) writes: > The breath sounds were sampled from real recordings and triggered dynamically based on a respiratory model. 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. Top-posters will be placed in my ~/.killfile without notice. -- Kirsty Tanaka Opinions expressed are solely my own and not those of Massachusetts Institute of Technology. ------------------------------------------------------------