TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

An IBM computer learned to sing in 1961

81 pointsby isomorphabout 2 years ago

18 comments

gwbas1cabout 2 years ago
One of the things I get a kick out of in the clip of HAL singing Daisy is just how much the physical modules being removed <i>look</i> like hard drives being pulled out of a NAS. I could easily think of a much larger version of my Synchrony NAS looking just like that.<p>BUT: When I first watched 2001 sometime in the early 1990s, I had only seen a 5.25&quot; hard drive, and not on a slider &#x2F; rails. I thought the inside of HAL was just tacky scifi from the 1960s.<p>It&#x27;s only later as I&#x27;ve seen the predictions come true that I&#x27;ve realized just how forward-looking 2001 is. Like the scene with watching news reports on the tablets at breakfast. It wasn&#x27;t until I watched a video, on my phone, in the late 2010s, that I realized that prediction in the move was 100% spot-on.<p>BTW, the 4k Ultra-HD bluray of 2001 is awesome.
评论 #35919927 未加载
评论 #35922915 未加载
评论 #35924849 未加载
blincolnabout 2 years ago
Are there any detailed descriptions available of how the music and voice were synthesized?<p>Based on the recording, the information I could find, and imagining how I&#x27;d try to do the same thing using the technology of the era, I assume the melody is based on single-cycle samples of a piano and Max Matthews playing the violin. The vocals sound like formant synthesis like the Votrax SC-01 or TI LPC series, although of course those chips didn&#x27;t exist until 15+ years after the work at IBM. But I&#x27;m very curious about the details. Did the team develop a general-purpose sequencer for the melody and&#x2F;or speech, or were all of the notes, slides, etc. hardcoded? Did the computer actually output all 3+ parts together, or were they separate elements mixed after the fact? I assume the output was not realtime, but it would be a neat surprise if they achieved that in the 60s. Was it all handled digitally in the computer, or was the computer controlling some add-on hardware, maybe with analogue filters? Etc.
评论 #35917840 未加载
dbarlettabout 2 years ago
I inherited a Southern Bell promotional card&#x2F;record that includes <i>Daisy Bell</i>:<p><a href="https:&#x2F;&#x2F;dbarlett-wordpress.s3.us-east-1.amazonaws.com&#x2F;wp-content&#x2F;uploads&#x2F;2023&#x2F;05&#x2F;Computer_Speaks_1-1024x762.jpg" rel="nofollow">https:&#x2F;&#x2F;dbarlett-wordpress.s3.us-east-1.amazonaws.com&#x2F;wp-con...</a><p><a href="https:&#x2F;&#x2F;dbarlett-wordpress.s3.us-east-1.amazonaws.com&#x2F;wp-content&#x2F;uploads&#x2F;2023&#x2F;05&#x2F;Computer_Speaks_2-1024x762.jpg" rel="nofollow">https:&#x2F;&#x2F;dbarlett-wordpress.s3.us-east-1.amazonaws.com&#x2F;wp-con...</a>
tomcamabout 2 years ago
It didn’t “learn“ how to sing, of course. The voice was built bottom up, phoneme by phoneme, pitch by pitch.
rzzztabout 2 years ago
The crowdsourced version of the song is quite chilling: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;Gz4OTFeE5JY" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;Gz4OTFeE5JY</a>
评论 #35916854 未加载
krunckabout 2 years ago
Nice. But why did the video creator feel the need to put in the fake film projector effects? The urge people have to add &quot;oldness&quot; where it is already present - though not in the form they imagine - is interesting by itself.
jlaroccoabout 2 years ago
A few years ago I picked up &quot;Music By Computer&quot;[1] from a used book store, and it&#x27;s fascinating.<p>Published in 1969, it&#x27;s a collection of papers from the 60s about music and sound processing on the machines back then, and it goes into a lot more detail, if anybody is interested and can find a copy. It even came with recorded music on 5 paper thin flexi-discs that I&#x27;ve never been able to play.<p><a href="https:&#x2F;&#x2F;www.amazon.com&#x2F;Music-Computers-Heinz-von-Foerster&#x2F;dp&#x2F;0471910309" rel="nofollow">https:&#x2F;&#x2F;www.amazon.com&#x2F;Music-Computers-Heinz-von-Foerster&#x2F;dp...</a><p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Flexi_disc" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Flexi_disc</a>
cf100clunkabout 2 years ago
Library of Congress essay by Cary O&#x27;Dell on &quot;Daisy Bell (Bicycle Built For Two)&quot; from song origins to Bell Labs recording:<p><a href="https:&#x2F;&#x2F;www.loc.gov&#x2F;static&#x2F;programs&#x2F;national-recording-preservation-board&#x2F;documents&#x2F;DaisyBell.pdf" rel="nofollow">https:&#x2F;&#x2F;www.loc.gov&#x2F;static&#x2F;programs&#x2F;national-recording-prese...</a>
bregmaabout 2 years ago
We had a floppy vinyl 45 of that when I was a kid in the 1960s (my mother was a high school science teacher and we often had cool stuff like that around the house).
cf100clunkabout 2 years ago
A recording of it was included in some electronics hobbyist magazines of that time on shiny black flexible vinyl for playing on a phonograph at 45rpm. I seem to recall that Bell Labs was credited on the label but IBM was not.<p>EDIT: dbarlett just posted an image of the recording&#x27;s label elsewhere in this thread
zebprojabout 2 years ago
The neat thing about this particular singing synthesizer is that it used a surprisingly sophisticated (especially for the 60s) physical model of the human vocal tract [1], and was perhaps the first use of physical modeling sound synthesis. Vowel shapes were obtained through physical measurements of an actual vocal tract via x-rays. In this case, they were Russian vowels, but were close enough for English.<p>While this particular kind of speech synthesis[2] isn&#x27;t really used anymore, it&#x27;s still fun to play around with. Pink Trombone [3] is a good example of a fun toy that uses a waveguide physical model, similar to the Kelly-Lochbaum model above. I&#x27;ve adapted some of the DSP in Pink Trombone a few times[4][5][6], and used it in some music[7] and projects[8]of mine.<p>For more in-depth information about specifically doing singing synthesis (as opposed to general speech synthesis) using waveguide physical models, Perry Cook&#x27;s Dissertation [9] is still considered to be a seminal work. In the early 2000s, there were a handful of follow-ups to physically-based singing synthesis being done at CCRMA. Hui-Ling Lu&#x27;s dissertation [10] on glottal source modelling for singing purposes comes to mind.<p>1: <a href="https:&#x2F;&#x2F;ccrma.stanford.edu&#x2F;~jos&#x2F;pasp&#x2F;Singing_Kelly_Lochbaum_Vocal_Tract.html" rel="nofollow">https:&#x2F;&#x2F;ccrma.stanford.edu&#x2F;~jos&#x2F;pasp&#x2F;Singing_Kelly_Lochbaum_...</a><p>2: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Articulatory_synthesis" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Articulatory_synthesis</a><p>3: <a href="https:&#x2F;&#x2F;dood.al&#x2F;pinktrombone&#x2F;" rel="nofollow">https:&#x2F;&#x2F;dood.al&#x2F;pinktrombone&#x2F;</a><p>4: <a href="https:&#x2F;&#x2F;pbat.ch&#x2F;proj&#x2F;voc&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pbat.ch&#x2F;proj&#x2F;voc&#x2F;</a><p>5: <a href="https:&#x2F;&#x2F;pbat.ch&#x2F;sndkit&#x2F;tract&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pbat.ch&#x2F;sndkit&#x2F;tract&#x2F;</a><p>6: <a href="https:&#x2F;&#x2F;pbat.ch&#x2F;sndkit&#x2F;glottis&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pbat.ch&#x2F;sndkit&#x2F;glottis&#x2F;</a><p>7: <a href="https:&#x2F;&#x2F;soundcloud.com&#x2F;patchlore&#x2F;sets&#x2F;looptober-2021" rel="nofollow">https:&#x2F;&#x2F;soundcloud.com&#x2F;patchlore&#x2F;sets&#x2F;looptober-2021</a><p>8: <a href="https:&#x2F;&#x2F;pbat.ch&#x2F;wiki&#x2F;vocshape&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pbat.ch&#x2F;wiki&#x2F;vocshape&#x2F;</a><p>9: <a href="https:&#x2F;&#x2F;www.cs.princeton.edu&#x2F;~prc&#x2F;SingingSynth.html" rel="nofollow">https:&#x2F;&#x2F;www.cs.princeton.edu&#x2F;~prc&#x2F;SingingSynth.html</a><p>10: <a href="https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20080725195347&#x2F;http:&#x2F;&#x2F;ccrma-www.stanford.edu&#x2F;~vickylu&#x2F;thesis&#x2F;index.html" rel="nofollow">https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20080725195347&#x2F;http:&#x2F;&#x2F;ccrma-www....</a>
评论 #35921082 未加载
评论 #35919900 未加载
xaedesabout 2 years ago
Eery, this song performance reminded me of the ending song of Portal.
sibeliussabout 2 years ago
Does anyone have any information &#x2F; background on the programming behind this project?<p>It seems incredible for so long ago and I can&#x27;t quite conceive of how they were able to do it.
评论 #35924148 未加载
silveiraabout 2 years ago
Reminds me of Kapp&#x27;n in Animal Crossing.
zabzonkabout 2 years ago
the thing i most like in the film 2010 is that HAL gets put back together and saves Helen Mirren&#x27;s human crew.
jagged-chiselabout 2 years ago
“Learned” or “was instructed”?
vidanayabout 2 years ago
Daisy, Daisy, Daisy.
SCAQTonyabout 2 years ago
HAL did it better 40-years later in 2001: <a href="https:&#x2F;&#x2F;www.google.com&#x2F;search?q=HAL+singing+D+a+bicycle+built+for+two+2001&amp;oq=HAL+singing+D+a+bicycle+built+for+two+2001&amp;aqs=chrome..69i57j33i160l2.13467j1j4&amp;sourceid=chrome&amp;ie=UTF-8#fpstate=ive&amp;vld=cid:66e079f5,vid:E7WQ1tdxSqI" rel="nofollow">https:&#x2F;&#x2F;www.google.com&#x2F;search?q=HAL+singing+D+a+bicycle+buil...</a>
评论 #35917252 未加载