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.

Pink Trombone

575 pointsby errozeroover 6 years ago

23 comments

modelessover 6 years ago
In a similar vein: <a href="http:&#x2F;&#x2F;www.adultswim.com&#x2F;etcetera&#x2F;choir&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.adultswim.com&#x2F;etcetera&#x2F;choir&#x2F;</a><p>The most interesting thing about this one is the chord progressions it generates.
评论 #18913436 未加载
评论 #18916045 未加载
评论 #18915906 未加载
评论 #18918661 未加载
评论 #18913559 未加载
评论 #18913373 未加载
sgentleover 6 years ago
A little while back I used this combined with a physics simulator to make a toy where you throw polygons in the air and they scream: <a href="https:&#x2F;&#x2F;ohgodwhathaveidone.stackblitz.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;ohgodwhathaveidone.stackblitz.io&#x2F;</a><p>Code&#x27;s here if anyone wants to play: <a href="https:&#x2F;&#x2F;stackblitz.com&#x2F;edit&#x2F;ohgodwhathaveidone" rel="nofollow">https:&#x2F;&#x2F;stackblitz.com&#x2F;edit&#x2F;ohgodwhathaveidone</a> – I did a fairly medium job of abstracting the synthesis engine away from the UI, but it might be a decent starting point if you&#x27;re looking to make other Trombone-based web silliness.
lqetover 6 years ago
This reminds me of the Sprechmaschine [1] (&quot;speaking machine&quot;) built at the end of the 18th century by Wolfgang von Kempelen (the guy who build the original mechanical turk [2]). Here is a YouTube video showing it in action (for example, the machine says &quot;Mama&quot; around 1:14): <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=k_YUB_S6Gpo" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=k_YUB_S6Gpo</a><p>[1] <a href="https:&#x2F;&#x2F;de.wikipedia.org&#x2F;wiki&#x2F;Wolfgang_von_Kempelen#Die_Sprechmaschine" rel="nofollow">https:&#x2F;&#x2F;de.wikipedia.org&#x2F;wiki&#x2F;Wolfgang_von_Kempelen#Die_Spre...</a><p>[2] <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Turk" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Turk</a>
评论 #18916819 未加载
spepsover 6 years ago
Literate C version: <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>Literate depot: <a href="https:&#x2F;&#x2F;github.com&#x2F;PaulBatchelor&#x2F;voc" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;PaulBatchelor&#x2F;voc</a><p>Actually compiled source is there: <a href="https:&#x2F;&#x2F;github.com&#x2F;PaulBatchelor&#x2F;Soundpipe&#x2F;blob&#x2F;master&#x2F;modules&#x2F;voc.c" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;PaulBatchelor&#x2F;Soundpipe&#x2F;blob&#x2F;master&#x2F;modul...</a>
goodmachineover 6 years ago
Lest we forget that speech synthesis is not just for grotesque but amusing semi-real vocal synths like this, here&#x27;s a BBC Radio 4 history of speech synthesis as an assistive technology - Klatt&#x27;s Last Tapes, by Stephen Hawking&#x27;s daughter, Lucy:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=097K1uMIPyQ" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=097K1uMIPyQ</a>
jedbergover 6 years ago
Man this brings back memories. We used this program for my linguistics homework in college. In 1996. Although I think it was an app then not a web page.
评论 #18915029 未加载
emmelaichover 6 years ago
This would be useful to demonstrate the difference between p&#x2F;f and l&#x2F;r for those brought up without those distinctions.<p>I&#x27;d also (as an English speaker) like to see&#x2F;hear Dutch g and Xhosan clicks.
评论 #18917701 未加载
smlacyover 6 years ago
Would it be possible to use Reinforcement Learning + Speech Recognition to turn this thing into a real voice synthesizer?
评论 #18913852 未加载
评论 #18913192 未加载
zackmorrisover 6 years ago
Reminds me of Xiph&#x27;s Speex&#x2F;CELP model of speech as a mix of noise and frequency to achieve high compression, requiring as little as 2.15 kilobits (275 bytes) per second. It sounds perceptibly similar to the original recording, even though the difference between the input and output sampled data may be high:<p><a href="https:&#x2F;&#x2F;www.speex.org&#x2F;docs&#x2F;manual&#x2F;speex-manual&#x2F;node9.html" rel="nofollow">https:&#x2F;&#x2F;www.speex.org&#x2F;docs&#x2F;manual&#x2F;speex-manual&#x2F;node9.html</a><p>Bitrate comparison:<p><a href="https:&#x2F;&#x2F;www.speex.org&#x2F;comparison&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.speex.org&#x2F;comparison&#x2F;</a><p>Samples:<p><a href="https:&#x2F;&#x2F;www.speex.org&#x2F;samples&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.speex.org&#x2F;samples&#x2F;</a><p>Maybe higher compression can be achieved with better prediction, aka machine learning.
colandermanover 6 years ago
I&#x27;ve actually been looking for the <i>opposite</i> of this (i.e. sound in, mouth representation out) for a while. Does anyone know of such a thing?
评论 #18916737 未加载
t0mbstoneover 6 years ago
Wow! I was able to successfully recreate all sorts of letters and sounds just by imagining how my own mouth works, and then manipulating the different components on the pink trombone in the same way. I&#x27;m impressed!
smlacyover 6 years ago
Pondering what makes this sound &quot;male&quot;.
评论 #18917580 未加载
评论 #18913346 未加载
评论 #18918714 未加载
评论 #18913253 未加载
triclops200over 6 years ago
Sudden sound warning.
评论 #18919914 未加载
willchangover 6 years ago
This is amazing. I can get it to make almost any speech sound, but one I can&#x27;t get is [s], because the model lacks teeth!
评论 #18913053 未加载
评论 #18918241 未加载
评论 #18916200 未加载
BFattsover 6 years ago
I feel like I am simulating orgasmic responses!
jarmitageover 6 years ago
This was also ported to C++ inside a modular synth:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=PDn7ygnJUfI" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=PDn7ygnJUfI</a><p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=3jcqKnIa8T4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=3jcqKnIa8T4</a><p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=bo5ZEgBEapk" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=bo5ZEgBEapk</a><p><a href="https:&#x2F;&#x2F;github.com&#x2F;giuliomoro&#x2F;pink-trombone" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;giuliomoro&#x2F;pink-trombone</a>
sonnyblarneyover 6 years ago
What someone needs to do is put sensors in people&#x27;s mouths, record them saying known phrases, then stick the sensor data+phrases into some AI and see if we can&#x27;t get that Trombone talkin&#x27;!
glitcherover 6 years ago
Previous post in Apr 2017: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14135658" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14135658</a>
philsnowover 6 years ago
The shape of the tongue control reminds me a lot of the rhombus in <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;International_Phonetic_Alphabet#Vowels" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;International_Phonetic_Alphabe...</a><p>... which is because the latter was patterned after the shape of the mouth.
ben-hudsonover 6 years ago
I feel embarrassed playing with this
评论 #18917407 未加载
mmjaaover 6 years ago
Thats nice and everything but until I have a hardware version where I can just switch a button on and do this and that, I&#x27;m not really going to be truly satisfied. Please hardware&#x27;ify.
joshuover 6 years ago
how do i use this to answer the phone?
Digit-Alover 6 years ago
Is the author aware of the other meaning of &quot;pink trombone&quot;?[1]<p>[1] <a href="https:&#x2F;&#x2F;www.urbandictionary.com&#x2F;define.php?term=pink%20trombone" rel="nofollow">https:&#x2F;&#x2F;www.urbandictionary.com&#x2F;define.php?term=pink%20tromb...</a>
评论 #18914592 未加载
评论 #18913724 未加载
评论 #18918269 未加载
评论 #18913885 未加载
评论 #18913749 未加载