Live data from Hacker News

Pink Trombone

dood.al

31–40 of 80 posts

Re: Pink Trombone

#32
post #30

Earlier quoted context omitted.

No need. This thing is already a voice synthesizer. This is how modern synthesizers work, more or less: by generating a sine wave and then modifying it in the same way as the vocal tract does.

I meant "text to speech engine" then I guess.

Yeah, I know what you meant. You use a tool like the CMU pronunciation dictionary[1] to turn words into phonemes, and then you use a model similar to the pink trombone to turn the phoneme string into sound, including the transitions between different phones (which, it turns out, actually matter more than the phones themselves for making it understandable). This is how TTS works.

1 http://www.speech.cs.cmu.edu/cgi-bin/cmudict

Re: Pink Trombone

#34
post #14

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.

Referring to something from 1996 as an app and a modern web app as a page is a bizarre conflation of terminology.

Re: Pink Trombone

#36
post #6

This is amazing. I can get it to make almost any speech sound, but one I can't get is [s], because the model lacks teeth!

disable "always voice", and click a bit below hard palate, slightly to the right towards the lip (below the at in pal at e), so there will only be a small gap for the air to go through

You're right. It sounds to me like [s] with lip rounding, where the teeth don't contribute as much acoustically, but it does indeed sound like an [s].

Re: Pink Trombone

#37
post #14

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.

Referring to something from 1996 as an app and a modern web app as a page is a bizarre conflation of terminology.

I'm guessing the thing from '96 was a Java applet, so indeed an app.

Re: Pink Trombone

#38
post #13
post #11

Pondering what makes this sound "male".

You can make it sound female by dragging the voicebox control to the right and down. It requires both higher pitch, and less power in the odd harmonics.

I agree it gets closer, but as is with much of speech synthesis, it still to me ends up sounding like "a male talking in a high-pitched voice" and not "a female".

In addition, this would imply that only males can talk in a low register, which is patently false. Low register female voices are fairly common.

Re: Pink Trombone

#39
post #30

Earlier quoted context omitted.

I meant "text to speech engine" then I guess.

Yeah, I know what you meant. You use a tool like the CMU pronunciation dictionary[1] to turn words into phonemes, and then you use a model similar to the pink trombone to turn the phoneme string into sound, including the transitions between different phones (which, it turns out, actually matter more than the phones themselves for making it understandable). This is how TTS works. 1 http://www.speech.cs.cmu.edu/cgi-bin…

Great man-splaining of how synthesis works.

Pink Trombone has no phoneme mapping, you'd have to code all that by hand, and that's exactly what my original question was.

Re: Pink Trombone

#40
post #14

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.

Referring to something from 1996 as an app and a modern web app as a page is a bizarre conflation of terminology.

We had applications back in the 1990s. I know, it seems unfathomable now but applications preceded the App Store.
Post reply on HN