[HN Gopher] "All your base are belong to us" intro to my 2004 MI...
___________________________________________________________________
"All your base are belong to us" intro to my 2004 MIT Spam
Conference talk
Author : jgrahamc
Score : 39 points
Date : 2024-12-08 17:25 UTC (5 days ago)
(HTM) web link (blog.jgc.org)
(TXT) w3m dump (blog.jgc.org)
| jgrahamc wrote:
| I made one big mistake with that introduction when it was
| recorded on to the video tape for playback at the conference: I
| didn't realize how much people were going to laugh at the end and
| went straight into my presentation. I got to hear the laughter
| because the conference was live streamed using RealPlayer.
| colechristensen wrote:
| I would like to see more modern text-to-speech that sounds
| good, but also inhuman. On one hand very easy to understand but
| on the other obviously constructed and not something a living
| person could generate. Like the scifi where robots always look
| like robots and it's illegal/immoral/taboo to have a robot
| that's indistinguishable from a person.
|
| Maybe just an ordinary human sounding TTS that gets put through
| a mild vocoder of some kind.
| bitwize wrote:
| It sounds like a guy recorded his own voice and ran it
| through an LPC.
| moffkalast wrote:
| That's a real problem with the vast majority of current TTS.
| Terrible in things like consistent intonation, proper
| pronunciation, believable pauses, while sounding human all
| the same and the result is super uncanny valley.
|
| The gaming and movie industry understands this very well,
| they use human voice actors that can nail all of that and
| then make it sound more metallic or compressed or whatnot.
| Otherwise it does not fit.
| sandworm101 wrote:
| And on the high end, making everyone sound like a
| professional public speaker. The machine sees mistakes as
| errors when in fact every non-hollywood speech contains
| multiple mistakes.
| Uehreka wrote:
| This is why it pisses me off when a techy person makes a
| YouTube video and just uses TTS instead of recording a
| voiceover. I know some people don't have a good recording
| situation, but I get the sense that a lot of people just do
| it because they either think people can't tell or they
| think it's a clever hack or "the way of the future" or
| something.
|
| It isn't. Instead I find myself watching videos and getting
| a weird creepy feeling when I suddenly hear the voiceover
| mispronounce a word or put an emphasis in the wrong place.
| Part of it is the uncanny valley for sure, but the more
| pernicious thing is this: once I realize that the voice is
| AI-generated, I start to worry that the script might be
| too. Now I'm trying to figure out "is this guy just an
| amateur writer taking a while to get to his point, or is
| this an LLM-authored script that is never going to go
| beyond surface-level statements about the topic."
| Cpoll wrote:
| I think this undersells the difficulty of recording a
| good voice-over, both technically and performatively.
| martylamb wrote:
| I was there and remember it well. The whole thing was
| completely unexpected and people lost it. Well done. :)
| metadat wrote:
| This is cool, how did you make the voice? It's perfect for the
| application :)
| jgrahamc wrote:
| I believe I used the Mac's 'say' command with one of the
| default voices (perhaps with some parameter tweaks).
| jmarcher wrote:
| ``` say 'something' -v '?' | grep en_US Albert en_US # Hello!
| My name is Albert. Bad News en_US # Hello! My name is Bad
| News. Bahh en_US # Hello! My name is Bahh. Bells en_US #
| Hello! My name is Bells. Boing en_US # Hello! My name is
| Boing. Bubbles en_US # Hello! My name is Bubbles. Cellos
| en_US # Hello! My name is Cellos. Wobble en_US # Hello! My
| name is Wobble. Eddy (English (US)) en_US # Hello! My name is
| Eddy. Flo (English (US)) en_US # Hello! My name is Flo. Fred
| en_US # Hello! My name is Fred. Good News en_US # Hello! My
| name is Good News. Grandma (English (US)) en_US # Hello! My
| name is Grandma. Grandpa (English (US)) en_US # Hello! My
| name is Grandpa. Jester en_US # Hello! My name is Jester.
| Junior en_US # Hello! My name is Junior. Kathy en_US # Hello!
| My name is Kathy. Organ en_US # Hello! My name is Organ.
| Superstar en_US # Hello! My name is Superstar. Ralph en_US #
| Hello! My name is Ralph. Reed (English (US)) en_US # Hello!
| My name is Reed. Rocko (English (US)) en_US # Hello! My name
| is Rocko. Samantha en_US # Hello! My name is Samantha. Sandy
| (English (US)) en_US # Hello! My name is Sandy. Shelley
| (English (US)) en_US # Hello! My name is Shelley. Trinoids
| en_US # Hello! My name is Trinoids. Whisper en_US # Hello! My
| name is Whisper. ```
| bombcar wrote:
| The main thing I realize is just how amazing we thought those
| machine voices were and how good and realistic, and how bad they
| sound now compared to what we have.
| hvs wrote:
| I don't think we ever thought they were particularly good or
| realistic, just the best we could do with the limitations of
| the time.
| havblue wrote:
| As a kid I thought the announcer voice for Blades of Steel was
| excellent at the time. Despite it being distorted it gave the
| feeling that you were watching an actual hockey game. Of
| course, most of the games I played then didn't have much in the
| way of human voice.
| GiorgioG wrote:
| https://www.youtube.com/watch?v=7XJlTaBnlrI
| asdfman123 wrote:
| Elegant memes from a more civilized age
| averageRoyalty wrote:
| For great justice.
___________________________________________________________________
(page generated 2024-12-13 23:00 UTC)