31–40 of 46 posts
I first heard the Voder as the first sample on the Klatt Record [1]. Unfortunately, there it's credited solely to Homer Dudley; neither Bell Telephone Laboratory nor women like Helen Harper who operated the machine were mentioned. [1]: http://www.festvox.org/history/klatt.html
Earlier quoted context omitted.
Probably to some degree, but for your two examples I would argue that isn't necessary: For TTS, the "tone" is something you should encode in the input rather than have TTS figure out. I can imagine ebook > LLM > annotated text with speakers, emotions etc > TTS. So the TTS can remain rather dumb. For the self-driving car, it shouldn't know cultural norms and be "more careful" sometimes. It should always know how much…
> For the self-driving car, it shouldn't know cultural norms and be "more careful" sometimes. It should always know how much it sees and what stoping distance it can get with max breaking and its reaction time and adjust accordingly. I used to live next to two schools. In the morning before school the pavement and road outside my house was always full of school kids on bikes. During this time I'd drive with the assum…
But they will probably be way slower than people on streets that are just at the side of sidewalks and full of pedestrians.
[0] https://en.wikipedia.org/wiki/Wolfgang_von_Kempelen%27s_spea...
Earlier quoted context omitted.
> For the self-driving car, it shouldn't know cultural norms and be "more careful" sometimes. It should always know how much it sees and what stoping distance it can get with max breaking and its reaction time and adjust accordingly. I used to live next to two schools. In the morning before school the pavement and road outside my house was always full of school kids on bikes. During this time I'd drive with the assum…
I'd expect self driving cars to have much better sensors and reaction times than we do, and as a consequence not needing to choose between those risks and actually carrying people from one point to another. But they will probably be way slower than people on streets that are just at the side of sidewalks and full of pedestrians.
That is never going to happen.
This is quite off topic, but it reminded me of something I have been thinking about recently – perhaps at the limit all highly capable narrow AI systems must become generally intelligent. I was thinking about the complexity of expression in TTS voice synthesizers recently and it struck me just how difficult a problem that is. To be as expressive as a human the AI model would need to fully "understand" the context of…
Someone was selling a vocoder on eBay, so they made a video of the vocoder describing it's own selling features. https://www.youtube.com/watch?v=5kc-bhOOLxE
Earlier quoted context omitted.
I agree that they got pretty good but there’s still something that they get wrong, their intonation is a kind of passable average. If you want to be able to distinguish them from actual human speech pay close attention to intonation/inflection. They’re still very usable, Im not claiming otherwise
I can't hear much difference in the Studio voice: https://cloud.google.com/text-to-speech/docs/wavenet I'm fairly sure I couldn't tell Studio voices and real people apart in a blind test.
Earlier quoted context omitted.
I made a fork with few more features, it might even work on your phone browser: https://jmiskovic.github.io/voicebox
Thank you for this. I had a lot of fun scaring my cat in bed and it inspired me to become a late middle aged opera savant.
only a woman could operate the machine yet it was built to create a man's voice
Earlier quoted context omitted.
There's also a very nice simulation, where you can play with the very different parts of vocal chords: https://imaginary.github.io/pink-trombone/
I made a fork with few more features, it might even work on your phone browser: https://jmiskovic.github.io/voicebox