View Single Post
Old 11-13-2021, 01:52 PM   #9
Quoth
Still reading
Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.Quoth ought to be getting tired of karma fortunes by now.
 
Quoth's Avatar
 
Posts: 14,303
Karma: 105299897
Join Date: Jun 2017
Location: Ireland
Device: All 4 Kinds: epub eink, Kindle, android eink, NxtPaper
I'm not against Text to Speech, but arguing that for actual novels it's never quite good enough. Certainly Ray Kurzweil's late 1970s scan + OCR + speech synth can be on a smartphone now but those are ghastly for the blind or partially sighted. So scan + OCR + synth is sort of generally available.

Quote:
That high-quality, bleeding-edge TTS will trickle its way down into the OSes themselves, and if we stop back in another 10 years, you'll see all that breathing+mood+other enhancements make their way down to the free version sitting right inside your pocket.
But that's exactly what people were telling me in late 1980s to late 1990s. I don't hear much evidence that it's much better than state of the art then. The Kindle DX and speech pack for the Kindle PW3 are strangely poorer than 2002 Windows XP (built-in free option). I need to figure out Linux and Android Text to Speech for my friend who is now almost blind with Macular Degeneration. Except Covid has meant his ex Nurse wife has pulled up the drawbridge!


Recognition has been slower and gone backwards, needing always on Internet.

The single chip synthesisers for speech were far behind state-of-the-art and rubbish with ordinary text. You needed a crafted file.
Something using someone else's server isn't a solution. Google's AI is also dumb pattern matching using misappropriated information. They have no AI.

Quote:
And those that create ebooks can do their best to take reasonable measures with markup... like marking the proper language so "tacos" (English) + "tacos" (Spanish) can be pronounced correctly (at some near-future date!). That would be infinitely more helpful than manually trying to insert CSS Speech + you can actually benefit from language markup now.
Absolutely!

But Audio books have a problem too.

English isn't spoken the same everwhere in Ireland or UK, nor across the USA. Or SA, Canada, Australia.

Best practice is use the speech patterns and accent the author intends OR to use the local dialect? Which?
Narration is hard work and needs skill. A sample in my sig.

Last edited by Quoth; 11-13-2021 at 02:05 PM.
Quoth is offline   Reply With Quote