Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Apple Books digital narration

authors.apple.com

Post reply on HN
Print view View original

91–100 of 244 posts

Re: Apple Books digital narration

#91

Post by michaelmior »

qwerty456127 wrote: post #68
andy_ppp wrote: post #63

"Once your request is submitted, it takes one to two months to process the book and conduct quality checks." My guess is that these generated voices are far from perfect and someone has to go in and crank the algorithm to get a fair number of passages to not sound strange. Even in the example Helena there is a word at the end of a sentence that sounds like it should be in the middle and has a bit of weirdness to it.…

Why is that we still can't have a perfect or near-perfect text-to-speech given all the astonishing advances in ML taking place? Is TTS an area nobody is really interested in or is it harder than generating beautiful pictures and sophisticated writings? This thing by Apple already sounds way better than the best I heard previously (NextUp Ivona) but it is not an instant-result offline tool yet and that's sad.

> is it harder than generating beautiful pictures and sophisticated writings

I think one differences with pictures and audio is that pictures are two-dimensional and we can't take in the whole image at a time. This makes it easy to overlook flaws without careful inspection. And I find that although there has been some amazing AI-generated art, there are still a lot of rough edges and tweaking required to get really clean images.

As far as writing goes, I suspect that the rules of written language are easier to learn and violations easier to overlook than with generated audio.

Re: Apple Books digital narration

#92

Post by vortegne »

drexlspivey wrote: post #89
33955985 wrote: post #83

So happy to hear Apple putting African American voices front and center for this initiative. Along with Google’s push to make camera lenses / computational photography more accurate for darker skin (and Apple following suit) this feels like a real step forward for inclusion.

Voices have a race?

Often there are clear voice and accent differences. Are you saying there aren't? That would be a very strange statement.

Re: Apple Books digital narration

#93

Post by 33955985 »

drexlspivey wrote: post #89
33955985 wrote: post #83

So happy to hear Apple putting African American voices front and center for this initiative. Along with Google’s push to make camera lenses / computational photography more accurate for darker skin (and Apple following suit) this feels like a real step forward for inclusion.

Voices have a race?

Speakers of African American English have distinct timbre, rhythm, and cadences in their speech. There has long been a lack of these distinct features in TTS. Apple appears to have added a “Black voice” (though to be clear, there are speakers of African American English who are not Black) in 2021:

https://www.consumerreports.org/digital-assistants/apples-ne...

Re: Apple Books digital narration

#94

Post by rickdeckard »

amelius wrote: post #23
rickdeckard wrote: post #18

Earlier quoted context omitted.

I think the cat is already out of the bag, and the death of human narration is imminent. The fight now seems to be whether this transformation happens only in production, or companies like Apple succeed in breaking the total Audiobook price apart into "license" and "production", only buying the license and have the production done on their proprietary servers. Overall, I agree it's inevitable that this results in a s…

> Overall, I agree it's inevitable that this results in a sharp decline in professionally narrated Audiobooks... Or, it will increase demand for audiobooks so much that more humans are needed to create top-notch audio.

I don't know how badly narrated Audiobooks can increase the demand for Audiobooks as a whole.

The only scenario I could imagine is a narration language where Audiobooks didn't exist so far for economic reasons (i.e. low population). Digital narration could bring down production costs to the point of making it economic, basically creating the audiobook market for this language.

But then, if the narration is bad (which it likely is because TTS is worse in minor languages), I don't know how many users could be converted to pay a premium for a better human narration. Also here I think it's more likely that funding will be used to improve the narration engine as a whole instead of going back to hiring humans and renting a studio for each book...

Re: Apple Books digital narration

#95

Post by davidzweig »

enlyth wrote: post #46
bongobingo1 wrote: post #6

Will we see this level of voice synthesis in the public domain? Maybe I am out of touch but I found those examples very impressive - more impressive than the jobs vs rogan demo a few months back. But I am also saddened at a future where all this is locked up in corporate hands - obviously there is money needed and (licensed) data needed too which Apple can get at. Honestly I would rather eschew the ethics of it and j…

This is already easily achievable on consumer hardware, you can train something like Tacotron 2 + WaveRNN on your own computer to achieve similar, if not better results. Check out this repo: https://github.com/coqui-ai/TTS You can also clone someone's voice by finetuning a pretrained LJSpeech model and training a vocoder from scratch, I've had great success with as little as 15 minutes of speech.

Check my other comment in this thread, you might try our dataset. :)

Re: Apple Books digital narration

#96

Post by drcongo »

dbspin wrote: post #52
ClassyJacket wrote: post #21

Earlier quoted context omitted.

I can understand that sentence fine, I don't see anything wrong with it.

Writer here, it's a terrible sentence. "I know Bill carried within him deep currents of spiritual yearning that he found easiest to express through the beauty he saw in all places wild." "Deep currents of spiritual yearning" is both cliched and unspecific / unclear. "That" is superfluous. It's unclear how Bill is expressing the beauty he sees, and the sentence structure implies he's somehow responsible for the natura…

Mind if I ask where you're from? While not really adding anything or altering the meaning (so technically it could be called superfluous), removing it here to my British brain makes the sentence sound lazy and I was definitely taught in school that it should be there. I do also agree that the sentence is terribly written in general though.

Re: Apple Books digital narration

#97

Post by tchalla »

drexlspivey wrote: post #89
33955985 wrote: post #83

So happy to hear Apple putting African American voices front and center for this initiative. Along with Google’s push to make camera lenses / computational photography more accurate for darker skin (and Apple following suit) this feels like a real step forward for inclusion.

Voices have a race?

Are you saying that voices across all races, cultures etc sound the same?

Re: Apple Books digital narration

#98

Post by dahfizz »

qwerty456127 wrote: post #68
andy_ppp wrote: post #63

"Once your request is submitted, it takes one to two months to process the book and conduct quality checks." My guess is that these generated voices are far from perfect and someone has to go in and crank the algorithm to get a fair number of passages to not sound strange. Even in the example Helena there is a word at the end of a sentence that sounds like it should be in the middle and has a bit of weirdness to it.…

Why is that we still can't have a perfect or near-perfect text-to-speech given all the astonishing advances in ML taking place? Is TTS an area nobody is really interested in or is it harder than generating beautiful pictures and sophisticated writings? This thing by Apple already sounds way better than the best I heard previously (NextUp Ivona) but it is not an instant-result offline tool yet and that's sad.

Chat-GPT and StableDiffusion aren't perfect. They still produce weird responses or visual artifacts sometimes. But, it can be easy to move past these idiosyncrasies.

I think the brain is just more sensitive to speech, because inflection and tone is a key part of communication. So even subtle artifacts in the generated voice are really obvious and annoying.

Plus, as another commenter mentioned, books are long. An issue in 1 out of 10,000 words will be enough to break emersion.

Re: Apple Books digital narration

#99

Post by ClassyJacket »

dbspin wrote: post #52
ClassyJacket wrote: post #21

Earlier quoted context omitted.

I can understand that sentence fine, I don't see anything wrong with it.

Writer here, it's a terrible sentence. "I know Bill carried within him deep currents of spiritual yearning that he found easiest to express through the beauty he saw in all places wild." "Deep currents of spiritual yearning" is both cliched and unspecific / unclear. "That" is superfluous. It's unclear how Bill is expressing the beauty he sees, and the sentence structure implies he's somehow responsible for the natura…

Reader here, it's a perfectly fine sentence.
Post reply on HN