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

221–230 of 244 posts

Re: Apple Books digital narration

#221

Post by csande17 »

twobitshifter wrote: post #217
csande17 wrote: post #8

The "Helena" sample contains a pretty good test case of this system's ability to guess where emphasis and pauses go: > 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. (I checked in an online sample of the ebook: there is no punctuation in this sentence.) Unfortunately the AI completely faceplants, placing an enormous pau…

By normal sentence construction it would be all wild places. It’s a good test as you say, the author is having fun with grammar to give you the idea that it’s a subset of places rather than “wild places”, so I would expect it to be written with a link between places and wild, “all places-wild.”

I've seen this construction used in a lot of places (like the name of "All Things Digital", the predecessor to Re/code), but I have never heard of anyone putting a dash between the last two words.

Re: Apple Books digital narration

#222

Post by fsflover »

FinalBriefing wrote: post #220
abraxas wrote: post #69

Earlier quoted context omitted.

Linux is a prime example of a technology that was at first far behind its proprietary counterparts but eventually dominated and nearly extinguished all non-free competitors.

For very specific uses. Linux is not a good options for general computers used by everyday people. That experience is still owned by large corporations.

There are only two cases when you can't use Linux as you daily driver:

    * You must use proprietary software not supporting Linux
    * You must use a device with proprietary drivers not supporting Linux
For me, it works flawlessly, since I avoid both cases.

Re: Apple Books digital narration

#223

Post by lilyball »

potatolicious wrote: post #184
qwerty456127 wrote: post #68

Earlier quoted context omitted.

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.

It's an extremely hard problem that lots of people are working on. The trick is that we have "pretty good" results for TTS as-is, but it has significant shortcomings that are more visible in certain use cases. The operative word is "prosody" - the cadence, rhythm, and pauses that are natural when speaking that are heavily dependent on context and content. Prosody is incredibly important to making natural utterances -…

I wonder how effective it would be to feed the book to some other AI model first that reads the whole thing and figures out the necessary context that it can then go back and feed into the TTS model

Re: Apple Books digital narration

#224

Post by davidzweig »

davidzweig wrote: post #85
qwerty456127 wrote: post #68

Earlier quoted context omitted.

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.

I wanted to make a human-like reading feature for our language-learning software. Training a model isn't too hard using something like https://github.com/coqui-ai/TTS . The weak link was the available free/open datasets. You needed a single speaker with a pleasant voice, 20hrs+ material from varied sources, recorded in a good recording enviroment with a good mic etc. For English, the go-to was LJSpeech, which doesn't…

Added a download link to the readme: https://github.com/dioco-group/jenny-tts-dataset/blob/main/R...

Re: Apple Books digital narration

#225

Post by jasonjmcghee »

thiht wrote: post #127
dmazin wrote: post #37

Woah, the Madison voice is quite clearly Julia Whelan.

Mitchell sounds like Alan Rickman, I felt like I was hearing Snape reading the sentence. I like it

I heard and rather confident it's Ray Porter- it's uncanny. Instantly recognized it (have listened to a number of books narrated by him)

Re: Apple Books digital narration

#226

Post by jasonjmcghee »

mgh2 wrote: post #55

Samples from https://news.ycombinator.com/item?id=34253424 Male: https://books.apple.com/gb/audiobook/pale-moon-rising/id1640... Female: https://books.apple.com/gb/audiobook/shelter-from-the-storm/...

The male sample has many pauses that are distractingly long. Pretty interesting.

Re: Apple Books digital narration

#227

Post by fuzzywalrus »

southp4w wrote: post #202
habosa wrote: post #160

Whoah the Madison voice sounds _exactly_ like Julia Whelan, who is a real audiobook narrator. I have listened to many articles on Audm (narrated news articles) using her voice. I wonder if she had a part in this?

The Mitchell voice also sounds almost exactly like Ray Porter, another real audiobook narrator.

I heard that and it was uncanny how much it sounded like ray porter to me

Re: Apple Books digital narration

#228

Post by lern_too_spel »

jdmoreira wrote: post #53

2019 I did an "Ask HN: When will text-to-speech replace narrators" Most answers did not age well I would say. https://news.ycombinator.com/item?id=20931541

If this is your standard, the answer was 2020 or maybe earlier. https://news.ycombinator.com/item?id=34271329

I don't think publishers will stop hiring professional narrators for the bestsellers (instead of the long tail that has been text-only until recently) for a few years more.

Re: Apple Books digital narration

#229

Post by dmitriid »

rockemsockem wrote: post #213
dmitriid wrote: post #200

Earlier quoted context omitted.

> I don't think that Apple providing a high quality narration tool with their phone which can be used on any ebook would infringe licensing terms. Oh, it definitely would. This produces a derivative work besides anything else. > It's not like they'd be saying "Here is this specific title for you to read/buy/rent", they'd be releasing a tool with the power to do that. That's exactly what they will be doing from the po…

Citation needed? TTS tools exist on all computing platforms these days. The difference with this recent release is just that it sounds better. Apple would not be creating a derivative work, whoever uses it would be. EDIT: It has occurred to me that they may have signed a deal as part of Apple Books that says they won't release tools of this nature. I don't know if that is the case, but that isn't the scenario I'm tal…

TTS tools are required for accessibility etc. However, "convert your ebook into audiobook with this amazing voice over" will run into issues. Amazon tried it: https://www.wsj.com/articles/SB123419309890963869

Re: Apple Books digital narration

#230

Post by Osborne »

dmitriid wrote: post #229
rockemsockem wrote: post #213

Earlier quoted context omitted.

Citation needed? TTS tools exist on all computing platforms these days. The difference with this recent release is just that it sounds better. Apple would not be creating a derivative work, whoever uses it would be. EDIT: It has occurred to me that they may have signed a deal as part of Apple Books that says they won't release tools of this nature. I don't know if that is the case, but that isn't the scenario I'm tal…

TTS tools are required for accessibility etc. However, "convert your ebook into audiobook with this amazing voice over" will run into issues. Amazon tried it: https://www.wsj.com/articles/SB123419309890963869

[dead]
Post reply on HN