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

Amazon Polly – Lifelike Text-To-Speech

aws.amazon.com

Post reply on HN
Print view View original

61–70 of 106 posts

Re: Amazon Polly – Lifelike Text-To-Speech

#61

Post by mwcampbell »

derefr wrote: post #13

One thing I always still notice about these "lifelike" speech models is that they still have random pitch variation that wouldn't be present from a real speaker—sort of a "warbling", similar to audio heavily compressed by some cellular realtime audio codecs. I assume this is due to random variation in the pitches the speakers in the training data used to say given phonemes. Would this, then, imply that speech models…

I don't know about tonal languages. But you're definitely right about the artifacts of concatenative speech synthesis.

It's worth noting that purely synthetic speech, while lacking the superficial lifelike quality, doesn't have these little inconsistencies. Perhaps that's one reason why many blind people, particularly power users, prefer pure synthetic text-to-speech engines, such as ETI-Eloquence (commercial) and eSpeak (open source). These systems especially sound better at high speeds than the newer "lifelike" ones.

Just for fun, here's a side-by-side comparison between a concatenative system, IVONA (acquired by Amazon):

http://mwcampbell.us/tmp/derefr_comment_ivona.mp3

And a purely synthetic system, Eloquence:

http://mwcampbell.us/tmp/derefr_comment_eloquence.mp3

The latter is the text-to-speech engine I use every day, and that clip was synthesized at the speaking rate I normally use.

Edit: It appears the word I was looking for when I said "purely synthetic" is "parametric".

Re: Amazon Polly – Lifelike Text-To-Speech

#62

Post by mwcampbell »

revelation wrote: post #55
splike wrote: post #41

Earlier quoted context omitted.

Hence the need for intelligence

Which it fails miserably at. They probably picked the one example that worked. Someone linked another example here: https://soundcloud.com/zack-bloom/amazons-new-text-to-speech... And it pronounces 1970s (the decade) as one-thousand-nine-hundred-seven-ths.

One blind guy I know opined in the late 90s that it's better to let the brain do the interpreting. But I understand that expansion of abbreviations makes TTS more attractive for mainstream applications.

Re: Amazon Polly – Lifelike Text-To-Speech

#64

Post by derefr »

mwcampbell wrote: post #61
derefr wrote: post #13

One thing I always still notice about these "lifelike" speech models is that they still have random pitch variation that wouldn't be present from a real speaker—sort of a "warbling", similar to audio heavily compressed by some cellular realtime audio codecs. I assume this is due to random variation in the pitches the speakers in the training data used to say given phonemes. Would this, then, imply that speech models…

I don't know about tonal languages. But you're definitely right about the artifacts of concatenative speech synthesis. It's worth noting that purely synthetic speech, while lacking the superficial lifelike quality, doesn't have these little inconsistencies. Perhaps that's one reason why many blind people, particularly power users, prefer pure synthetic text-to-speech engines, such as ETI-Eloquence (commercial) and eS…

How do you feel about the WaveNet results, by comparison?

• https://storage.googleapis.com/deepmind-media/pixie/us-engli...

• https://storage.googleapis.com/deepmind-media/pixie/us-engli...

Re: Amazon Polly – Lifelike Text-To-Speech

#65

Post by ausjke »

I assume now you can use LEX + Polly to make your own Echo.

Google, IBM and Microsoft all have invested way more in AI already and are actually way ahead of Amazon technically. However Amazon now becomes the first one that makes these technologies really approachable for ordinary developers. Way to go Amazon!

Re: Amazon Polly – Lifelike Text-To-Speech

#66

Post by bobajeff »

TazeTSchnitzel wrote: post #16

Could we drop “Lifelike” from the title? It's marketing puffery (and untrue, it sounded very robotic to me to the point I was convinced I'd heard the wrong audio file). The actual story is that it's Amazon's text-to-speech-as-a-service offering, not that it's particularly innovative in terms of sounding good.

So I take it that this isn't Amazon's version of Adobe's VoCo or DeepMind's WaveNet.

Re: Amazon Polly – Lifelike Text-To-Speech

#67

Post by mtgx »

mgamache wrote: post #60

There's a lot of negative reaction to Polly. Besides WaveNet (which is not available as an API-- and really slow), what are better alternatives? Or is the reaction just to Amazon's marketing speak using "lifelike" and "deep learning"? I find most of the voices to be okay, but Joanna is pretty good and better then anything I've heard besides WaveNet. Also, with Amazon's FPGA investment how long before it implements Wa…

Why would Google use FPGAs over its own (faster) TPUs? Chances are Google either doesn't have enough TPUs (it may be waiting on the next generation to go massive scale with them), or Wavenet is still too computationally intensive even for TPUs.

Re: Amazon Polly – Lifelike Text-To-Speech

#68

Post by mwcampbell »

derefr wrote: post #64
mwcampbell wrote: post #61

Earlier quoted context omitted.

I don't know about tonal languages. But you're definitely right about the artifacts of concatenative speech synthesis. It's worth noting that purely synthetic speech, while lacking the superficial lifelike quality, doesn't have these little inconsistencies. Perhaps that's one reason why many blind people, particularly power users, prefer pure synthetic text-to-speech engines, such as ETI-Eloquence (commercial) and eS…

How do you feel about the WaveNet results, by comparison? • https://storage.googleapis.com/deepmind-media/pixie/us-engli... • https://storage.googleapis.com/deepmind-media/pixie/us-engli...

Those phrases sound very natural indeed. But are they carefully selected demo phrases, for which the system might have been tuned? That's always a danger with marketing demos. So I have two questions:

1. How does that engine sound when reading arbitrary text at high speed?

2. Can I run it on my own computer, so I can have low latency in my screen reader? (That, of course, is a problem with Amazon Polly as well.)

Re: Amazon Polly – Lifelike Text-To-Speech

#69

Post by hosh »

revelation wrote: post #55
splike wrote: post #41

Earlier quoted context omitted.

Hence the need for intelligence

Which it fails miserably at. They probably picked the one example that worked. Someone linked another example here: https://soundcloud.com/zack-bloom/amazons-new-text-to-speech... And it pronounces 1970s (the decade) as one-thousand-nine-hundred-seven-ths.

I was looking around for samples, and this is the only sample I have heard so far. I think that sounds pretty good. The emotional tone is off, but it is a lot better than say, Siri (which I understand was designed to sound robotic to highlight the tech). But I'm also the guy who has had my MBP announce the hour and it has freaked out coworkers.

I don't know if this is crossing into uncanny valley territory. I think some of this is not being used to it.

Google Map's driving voice sounds subtly better than that voice sample. I'm looking forward to seeing if a similar service is coming for GCP.

Post reply on HN