81–90 of 106 posts
Earlier quoted context omitted.
Probably the Ivona team, no? https://www.ivona.com/
Yeah IVONA. Sounds similar and after acquisition Amazon was looking for engineers to build cloud offering :-).
Earlier quoted context omitted.
I agree that the voice sounds pretty bad, but I think the 'lifelike' part comes from the intelligence part. I.E WA -> Washington, and 75F -> 75 Fahrenheit
Text-to-speech systems have been expanding abbreviations for decades, and it always backfires in some cases. For example, DECtalk would expand "Sun" to "Sunday" regardless of context, with the humorous result that blind people reading tech news in the 90s would often hear about Sunday Microsystems. Edit: Yes, that example was unfair, because it's from the 90s (and actually, DECtalk was largely unchanged since the 80s…
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.
I agree that the voice sounds pretty bad, but I think the 'lifelike' part comes from the intelligence part. I.E WA -> Washington, and 75F -> 75 Fahrenheit
This would drive me nuts, as there's no easy way to predict what sort of transformations it would make. Basically, if it's not near perfect, it's arguably worse than no intelligence at all.
With our PBX stuff, I know it's dumb, so I'm already accustomed to giving it something I know it will read correctly, like "domain dot com".
Earlier quoted context omitted.
I'm not sure about Mandarin, but this is definitely true for Japanese. Near-human Japanese text-to-speech has been around a very long time.
So good they can even sing, and so well that they create entirely virtual pop stars: https://en.wikipedia.org/wiki/Vocaloid
Earlier quoted context omitted.
I'm not sure about Mandarin, but this is definitely true for Japanese. Near-human Japanese text-to-speech has been around a very long time.
True, but Japanese isn't really a tonal language, so it doesn't really evidence the parent's point.
The idea of applying machine learning to add natural emphasis to speech is a good one, but seeing how language machine learning systems like Google Translate fail on very basic contextual cues, I don't have much hope... Especially when their demo samples are on par with systems from a decade ago.
I'll stick to Bruce.
Earlier quoted context omitted.
Sooo cynical. This is way better than most TTS systems, including Google's. The only one I've ever heard that is better is DeepWave, and that suffers from lots of background noise.
Seriously? Compare Polly's English samples (particularly #2) in the original article with the Google's WaveNet samples: Polly 1: https://d0.awsstatic.com/product-marketing/Polly/HelloEnglis... Polly 2: https://d0.awsstatic.com/product-marketing/Polly/HelloEnglis... WaveNet 1: https://storage.googleapis.com/deepmind-media/pixie/us-engli... WaveNet 2: https://storage.googleapis.com/deepmind-media/pixie/us-engli... Ther…
Danish is good, the rest sound not so very lifelike.