๐ Results from Google โข Bing โข DDG โข Marginalia (embeds) โข Maps โข YouTube โข YouTube Music โข Spotify โข Bluesky โข Fediverse โข X
๐ Node [[doesn t this really seem more like speech to phoneme stream]] โถ subnode @enki/doesn t this really seem more like speech to phoneme stream
๐ Doesn-t-this-really-seem-more-like-speech-to-phoneme-stream.md contributed by ๐ค @enki
Doesnโt this really seem more like speech-to-phoneme-stream?
Doesnโt this really seem more like speech-to-phoneme-stream? In languages where spelling diverges strongly from pronounciation (like English & French), we should expect phonetic pronounciation to spelling translation to be at least as complex as speech to phonetic pronounciation, if it used the same models (which it basically never does โ having a NN guess the spelling for an unfamiliar word would be a nightmare!).
By John Ohno on November 6, 2017.
[Canonical link](https://medium.com/@enkiv2/doesnt-this-really-seem-more-like- speech-to-phoneme-stream-21e55f9f70cf)
Exported from Medium on September 18, 2020.

Rendering context...