Closed peterolson closed 8 months ago
For English, only en-US
supports IPA
phones. Currently, it's by design.
We can support exposing the IPA
phone with some effort on en-GB
. Can you estimate the usage of pronunciation services to help use to priority the work? Thanks!
Is it documented anywhere on that only en-US
supports IPA
phones? If not, that limitation should definitely be in the documentation.
Can you estimate the usage of pronunciation services to help use to priority the work?
I'm not using it at all right now because it doesn't work. Once it starts working properly I plan on using it heavily.
To keep our open issues list up to date, this item will be closed since it's been inactive and needs more information to proceed. Please file a new issue (and feel free to reference this one) if there's new information we can follow up on. Thank you!
@jpalvarezl I don't understand what you mean by "needs more information to proceed". What other information do you need?
That is a template message we use in our team when closing an issue due to inactivity.
It seemed to me that @wangkenpu may have needed more information from you to proceed. Is that correct, @wangkenpu ? How can we unblock to continue work on this issue?
Please @peterolson , feel free to re-open this if necessary.
I'm using the
microsoft-cognitiveservices-speech-sdk
in Node.js.I'm trying to get the pronunciation of words in US English and UK English. To do that, I first run text-to-speech. Unfortunately, TTS doesn't return phoneme information directly, so I feed the result of TTS into speech recognition, and then run pronunciation assessment on that.
For the
en-US
locale, I get the following correct result:For
en-GB
, there are no IPA phonemes returned at all.These are the results I would expect based on the information here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-ssml-phonetic-sets#en-gben-ieen-au
Here's my code: