azure - Bing Voice Recognition API Output - Number vs Text -


i'm seeing odd behavior voice recognition api return words , return numbers. example, given audio input of "fifteen dollars , 7 cents" return "fifteen dollars , 7 cents" , others "$15.07". there way ensure 1 or other returned? or, need parse , convert words numbers on own.

thanks!

i looked similar issues, , found bingstt api returns both versions in different fields. tried example example code here: https://github.com/microsoft/cognitive-speech-stt-javascript , got response:

[{ "lexical": "fifteen dollars , 7 cents", "display": "$15.07.", "inversenormalization": null, "maskedinversenormalization": null, "transcript": "$15.07.", "confidence": 0.9474185 }] 

so guess choice yours field use, lexical or display. hope helps.


Comments

Popular posts from this blog

java - Jasper subreport showing only one entry from the JSON data source when embedded in the Title band -

serialization - Convert Any type in scala to Array[Byte] and back -

SonarQube Plugin for Jenkins does not find SonarQube Scanner executable -