Home › Forums › OpenEars › Increasing speech recognition accuracy using a custom languagemodel? › Reply To: Increasing speech recognition accuracy using a custom languagemodel?
Thank you for your fast response, Halle. I appreciate it!
The reason I was trying to modify the languagemodel in my original post is that I thought I was having problems with number recognition, specifically “fives” and “nines”. After more testing, I narrowed down the problem. I am having problems recognizing words at the end of utterances. For example, when I try to recognize the phrase “three five five”, Openears often only recognizes “three five”. Why is that? It is almost like the last word gets cut off from being recognized.
Settings:
setVadThreshold:3.0
setSecondsOfSilenceToDetect:0.3