search

twerkmeister / iLID

automatic spoken language identification
MIT License
90 stars 24 forks source link

Is there a reported accuracy and latency to predict a wav file #4

Open YunzhaoLu opened 6 years ago

YunzhaoLu commented 6 years ago

would someone tell me the accuracy of iLID and latency to decode a wav file of 10s? I want to have the reference. Regards, Luke

hotzenklotz commented 6 years ago

@YunzhaoLu Hi. This is an old university study we did quite some time ago. There is no "latency" per se since all WAV files were converted to spectrogram images before prediction. Conversion was done using the Sox CLI tool, so you could measure yourself. For numbers on accuracy, precision etc. please refer to our technical report: https://github.com/twerkmeister/iLID/blob/master/Deep%20Audio%20Paper%20Thomas%20Werkmeister%2C%20Tom%20Herold.pdf