Hi all, I am trying to build a language learning app in which users can pronounce foreign words and automatically get feedback on how they did. It's a client-server setup. The server is a speech recognizer which I've built for this purpose. The client is an android activity which main purpose is to send the user's speech via a socket to the server. The program is already able to send the audio data to the server using the AudioRecord class. I record the data with a sample rate of 16kHz, 16-bit PCM, mono. My buffer size is 4096 bytes. The main problem is that the recordings contain quite a lot of clicks; indicating missing samples. Anyone knows how to make the recording process less prone to these missing samples? I think I can go down to 8kHz without much speech recognition performance decrease, if that would help me get rid of the clicks, but I'll have to retrain my recognizer again, so I'd rather not do that :) Thanks in advance!
-- You received this message because you are subscribed to the Google Groups "Android Developers" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/android-developers?hl=en
