When I am getting a audio clips through internet, in addition to speech (expected sound), there could be distortion - sound could not be intelligible due to distortion. What might be a sure fire way or any other ways to detect this - other than noise suppression? If it is a good speech sound, then I want to do some feature extraction - before extracting features, I want to decide if it is going to be worth doing.
Detecting Speech Vs non-Speech and random sounds?
Started by ●February 10, 2015
Reply by ●February 13, 20152015-02-13
On Wednesday, February 11, 2015 at 6:48:32 AM UTC+13, speec...@gmail.com wrote:> When I am getting a audio clips through internet, in addition to speech (expected sound), there could be distortion - sound could not be intelligible due to distortion. > > What might be a sure fire way or any other ways to detect this - other than noise suppression? > > If it is a good speech sound, then I want to do some feature extraction - before extracting features, I want to decide if it is going to be worth doing.Feature extraction methods and classification algorithms such as SVM.
