0 Replies Latest reply on Jan 25, 2015 10:21 AM by Travis Banger

    Unsupervised Noise Reduction (even better: Removal)

    Travis Banger Level 1

      More often than not, the noise is glaringly evident. Regardless, we users are required to provide a noise profile, which -being a sample- is by definition inaccurate.

       

      The breathing of the speaker or parts of his speech are included by us, and are therefore considered "noise". The dreaded "tinkle bells" (*) ensue.

       

      The "Sound Cleaner II" application for example does a remarkable job at discerning what is noise and what is "show".

       

      TIA,

       

      -RFH

       

      (*) Variously know as "wine glass", "metallic bubbles", "robotic", etc.