According to one exemplary embodiment, a method for updating an audio dictionary is provided. The method may include receiving at least one audio file within a plurality of audio files associated with a term. The method may also include receiving at least one user evaluation associated with the at least one audio file, the at least one user evaluation being based on a correlation between nationality characteristics associated with the received at least one audio file and the at least one user evaluation. The method may further include assigning a ranking to the at least one audio file within the plurality of audio files based on the received at least one user evaluation associated with the at least one audio file, wherein the assigned ranking is from a lowest ranking to a highest ranking. The method may also include adding the assigned highest ranking audio file into the audio dictionary.