|
|
|
ACTNow
Audio Classification Technologies
(ACT) is a package of various software technologies, which enable you to automatically classify audio data into various types such as:
-
words or phrases: Where
was a particular word or phrase spoken?
Using Phonetic Index Search technology to search in a sound database
is several thousand times faster than searching manually. ACTNow makes the slow, error prone and
exhausting process of searching manually for texts in sound recordings obsolete.
-
speakers: Who is currently
speaking? Speaker Detection is used to find out if and where a certain person was speaking
-
audio clips/jingles/music:
Is a certain song or jingle being played? Detect if a song or advertising was aired. Automatically find out when a certain show or ads block starts and ends.
-
music vs. speech: Is it
rather music or is somebody currently speaking? Create statistics about the % of music aired vs. speech.
-
music track changes:
Where
does a music track begin and where does it end?
-
previously recorded words or
phrases: Where did a particular person say the same word again?
-
silence, multi-channel silence, multi-channel speech collision: Detect if all parties are silent, detect if multiple parties are speaking at
the same time.
The ACTNow SDK (Software Development Kit) helps you to easily integrate the ACTNow technology into your
software applications. It provides an
easy to use C/C++ API (Application Programming Interface) or COM Interface, which can be used in any software development environment.
Please
click here to download the specification sheet of ACTNow
Please
click here to download the German specification sheet of ACTNow
Please
select for further information:
|
|
|
|
