In real-time audio signal processing, parameters (such as filter coefficients) must be updated (changed) in a manner precisely synchronized in time. Since any audio processor of reasonable size is dealing with multiple, independent channels of audio data, the overall data rate of such changes can be very high. In fact, even the average update rate can approach audio speeds (100K bytes per second) or higher. Furthermore, updates come in a burst fashion in that there are critical moments where many, many parameters change virtually simultaneously. In this case, the instantaneous update rate required can be as high as 30 million bytes per second if we require that all the updates be done precisely at a particular sample number. The update queue is a hardware method of dealing with all there problems in a uniform manner that incurs little management overhead. The update queue is a time-tagged first-in first-out queue. All the pointers are maintained by control hardware. The queue can be edited, in that insertion of new updates may be made into any position in the queue; either at the front, the back, or anywhere in between. At the end of each sample computation, the signal processor is placed in "update mode" where updates at the beginning of the queue are successively read off the queue and executed at machine speed (one per machine cycle). This provides flexibility, precise synchronization, and minimum timing overhead even in the presence of long bursts of updates.
Click to purchase paper as a non-member or you can login as an AES member to see more options.
No AES members have commented on this paper yet.
To be notified of new comments on this paper you can
subscribe to this RSS feed.
Forum users should login to see additional options.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.
