A new technique to filter reduction for speech signal processing systems

In many applications, one needs to approximate a filter of very high order with that of lower order. To reduce the order of the filter, some techniques such as the balanced model reduction approach are often applied. In this paper, we introduce a new technique which is based on minimizing the H₂-norm between the filter of very high order and the reduced one. This technique shows much better performance than other existing model reduction methods and is applied to estimating the vocal tract filter for speech processing systems. A speech processing example is presented to demonstrate the design procedure and the performance of the proposed algorithm