抄録
This paper proposes an improved voice activity detection (VAD) algorithm for controlling discontinuous transmission (DTX) of the adaptive multi-rate wideband (AMR-WB) speech codec. First, the original 12-band filter bank of AMR-WB VAD is implemented via wavelet transform. In addition, the background noise can be estimated in each sub-band by using the wavelet de-noising method. Then one can apply support vector machine (SVM) to train an optimized non-linear VAD decision rule involving the sub-band power and noise level of input speech signals. By the use of the trained SVM, the proposed VAD algorithm can produce more accurate detection results. Various experimental results carried out from the Aurora speech database show that the proposed algorithm gives considerable VAD performances superior to the AMR-WB VAD.
