Subspace tracking for speech enhancement in car noise environments
Jhing-Fa Wang, Chung-Hsien Yang, Kai-Hsing Chang · 2004
A signal subspace speech enhancement based on a subspace tracking algorithm is presented. The proposed method incorporates a perceptual filterbank which is derived from a psycho-acoustic model for subband processing. The experiments were performed using the TAICAR in-car noisy speech database. Subjective and objective tests show that our method outperforms other existing signal subspace methods.