This paper presents a new technique for speech enhancement with applications in speech recordings and telecommunications. The technique implements a noise subtraction scheme which is a hybrid combination of spectral and cepstral subtraction concepts. Results show that this provides enhancement of both the quality and intelligibility of the speech superior to a single implementation of either of the above mentioned techniques.:
(See document for exact affiliation information.)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
