Smoothing and differencing operations on the digitized acoustic waveform generate parameters which are used to determine whether the characteristics of a sound are changing or similar; parts that possess similar parameters are grouped together to form sustained segments and parts that possess changing parameters form transitional segments, resulting in the segmentation of connected speech into parts approximately corresponding to phonemes.
(See document for exact affiliation information.)
https://aes2.org/publications/elibrary-page/?id=1624
(863KB)
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.
