AUTOMATIC SEGMENTATION IN SPEECH SYNTHESIS

摘要

Systems and methods for automatically segmenting speech inventories. A set of Hidden Markov Models (HMMs) are initialized using bootstrap data. The HMMs a re next re-estimated and aligned to produce phone labels. The phone boundaries of th e phone labels are then corrected using spectral boundary correction. Optionally, this process of using the spectral-boundary-corrected phone labels as input instead of the bootstrap data is performed iteratively in order to further reduce mismatches between manual labels and phone labels assigned by the HMM approach.