EP 1860645 A2 20071128 - Automatic segmentation in speech synthesis
Title (en)
Automatic segmentation in speech synthesis
Title (de)
Automatische Segmentierung bei der Sprachsynthese
Title (fr)
Segmentation automatique dans la synthèse vocale
Publication
Application
Priority
- EP 03100795 A 20030327
- US 36904302 P 20020329
- US 34186903 A 20030114
Abstract (en)
In a system having a speech inventory that includes phone labels that are concatenated to form synthetic speech, a method for segmenting the phone labels comprises: performing an alignment on a trained set of HMMs to produce phone labels that are segmented, wherein each phone label has a spectral boundary; and performing spectral boundary correction on the phone labels, wherein spectral boundary correction re-aligns each spectral boundary using bending points of spectral transitions, wherein the phone labels having spectral boundary correction are used for speech synthesis.
IPC 8 full level
G10L 13/06 (2006.01); G10L 15/14 (2006.01)
CPC (source: EP)
G10L 13/06 (2013.01)
Designated contracting state (EPC)
DE FI FR GB NL
DOCDB simple family (publication)
EP 1860645 A2 20071128; EP 1860645 A3 20080903; EP 1860646 A2 20071128; EP 1860646 A3 20080903
DOCDB simple family (application)
EP 07116265 A 20030327; EP 07116266 A 20030327