Speech synthesis
First Claim
Patent Images
1. A speech synthesiser comprising:
- a store containing representations of speech waveform;
selection means responsive in operation to phonetic representations input thereto of desired sounds to select from the store units of speech waveform representing portions of words corresponding to the desired sounds;
voiced portion identification means arranged in operation to identify voiced portions of the selected units;
means for concatenating the selected units of speech waveform; and
amplitude adjustment means responsive to said voiced portion identification means and arranged to adjust the amplitude of the voiced portions of the units relative to a predetermined reference level and to leave unchanged at least part of any unvoiced portion of the unit.
1 Assignment
0 Petitions
Accused Products
Abstract
Portions of recorded speech waveform (e.g., corresponding to phonemes) are combined to synthesize words. In order to provide a smoother delivery, each voiced portion of a waveform portion has its amplitude adjusted to a predetermined reference level. The scaling factor used is varied gradually over a transition region between such portions and between voiced and unvoiced portions.
-
Citations
8 Claims
-
1. A speech synthesiser comprising:
-
a store containing representations of speech waveform; selection means responsive in operation to phonetic representations input thereto of desired sounds to select from the store units of speech waveform representing portions of words corresponding to the desired sounds; voiced portion identification means arranged in operation to identify voiced portions of the selected units; means for concatenating the selected units of speech waveform; and amplitude adjustment means responsive to said voiced portion identification means and arranged to adjust the amplitude of the voiced portions of the units relative to a predetermined reference level and to leave unchanged at least part of any unvoiced portion of the unit. - View Dependent Claims (2, 3, 4)
-
-
5. A method for synthesising speech comprising:
-
storing representations of speech waveform; selecting, in response to phonetic representations of desired sounds, units of stored speech waveform representing portions of words corresponding to the desired sounds; identifying voiced portions of the selected units; concatenating the selected units of speech waveform; and adjusting the amplitude of the voiced portions of the units relative to a predetermined reference level and responsive to said voiced portion while leaving unchanged at least part of any unvoiced portion of the unit. - View Dependent Claims (6, 7, 8)
-
Specification