METHODS AND SYSTEMS FOR SPLITTING A DIGITAL SIGNAL
First Claim
Patent Images
1. A method for splitting a digital signal using prosodic features included in the signal comprising:
- calculating onset value locations in the signal, the onset values corresponding to stress accents in the signal;
splitting, using a processor, the signal into a prosodic unit candidate sequence by superimposing the stress accent locations on the signal; and
processing the sequence to include only true prosodic units.
3 Assignments
0 Petitions
Accused Products
Abstract
A method for splitting a digital signal using prosodic features included in the signal is provided that includes calculating onset value locations in the signal. The onset values correspond to stress accents in the signal. Moreover, the method includes splitting, using a processor, the signal into a prosodic unit candidate sequence by superimposing the stress accent locations on the signal, and processing the sequence to include only true prosodic units.
-
Citations
14 Claims
-
1. A method for splitting a digital signal using prosodic features included in the signal comprising:
-
calculating onset value locations in the signal, the onset values corresponding to stress accents in the signal; splitting, using a processor, the signal into a prosodic unit candidate sequence by superimposing the stress accent locations on the signal; and processing the sequence to include only true prosodic units. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A system for splitting a digital signal using prosodic features included in the signal comprising:
-
a processor; and a memory operable to store data, said processor being programmed to; calculate locations of a phonetic cue type prosodic feature in a signal, the signal representing an utterance; and split the signal into a prosodic unit candidate sequence based on the calculated locations. - View Dependent Claims (8, 9, 10, 11, 12, 13)
-
-
14. A method for splitting a digital signal comprising:
-
extracting prosodic features from a digital signal representing a user utterance; calculating, using a processor, locations of a phonetic cue type prosodic feature, the phonetic cue type prosodic feature being included in the extracted prosodic features; and splitting the signal into prosodic unit candidates based on the calculated locations.
-
Specification