Methods and apparatus for rapid acoustic unit selection from a large speech corpus
AssigneeAT&T Corp.
InventorsMark Charles. Beutnagel, Mehryar Mohri, Michael Dennis Riley
Life of this patent
Estimating the term…
Loading patent…
AssigneeAT&T Corp.
InventorsMark Charles. Beutnagel, Mehryar Mohri, Michael Dennis Riley
Estimating the term…
A speech synthesis system can select recorded speech fragments, or acoustic units, from a very large database of acoustic units to produce artificial speech. The selected acoustic units are chosen to minimize a combination of target and concatenation costs for a given sentence. However, as concatenation costs, which are measures of the mismatch between sequential pairs of acoustic units, are expensive to compute, processing can be greatly reduced by pre-computing and caching the concatenation costs. Unfortunately, the number of possible sequential pairs of acoustic units makes such caching prohibitive. However, statistical experiments reveal that while about 85% of the acoustic units are typically used in common speech, less than 1% of the possible sequential pairs of acoustic units occur in practice. A method for constructing an efficient concatenation cost database is provided by synthesizing a large body of speech, identifying the acoustic unit sequential pairs generated and their respective concatenation costs, and storing those concatenation costs likely to occur. By constructing a concatenation cost database in this fashion, the processing power required at run-time is greatly reduced with negligible effect on speech quality.
A method of selecting acoustic units from an acoustic unit database for synthesizing speech, a concatenation cost being a measure of the mismatch between an acoustic unit sequential pair, the method comprising:
An apparatus for selecting acoustic units, comprising:
A method of forming a computer readable medium containing a concatenation cost database, a concatenation cost being a measure of the mismatch between an acoustic unit sequential pair, the method comprising;
Dependencies are inferred from the claim text.