Patent Number: 8,788,268

Title: Speech synthesis from acoustic units with default values of concatenation cost

Abstract: A speech synthesis system can select recorded speech fragments, or acoustic units, from a very large database of acoustic units to produce artificial speech. When a pair of acoustic units in the database does not have an associated concatenation cost, the system assigns a default concatenation cost. The system then synthesizes speech, identifies the acoustic unit sequential pairs generated and their respective concatenation costs, and stores those concatenation costs likely to occur.

Inventors: Beutnagel; Mark Charles (Mendham, NJ), Mohri; Mehryar (New York, NY), Riley; Michael Dennis (New York, NY)

Assignee: AT&T Intellectual Property II, L.P.

International Classification: G10L 13/06 (20130101)

Expiration Date: 2022-07-22 0:00:00