| US 7,523,036 B2 | ||
| Text-to-speech synthesis system | ||
| Makoto Akabane, Tokyo (Japan); Hajime Yano, Kanagawa (Japan); Keiichi Yamada, Tokyo (Japan); Goro Shiraishi, Tokyo (Japan); Junichi Kudo, Tokyo (Japan); and Akira Tange, Tokyo (Japan) | ||
| Assigned to Sony Corporation, Tokyo (Japan) | ||
| Filed on Mar. 21, 2006, as Appl. No. 11/385,210. | ||
| Application 11/385210 is a continuation of application No. 10/161329, filed on May 31, 2002, granted, now 7,099,826. | ||
| Claims priority of application No. JP2001-167416 (JP), filed on Jun. 01, 2001. | ||
| Prior Publication US 2006/0161437 A1, Jul. 20, 2006 | ||
| This patent is subject to a terminal disclaimer. | ||
| Int. Cl. G10L 13/08 (2006.01) | ||
| U.S. Cl. 704—260 | 50 Claims |
| 1. A text-to-speech synthesis apparatus comprising:
storage means for storing phoneme data of a plurality of speaker voices;
selecting means for selecting at least two speaker voices from said plurality of speaker voices;
searching means for searching said storage means for phoneme data of the speaker voices selected by said selecting means;
and
text-to-speech synthesis processing means for linking said phoneme data of said speaker voices retrieved by said searching
means to convert input data into a synthetic speech;
wherein said text-to-speech synthesis processing means can convert said input data into a synthetic speech including at least
two speaker voices.
|