FIELD: information technology.
SUBSTANCE: method involves merging words into syntagmas with marking of pause symbols at the end of the syntagmas with subsequent transcription of syntagmas to obtain ideal syntagma transcriptions in phoneme and allophone terms. Further, a data base of reference allophones is formed. Matching of allophones of ideal syntagma transcriptions with reference allophones is compared and allophones of ideal syntagma transcriptions which do not match reference allophones are excluded. Based on allophones of ideal syntagma transcriptions which match reference allophones, balanced text syntagmas are formed, having the highest number of matches of allophones of ideal syntagma transcriptions with reference allophones. The device has a text input unit, an analysis unit, a data base unit and a result display unit. The device also includes a parameter input unit and a unit for forming balanced syntagmas.
EFFECT: high quality, faster processing and fewer information resources.
6 cl, 10 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD FOR PRELIMINARY PROCESSING OF TEXT | 2007 |
|
RU2386178C2 |
| COMPUTER EQUIPMENT FOR READING OF PRINTED TEXT | 1996 |
|
RU2113726C1 |
| SPEECH SYNTHESIS METHOD | 2009 |
|
RU2421827C2 |
| SPEECH SYNTHESIS DEVICE | 2014 |
|
RU2606312C2 |
| METHOD FOR MESSAGE EXCHANGING AND DEVICES FOR IMPLEMENTATION OF THIS METHOD | 2007 |
|
RU2324296C1 |
| METHOD OF RE-SOUNDING AUDIO MATERIALS AND APPARATUS FOR REALISING SAID METHOD | 2012 |
|
RU2510954C2 |
| METHOD AND SYSTEM FOR LEXICAL INTERPRETATION OF FUSED SPEECH | 1997 |
|
RU2119196C1 |
| SPEECH RECOGNITION METHOD BASED ON TWO-LEVEL MORPHOPHONEMIC PREFIX GRAPH | 2015 |
|
RU2597498C1 |
| METHOD OF TEXT ANALYSIS | 2008 |
|
RU2392666C1 |
| SPEECH INFORMATION OUTPUT ARRANGEMENT | 0 |
|
SU607211A1 |
