{"id":100106,"date":"2021-05-06T10:22:50","date_gmt":"2021-05-06T08:22:50","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-sintezatora-rechi-rhvoice-1-2-4-razvivaemogo-dlya-russkogo-yazyka"},"modified":"2021-05-06T10:22:50","modified_gmt":"2021-05-06T08:22:50","slug":"vypusk-sintezatora-rechi-rhvoice-1-2-4-razvivaemogo-dlya-russkogo-yazyka","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hu\/blog\/news\/vypusk-sintezatora-rechi-rhvoice-1-2-4-razvivaemogo-dlya-russkogo-yazyka","title":{"rendered":"A RHVoice 1.2.4 besz\u00e9dszint\u00e9zis kiad\u00e1s\u00e1nak megjelen\u00e9se, amelyet orosz nyelv sz\u00e1m\u00e1ra fejlesztettek ki","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
Megjelent a RHVoice 1.2.4 ny\u00edlt forr\u00e1sk\u00f3d\u00fa besz\u00e9dszintetiz\u00e1l\u00f3, amelyet eredetileg az orosz nyelv sz\u00ednvonalas t\u00e1mogat\u00e1s\u00e1nak biztos\u00edt\u00e1s\u00e1ra fejlesztettek ki, de k\u00e9s\u0151bb m\u00e1s nyelvekre is adapt\u00e1lt\u00e1k, bele\u00e9rtve az angolt, portug\u00e1lt, ukr\u00e1nt, kirgizt, tat\u00e1rt \u00e9s gr\u00fazt. A k\u00f3d C++ nyelven k\u00e9sz\u00fclt, \u00e9s az LGPL 2.1 licenc alatt terjesztik. T\u00e1mogatja a GNU\/Linux, Windows \u00e9s Android rendszereket. A program kompatibilis a standard TTS interf\u00e9szekkel (text-to-speech) a sz\u00f6veg besz\u00e9dd\u00e9 alak\u00edt\u00e1s\u00e1hoz: SAPI5 (Windows), Speech Dispatcher (GNU\/Linux) \u00e9s Android Text-To-Speech API, de haszn\u00e1lhat\u00f3 az NVDA k\u00e9perny\u0151olvas\u00f3val is. <\/p>\n
A parametric synthesis method is used in the program with statistical models (Statistical Parametric Synthesis based on HMM \u2014 Hidden Markov Model). The advantages of the statistical model are low overhead and minimal CPU power requirements. All operations are performed locally on the user's system. Three levels of speech quality are supported (the lower the quality \u2014 the higher the performance and the shorter the response time). <\/p>\n
Voice configuration and switching are supported. There are 9 voice options available for Russian and 5 for English. The voices are generated based on recordings of natural speech. Due to the use of a statistical model, the pronunciation quality does not reach the level of synthesizers that generate speech based on combinations of natural speech fragments, but the result is still quite intelligible and resembles the playback of a recording via a loudspeaker. <\/p>\n
A be\u00e1ll\u00edt\u00e1sokban m\u00f3dos\u00edthat\u00f3 a sebess\u00e9g, a magass\u00e1g \u00e9s a hanger\u0151. A temp\u00f3 m\u00f3dos\u00edt\u00e1s\u00e1hoz haszn\u00e1lhat\u00f3 a Sonic k\u00f6nyvt\u00e1r. Automatikus nyelv\u00e9rz\u00e9kel\u00e9s \u00e9s v\u00e1lt\u00e1s is lehets\u00e9ges a bels\u0151 sz\u00f6veg elemz\u00e9se alapj\u00e1n (p\u00e9ld\u00e1ul m\u00e1s nyelven l\u00e9v\u0151 szavak \u00e9s id\u00e9zetek eset\u00e9n a szint\u00e9zishez a sz\u00f3 szerinti nyelv modellje haszn\u00e1lhat\u00f3). T\u00e1mogatottak a hangprofilok, amelyek meghat\u00e1rozz\u00e1k a k\u00fcl\u00f6nb\u00f6z\u0151 nyelvekhez tartoz\u00f3 hangkombin\u00e1ci\u00f3kat. \n Forr\u00e1s: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"