{"id":102522,"date":"2021-12-08T15:37:00","date_gmt":"2021-12-08T13:37:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-sintezatora-rechi-rhvoice-1-6-0"},"modified":"2021-12-08T15:37:00","modified_gmt":"2021-12-08T13:37:00","slug":"vypusk-sintezatora-rechi-rhvoice-1-6-0","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/vypusk-sintezatora-rechi-rhvoice-1-6-0","title":{"rendered":"Release of RHVoice speech synthesizer 1.6.0","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
The release of the open speech synthesis system RHVoice 1.6.0 has taken place. Initially developed to provide quality support for the Russian language, it has since been adapted for other languages including English, Portuguese, Ukrainian, Kyrgyz, Tatar, and Georgian. The code is written in C++ and is distributed under the LGPL 2.1 license. It supports operation in GNU\/Linux, Windows, and Android. The program is compatible with standard TTS interfaces for converting text to speech: SAPI5 (Windows), Speech Dispatcher (GNU\/Linux), and Android Text-To-Speech API, but can also be used in the NVDA screen reader. The creator and main developer of RHVoice is Olga Yakovleva, who continues to develop the project despite being completely blind. <\/p>\n
The new version adds 5 new voice options for Russian speech. Support for the Albanian language has been implemented. The Ukrainian language dictionary has been updated. Support for the pronunciation of emoji characters has been expanded. Work has been done to fix bugs in the Android application, user dictionary import has been simplified, and support for Android 11 has been added. New settings and features have been added to the core engine, including g2p.case, word_break, and support for equalization filters. <\/p>\n
It's worth noting that RHVoice incorporates advancements from the HTS project (HMM\/DNN-based Speech Synthesis System) and employs a parametric synthesis method with statistical models (Statistical Parametric Synthesis based on HMM \u2014 Hidden Markov Model). The advantages of the statistical model include 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, the higher the performance and the shorter the response time). <\/p>\n
A drawback of the statistical model is its relatively low quality of pronunciation, which does not reach the level of synthesizers that generate speech based on combinations of fragments of natural speech. Nonetheless, the result is quite intelligible and resembles the playback of a recording over a loudspeaker. For comparison, the Silero project, which provides an open engine for speech synthesis based on machine learning technologies and a set of models for the Russian language, surpasses RHVoice in quality. <\/p>\n
For the Russian language, there are 13 available voice options, while for English \u2014 there are 5. The voices are generated based on recordings of natural speech. In the settings, you can modify the speed, pitch, and volume. The Sonic library can be used to change the tempo. Automatic language detection and switching is possible based on the analysis of the input text (for instance, native synthesis models may be used for words and quotes in another language). Voice profiles are supported, which define combinations of voices for different languages. \n Source: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"