翻訳と辞書 Words near each other ・ Ceren Alkan ・ Ceren Kestirengöz ・ Ceren Nurlu ・ Ceren Sarper ・ Cerenerian Sea ・ Cerenli, Yüreğir ・ Cereno Upham Jones ・ Cerenova ・ Cerent Corporation ・ Cerentino ・ Cerenzia ・ Cereo Company ・ Cereophagus ・ Cereopsis novaehollandiae grisea ・ Cereopsius ・ CereProc ・ Ceres ・ Ceres (1787 ship) ・ Ceres (dwarf planet) ・ Ceres (dwarf planet) in fiction ・ Ceres (mythology) ・ Ceres (organization) ・ CERES (satellite) ・ Ceres (workstation) ・ Ceres Airport ・ Ceres Arena ・ Ceres Brewery ・ Ceres Cafe ・ CERES Community Environment Park ・ Ceres Connection Dictionary Lists mini英和辞書 mini和英辞書 Webster 1913 Latin-English FOLDOC Wikipedia English ウィキペディア

翻訳と辞書　辞書検索 [ 開発暫定版 ] スポンサード リンク CereProc ： ウィキペディア英語版 CereProc CereProc is a speech synthesis company based in Edinburgh, Scotland, founded in 2005. The company specialises in creating natural and expressive-sounding text to speech voices, synthesis voices with regional accents, and in voice cloning. == Voice building technology == CereProc creates voices using two different voice-building technologies: unit selection synthesis and HTS. CereProc's unit selection voices are built from large databases of recorded speech. During database creation, each recorded utterance is segmented into some or all of the following: individual phones, syllables, morphemes, words, phrases, and sentences. The division into segments is done using a specially modified speech recognizer.〔Alan W. Black, (Perfect synthesis for all of the people all of the time. IEEE TTS Workshop 2002. )〕 An index of the units in the speech database is then created based on the segmentation and acoustic parameters like the fundamental frequency (pitch), duration, position in the syllable, and neighbouring phones. At runtime, the desired target utterance is created by determining the best chain of candidate units from the database (unit selection). Unit selection provides the greatest naturalness, because it applies digital signal processing (DSP) to the recorded speech only at concatenation points. DSP often makes recorded speech sound less natural. CereProc's HTS voices produce speech synthesis based on hidden Markov models (HMMs). In this system, the frequency spectrum (vocal tract), fundamental frequency (vocal source), and duration (prosody) of speech are modelled simultaneously by HMMs. Speech waveforms are generated from HMMs themselves based on the maximum likelihood criterion.〔The HMM-based Speech Synthesis System, http://hts.sp.nitech.ac.jp/〕 Critically, HTS voices can be built from significantly less recorded speech than unit selection voices and have a much smaller footprint when installed. 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「CereProc」の詳細全文を読む スポンサード リンク 翻訳と辞書 : 翻訳のためのインターネットリソース Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.