DATA PROCESSING DEVICE, DATA PROCESSING METHOD AND PROGRAM

To provide a data processing device, method, and program for reading text that reproduces in the desired voice pauses and inflections of other readers.SOLUTION: A data processing device 1 includes: a reading information storage unit 121 that stores reading information which associates a time in a pl...

Full description

Saved in:
Bibliographic Details
Main Authors LIU YAFEI, FUKUHARA TADAYUKI
Format Patent
LanguageEnglish
Japanese
Published 31.08.2023
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:To provide a data processing device, method, and program for reading text that reproduces in the desired voice pauses and inflections of other readers.SOLUTION: A data processing device 1 includes: a reading information storage unit 121 that stores reading information which associates a time in a playback time of the content, a character uttered at the time, a volume, a pitch, which are time-series data indicating characteristic quantities of a voice of a first speaker who reads content consisting of a character string; a vocalization information storage unit 122 that stores vocalization information generated by sampling the voice uttered by the second speaker, and stored associated with a plurality of characters and tones of the voice uttered in pronouncing each of the plurality of characters; a generation unit 132 for generating reading data to be output as a sound comprising the tones corresponding to the characters at the respective times in the vocalization information, the volume and pitch at the time; and an output control unit 133 for controlling the reading data to be output.SELECTED DRAWING: Figure 2 【課題】他の朗読者の間や抑揚のある朗読を所望する音声で再現したテキストの読み上げるデータ処理装置、方法及びプログラムを提供す。【解決手段】データ処理装置1は、文字列から構成されるコンテンツを朗読する第1話者の音声の特徴量を示す時系列データである、コンテンツの再生時間における時刻と、該時刻において発声される文字と、音量と、音高と、を関連づけた朗読情報を記憶する朗読情報記憶部121と、第2話者が発声した音声をサンプリングして生成され、複数の文字と、複数の文字それぞれを発音する際に発声された声の音色と、を関連づけて記憶した発声情報を記憶する発声情報記憶部122と、朗読情報の前記時刻それぞれにおける文字に発声情報において対応する音色と該時刻における音量と音高とからなる音として出力させる読上データを生成する生成部132と、読上データを出力するよう制御する出力制御部133と、を有する。【選択図】図2
Bibliography:Application Number: JP20220024675