SYNCHRONIZATION CONTROLLER

To secure the integrity of a video content and reproduce translated subtitles and the video content in synchronism by identifying voices included in the video content by voice recognition, translating these into another language to obtain translated subtitles and then adding these to the video conte...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: GUO XINYU, ONO TAKAYA
Format: Patent
Sprache:eng ; jpn
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:To secure the integrity of a video content and reproduce translated subtitles and the video content in synchronism by identifying voices included in the video content by voice recognition, translating these into another language to obtain translated subtitles and then adding these to the video content.SOLUTION: A synchronization controller 10 comprises: a detection unit 11 that detects a series of multiple voice sections in a video content and detects a longest voice section; a voice recognition unit 12 that acquires text data for each voice section as the processing result of voice recognition performed on voices in the multiple voice sections; a translation unit 13 that acquires translated subtitle data for each voice section as the processing result of translation of the acquired text data into another language; and a control unit 14 that causes the video content to be delayed for the total processing time of the detection unit 11, the voice recognition unit 12 and the translation unit 13 required for the longest voice section, and to be reproduced adding the translated subtitle data for each voice section to the delayed video content.SELECTED DRAWING: Figure 1 【課題】映像コンテンツの完全性を確保しつつ、映像コンテンツに含まれた音声を音声認識して他の言語に翻訳した翻訳字幕を、映像コンテンツに付与し、翻訳字幕と映像コンテンツとを同期させて再生する。【解決手段】同期制御装置10は、映像コンテンツにおける一連の複数の音声区間を検出して最長音声区間を検出する検出部11と、上記複数の音声区間の音声を対象とする音声認識の処理結果としての音声区間ごとのテキストデータを取得する音声認識部12と、取得されたテキストデータを対象とする他の言語への翻訳の処理結果としての音声区間ごとの翻訳字幕データを取得する翻訳部13と、最長音声区間を対象とした検出部11、音声認識部12および翻訳部13の合計処理時間だけ映像コンテンツを遅延させ、遅延させた映像コンテンツに音声区間ごとの翻訳字幕データを付与して再生する制御部14と、を備える。【選択図】図1