VOICE PROCESSING METHOD AND VOICE PROCESSING DEVICE

To synthesize voice which is aurally natural.SOLUTION: A voice processing device comprises a time extension/contraction unit 31 which, for a voice signal X representing voice, contracts forward a first steady period in a plurality of steady periods in which an acoustic property is stable in terms of...

Full description

Saved in:
Bibliographic Details
Main Authors DAIDO RYUNOSUKE, KAYAMA HIROSHI
Format Patent
LanguageEnglish
Japanese
Published 19.09.2019
Subjects
ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:To synthesize voice which is aurally natural.SOLUTION: A voice processing device comprises a time extension/contraction unit 31 which, for a voice signal X representing voice, contracts forward a first steady period in a plurality of steady periods in which an acoustic property is stable in terms of time and extends forward a transition period between the first steady period and a second steady period different in pitch from the first steady period right after the first steady period in the plurality of steady periods.SELECTED DRAWING: Figure 2 【課題】聴感的に自然な音声を合成する。【解決手段】音声処理装置は、音声を表す音声信号Ｘについて、音響特性が時間的に安定している複数の定常期間のうちの第１定常期間を前方に収縮し、複数の定常期間のうち第１定常期間の直後において当該第１定常期間とは音高が相違する第２定常期間と第１定常期間との間の遷移期間を前方に伸長する時間伸縮部３１を具備する。【選択図】図２
Bibliography:Application Number: JP20180043115