SENTENCE SELECTION DEVICE FOR SPEECH SYNTHESIS TRAINING TO BUILD A SPEECH SYNTHESIZER BASED ON THE VOICE OF A PERSONAL SPEAKER AND OPERATING METHOD THEREOF

SENTENCE SELECTION DEVICE FOR SPEECH SYNTHESIS TRAINING TO BUILD A SPEECH SYNTHESIZER BASED ON THE VOICE OF A PERSONAL SPEAKER AND OPERATING METHOD THEREOF

Disclosed are a device for selecting a sentence for voice synthesis training to build a voice synthesizer based on a voice of an individual speaker and an operation method thereof. Since the device provides a technique capable of selecting the minimum number of sentences for training, which may cove...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HOI RIN KIM, YOUNG JOO SUH, SUNG HEE JUNG, YEUN JU CHOI
Format: Patent
Sprache:eng ; kor
Schlagworte:
ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Disclosed are a device for selecting a sentence for voice synthesis training to build a voice synthesizer based on a voice of an individual speaker and an operation method thereof. Since the device provides a technique capable of selecting the minimum number of sentences for training, which may cover various variations, when an individual user wants to build a voice synthesizer based on his or her own voice, the device may support the individual user to easily build the voice synthesizer using utterance data generated based only on the selected sentences for training. 개인 화자의 음성을 기반으로 하는 음성합성기를 구축하기 위한 음성합성 훈련용 문장 선정 장치 및 그 동작 방법이 개시된다. 본 발명은 개인 사용자가 자신의 음성을 기반으로 하는 음성합성기를 구축하고자 할 때, 다양한 변이음들을 포괄할 수 있는 최소한의 훈련용 문장들을 선별해 줄 수 있는 기법을 제공함으로써, 상기 개인 사용자가 상기 선별된 훈련용 문장들만을 기초로 생성된 발화 데이터를 이용해서 손쉽게 음성합성기를 구축할 수 있도록 지원할 수 있다.