EMOTION INFORMATION-BASED VOICE SYNTHESIS METHOD AND DEVICE

Disclosed are an emotion information-based voice synthesis method and device. In an emotion information-based voice synthesis method according to an embodiment of the present invention, when emotion information is set in a received message, metadata corresponding to the set emotion information is de...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HAN, Sungmin, CHAE, Jonghoon, YANG, Siyoung, JANG, Juyeong, PARK, Yongchul
Format: Patent
Sprache:eng ; fre ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Disclosed are an emotion information-based voice synthesis method and device. In an emotion information-based voice synthesis method according to an embodiment of the present invention, when emotion information is set in a received message, metadata corresponding to the set emotion information is delivered to a voice synthesis engine, and when emotion information is not set in the received message, new emotion information is generated through semantic analysis and contextual analysis of the received message, and metadata corresponding to the generated emotion information is delivered to the voice synthesis engine. The voice synthesis engine can perform voice synthesis by loading emotion information on the basis of the delivered metadata. L'invention concerne un procédé et un dispositif de synthèse vocale basée sur des informations d'émotion. Dans un procédé de synthèse vocale basée sur des informations d'émotion selon un mode de réalisation de la présente invention, lorsque des informations d'émotion sont définies dans un message reçu, des métadonnées correspondant aux informations d'émotion définies sont délivrées à un moteur de synthèse vocale, et lorsque des informations d'émotion ne sont pas définies dans le message reçu, de nouvelles informations d'émotion sont générées par analyse sémantique et analyse contextuelle du message reçu, et des métadonnées correspondant aux informations d'émotion générées sont délivrées au moteur de synthèse vocale. Le moteur de synthèse vocale peut effectuer une synthèse vocale en chargeant des informations d'émotion sur la base des métadonnées délivrées. 감정 정보 기반의 음성 합성 방법 및 장치를 개시한다. 본 발명의 일 실시예에 따른 감정 정보 기반의 음성 합성 방법은, 수신된 메시지에 감정 정보가 설정된 경우, 설정된 감정 정보에 대응하는 메타 데이터를 음성 합성 엔진으로 전달하고, 수신된 메시지에 감정 정보가 설정되어 있지 않은 경우, 수신된 메시지의 문장 내 의미 분석 및 문맥 분석을 통해 새로운 감정 정보를 생성하고, 생성된 감정 정보에 대응하는 메타 데이터를 음성 합성 엔진으로 전달한다. 음성 합성 엔진은 전달된 메타 데이터에 기초하여 감정 정보를 실어서 음성 합성을 수행할 수 있다.