TR2021009134A1 - Artificial representation synthesis method with audio-to-video conversion. - Google Patents

Artificial representation synthesis method with audio-to-video conversion.

Info

Publication number
TR2021009134A1
TR2021009134A1 TR2021/009134 TR2021009134A1 TR 2021009134 A1 TR2021009134 A1 TR 2021009134A1 TR 2021/009134 TR2021/009134 TR 2021/009134 TR 2021009134 A1 TR2021009134 A1 TR 2021009134A1
Authority
TR
Turkey
Prior art keywords
artificial
voice
synthesis method
synthesizing
audio
Prior art date
Application number
TR2021/009134
Other languages
Turkish (tr)
Inventor
Cakir Yeni̇do An Duygu
Original Assignee
Bahçeşehi̇r Üni̇versi̇tesi̇
Filing date
Publication date
Application filed by Bahçeşehi̇r Üni̇versi̇tesi̇ filed Critical Bahçeşehi̇r Üni̇versi̇tesi̇
Priority to PCT/TR2022/050507 priority Critical patent/WO2022255980A1/en
Publication of TR2021009134A1 publication Critical patent/TR2021009134A1/en

Links

Abstract

Buluş, sesten nitelik çıkarımı, sese ait sahte yüz üretimi, eğitim seti için gerekli video üretimi ve gerçek zamanlı yapay temsilci üretilmesi işlemlerini gerçekleştiren yapay/sanal temsilci sentezleme yöntemi ile ilgilidir. Buluş özellikle, konuşan kişinin sesinden özelliklerinin çıkarılmasını, bu özelliklere uygun GAN tabanlı sahte bir yüz görüntüsünün sentezlenmesini, sonraki eğitim adımına beslemek için bir video kaydı alınması ve yapay yüze uygun şekilde sentezlenmesini ve gerçek zamanda konuşmacının sesiyle yeni video sentezlenmesini sağlayan bir yapay/sanal temsilci sentezleme yöntemi ile ilgilidir.The invention is related to the artificial/virtual representative synthesis method that performs feature extraction from voice, fake face production of voice, video production required for the training set and real-time artificial representative production. In particular, the invention is an artificial/virtual representative synthesis that enables extracting the features of the speaker's voice, synthesizing a GAN-based fake face image suitable for these features, recording a video to feed it to the next training step and synthesizing it in accordance with the artificial face, and synthesizing a new video with the speaker's voice in real time. It's about the method.

TR2021/009134 2021-06-02 2021-06-02 Artificial representation synthesis method with audio-to-video conversion. TR2021009134A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/TR2022/050507 WO2022255980A1 (en) 2021-06-02 2022-05-31 Virtual agent synthesis method with audio to video conversion

Publications (1)

Publication Number Publication Date
TR2021009134A1 true TR2021009134A1 (en) 2022-12-21

Family

ID=

Similar Documents

Publication Publication Date Title
KR102158743B1 (en) Data augmentation method for spontaneous speech recognition
US20220013106A1 (en) Multi-speaker neural text-to-speech synthesis
CN104123932B (en) A kind of speech conversion system and method
CN100347741C (en) Mobile speech synthesis method
ATE491202T1 (en) COMPENSATING BETWEEN-SESSION VARIABILITY TO AUTOMATICALLY EXTRACT INFORMATION FROM SPEECH
KR950035447A (en) Video Signal Processing System Using Speech Analysis Automation and Its Method
MY145597A (en) Method and apparatus for representing image granularity by one or more parameters
CN102201233A (en) Mixed and matched speech synthesis method and system thereof
EP4270255A3 (en) Cross-lingual voice conversion system and method
EP4075430A3 (en) Method and apparatus for speech generation
CN113066511B (en) Voice conversion method and device, electronic equipment and storage medium
CN105448289A (en) Speech synthesis method, speech synthesis device, speech deletion method, speech deletion device and speech deletion and synthesis method
CN108307250A (en) A kind of method and device generating video frequency abstract
TR2021009134A1 (en) Artificial representation synthesis method with audio-to-video conversion.
EP3361413A3 (en) Method and apparatus of selecting candidate fingerprint image for fingerprint recognition
CN1731510A (en) Text-speech conversion for amalgamated language
CN111128211A (en) Voice separation method and device
CN105788608B (en) Chinese phonetic mother method for visualizing neural network based
JP2024519739A (en) Audio and video translators
JP2006235712A (en) Conversation recording device
EA202091595A1 (en) METHOD AND DEVICE FOR BUILDING VOICE MODEL OF A TARGET ANNOUNCER
CN105931651B (en) Audio signal processing method, device and hearing-aid device in hearing-aid device
CN115985303A (en) Digital human figure generating method based on sound and related device thereof
CN102231275A (en) Embedded speech synthesis method based on weighted mixed excitation
CN116152888A (en) Method for quickly generating virtual human dynamic business card based on ultra-short video sample