Title:
SPEECH SYNTHESIS METHOD AND DEVICE USING ADVERSARIAL TRAINING TECHNIQUE
Document Type and Number:
WIPO Patent Application WO/2023/158226
Kind Code:
A1
Abstract:
A speech synthesis method using an adversarial training technique according to an embodiment may comprise the steps of: receiving speech data input; training an adversarial model for speech synthesis on the basis of the speech data input; and synthesizing a frame of a target speech by using the adversarial model, wherein the step of synthesizing the frame of the speech comprises synthesizing the frame of the target speech using a non-autoregressive method.
Inventors:
CHANG JOON HYUK (KR)
LEE MOA (KR)
LEE MOA (KR)
Application Number:
PCT/KR2023/002229
Publication Date:
August 24, 2023
Filing Date:
February 15, 2023
Export Citation:
Assignee:
IUCF HYU (KR)
International Classes:
G10L13/02; G06N20/00; G10L13/08; G10L25/30
Foreign References:
| US20200098353A1 | 2020-03-26 | |||
| KR102275656B1 | 2021-07-09 |
Other References:
JUHEON LEE; HYEONG-SEOK CHOI; CHANG-BIN JEON; JUNGHYUN KOO; KYOGU LEE: "Adversarially Trained End-to-end Korean Singing Voice Synthesis System", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 6 August 2019 (2019-08-06), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081456376
YANG JINHYEOK, BAE JAE-SUNG, BAK TAEJUN, KIM YOUNG-IK, CHO HOON-YOUNG: "GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis", INTERSPEECH 2021, ISCA, ISCA, 1 January 2021 (2021-01-01), ISCA, pages 2202 - 2206, XP093085648, DOI: 10.21437/Interspeech.2021-971
JAEHYEON KIM; JUNGIL KONG; JUHEE SON: "Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 11 June 2021 (2021-06-11), 201 Olin Library Cornell University Ithaca, NY 14853, XP081988468
YANG JINHYEOK, BAE JAE-SUNG, BAK TAEJUN, KIM YOUNG-IK, CHO HOON-YOUNG: "GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis", INTERSPEECH 2021, ISCA, ISCA, 1 January 2021 (2021-01-01), ISCA, pages 2202 - 2206, XP093085648, DOI: 10.21437/Interspeech.2021-971
JAEHYEON KIM; JUNGIL KONG; JUHEE SON: "Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 11 June 2021 (2021-06-11), 201 Olin Library Cornell University Ithaca, NY 14853, XP081988468
Attorney, Agent or Firm:
HAEUM PATENT & LAW FIRM (KR)
Download PDF: