Synthesis of voiced sounds using physics-informed neural networks

被引：0

作者：

Yokota, Kazuya ^{[1
]}

Ogura, Masataka ^{[2
]}

Abe, Masajiro ^{[3
]}

机构：

[1] Nagaoka Univ Technol, Dept Mech Engn, 1603-1 Kamitomioka, Nagaoka 9402188, Japan

[2] Nagaoka Univ Technol, Ctr Integrated Technol Support, 1603-1 Kamitomioka, Nagaoka 9402188, Japan

[3] Nagaoka Univ Technol, Dept Syst Safety Engn, 1603-1 Kamitomioka, Nagaoka 9402188, Japan

来源：

ACOUSTICAL SCIENCE AND TECHNOLOGY | 2024年 / 45卷 / 06期

关键词：

Physics-informed neural networks; PINNs; Vocal tract; Voiced sounds; Glottal inverse filtering; MODEL;

D O I：

10.1250/ast.e24.55

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Recently, physics-informed neural networks (PINNs) have garnered attention for use as a numerical simulation method for inverse analysis, such as property identification. However, studies on PINNs for conducting acoustic analysis are scarce. Thus, this study developed PINNs that performed acoustic analysis of the vocal tract and synthesized voiced sounds. In addition, PINNs were used to identify glottal source waveforms. Consequently, PINNs were demonstrated to be a promising solution for the inverse problem related to speech production.

引用

页码：333 / 336

页数：4

共 50 条

[41] Modeling of the Forward Wave Propagation Using Physics-Informed Neural Networks
Alkhadhr, Shaikhah
Liu, Xilun
Almekkawy, Mohamed
INTERNATIONAL ULTRASONICS SYMPOSIUM (IEEE IUS 2021), 2021,
[42] Optimizing Variational Physics-Informed Neural Networks Using Least Squares
Uriarte, Carlos
Bastidas, Manuela
Pardo, David
Taylor, Jamie M.
Rojas, Sergio
COMPUTERS & MATHEMATICS WITH APPLICATIONS, 2025, 185 : 76 - 93
[43] Asian Option Pricing Using the Physics-Informed Neural Networks Method
Park, Sungwon
Moon, Kyoung-Sook
Kim, Hongjoong
ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH, 2025, 59 (01): : 5 - 20
[44] Parameter Identification in Manufacturing Systems Using Physics-Informed Neural Networks
Khalid, Md Meraj
Schenkendorf, Rene
ADVANCES IN ARTIFICIAL INTELLIGENCE IN MANUFACTURING, ESAIM 2023, 2024, : 51 - 60
[45] Surface Flux Transport Modeling Using Physics-informed Neural Networks
Athalathil, Jithu J.
Vaidya, Bhargav
Kundu, Sayan
Upendran, Vishal
Cheung, Mark C. M.
ASTROPHYSICAL JOURNAL, 2024, 975 (02):
[46] Parallel Physics-Informed Neural Networks with Bidirectional Balance
Huang, Yuhao
Xu, Jiarong
Fang, Shaomei
Zhu, Zupeng
Jiang, Linfeng
Liang, Xiaoxin
6TH INTERNATIONAL CONFERENCE ON INNOVATION IN ARTIFICIAL INTELLIGENCE, ICIAI2022, 2022, : 23 - 30
[47] Tackling the curse of dimensionality with physics-informed neural networks
Hu, Zheyuan
Shukla, Khemraj
Karniadakis, George Em
Kawaguchi, Kenji
NEURAL NETWORKS, 2024, 176
[48] Boussinesq equation solved by the physics-informed neural networks
Ruozhou Gao
Wei Hu
Jinxi Fei
Hongyu Wu
Nonlinear Dynamics, 2023, 111 : 15279 - 15291
[49] Design of Turing Systems with Physics-Informed Neural Networks
Kho, Jordon
Koh, Winston
Wong, Jian Cheng
Chiu, Pao-Hsiung
Ooi, Chin Chun
2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2022, : 1180 - 1186
[50] The application of physics-informed neural networks to hydrodynamic voltammetry
Chen, Haotian
Kaetelhoen, Enno
Compton, Richard G.
ANALYST, 2022, 147 (09) : 1881 - 1891

← 1 2 3 4 5 →