Session Details

[D-14]音声

Tue. Mar 5, 2024 1:45 PM - 3:15 PM JST
Tue. Mar 5, 2024 4:45 AM - 6:15 AM UTC
School of Integrated Arts and Sciences K308(HIROSHIMA UNIVERSITY Higashi-Hiroshima campus)
Chair:Toda Tomoki

[D-14-01]Text Generation with Speech Recognition for Historical Sound Sources of Taisho Era using Whisper

○Kenichiro Miwa1, Ukyo Yamazaki1 (1. Salesian Polytechnic)
PDF DownloadDownload PDF

[D-14-02]Evaluation of Recognition for Eating Sounds with Speech by Using Simulated Data

○Kazuhiro Koiwai1, Masafumi Nishida1, Masafumi Nishimura1,2 (1. Shizuoka Univ., 2. Aichi Sangyo Univ.)
PDF DownloadDownload PDF

[D-14-03]Distribution of Chaotic Characteristic Defined in the Specific Individual Voice, and her Circadian Rhythm

○Kakuichi Shiomi1 (1. Fukui Health Science University)
PDF DownloadDownload PDF

[D-14-04]A Study on Visualization of Missing Fundamental Using Square Waves

○Rintaro Sunoda1, Fukuharu Maejima1, Yamato Saito2, Hiroshi Nomura3,4, Hiroyuki Kameda1 (1. TUT, 2. SIT, 3. Tokyo Medical Center, 4. TMSOL)
PDF DownloadDownload PDF

[D-14-05]A Study on Feature Extraction and Resynthesis of Speech Sound by using VSC

○Koki Inaba1, Satoru Kato1, Motoshi Hara1 (1. National Institute of Technology, Matsue College)
PDF DownloadDownload PDF

[D-14-06]LSTM variational autoencoder including denoising in drum groove pattern visualization

○Shun Matsukawa1, Komei Arasawa1, Akihiro Suzuki1, Hiroki Matsuzaki1 (1. Hokkaido University of Science)
PDF DownloadDownload PDF