IEICE Technical Report

Online edition: ISSN 2432-6380

Speech

Workshop Date : 2024-06-14 - 2024-06-15 / Issue Date : 2024-06-07

SP2024-1
[Poster Presentation] Computation of acoustic field in the vicinity of the wedge-shaped cut imitating the lips by using FDTD method
Chiune Sato, Kunitoshi Motoki (Hokkai-Gakuen Univ.)
pp. 1 - 4

SP2024-2
Real-time target speaker extraction using direction and voice features
Kengo Ohara, Kosuke Osumi, Erika Yamamoto, Masanori Morobishi, Takayuki Arakawa (Kyocera Corp.)
pp. 5 - 10

SP2024-3
Evaluation of nonlinear distortion for hearing loss simulators and its relationship to algorithms
Shintaro Doan, Toshio Irino, Minami Ishikawa (Wakayama Univ.)
pp. 11 - 16

SP2024-4
[Poster Presentation] Opera-singing voice synthesis from inexperienced voice considering vowel and tempo change.
Aoto Sugahara (Kobe Univ.), Soma Kishimoto, Yuji Adachi, Kiyoto Tai (MEC), Ryoichi Takashima, Tetsuya Takiguchi (Kobe Univ.)
pp. 17 - 22

SP2024-5
Beyond Word Count: Exploring Approximated Target Lengths for CIF-RNNT
Wen Shen Teo, Yasuhiro Minami (UEC)
pp. 23 - 27

SP2024-6
Acoustic-to-articulatory Inversion using real-time MRI for Pronunciation Practice
Anna Oura, Hideaki Kikuchi, Tetsunori Kobayashi (Waseda Univ.)
pp. 28 - 32

SP2024-7
[Poster Presentation] A voice synthesizer operated by fingers to control its vocal-tract area function.
Amane Koriki, Masashi Ito (Tohtech)
pp. 33 - 36

SP2024-8
Discussion toward Accurate Speech Signal Analysis
Shigeki Sagayama (UT/UEC)
pp. 37 - 42

SP2024-9
[Poster Presentation] Improving CTC-based ASR model by weighting encoder layers using attention mechanisms
Keigo Hojo, Yukoh Wakabayashi (TUT), Kengo Ohta (NITAC), Atsunori Ogawa (NTT), Norihide Kitaoka (TUT)
pp. 43 - 48

Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan