Online edition: ISSN 2432-6380
[TOP] | [2018] | [2019] | [2020] | [2021] | [2022] | [2023] | [2024] | [Japanese] / [English]
SP2023-34
Effectiveness of Signal Compression in Speech Enhancement with Diffusion Models
Yuki Nishi (Titech), Koji Iwano (Tokyo City Univ.), Koichi Shinoda (Titech)
pp. 1 - 6
SP2023-35
Development and effects of English speech training drills to improve perception and production skills seamlessly with interactive gamification
Nobuaki Minematsu, Yingxiang Gao (UTokyo), Noriko Nakanishi (KGU), Yusuke Inoue, Hiroaki Mizuno (Carriage)
pp. 7 - 12
SP2023-36
Enhancing Recognition of Rare Words in ASR through Error Detection and Context-Aware Error Correction
Jiajun He, Zekun Yang, Tomoki Toda (Nagoya Univ.)
pp. 13 - 18
SP2023-37
Improvement of Tacotron2 text-to-speech model based on masking operation and positional attention mechanism
Tong Ma, Daisuke Saito, Nobuaki Minematsu (Univ. of Tokyo)
pp. 19 - 24
SP2023-38
[Poster Presentation]
Enhancing Multi-Accent Automated Speech Recognition with Accent-Activated Adapters
Yuqin Lin, Longbiao Wang, Jianwu Dang (Tianjin Univ. & Univ. of Tokyo), Nobuaki Minematsu (Univ. of Tokyo)
pp. 25 - 30
SP2023-39
[Poster Presentation]
Enhancing Dysarthric Speech Recognition with Auxiliary Feature Fusion Module: Exploring Articulatory-related Features from Foundation Models
Yuqin Lin, Longbiao Wang, Jianwu Dang (Tianjin Univ. & Univ. of Tokyo), Nobuaki Minematsu (Univ. of Tokyo)
pp. 31 - 36
SP2023-40
[Poster Presentation]
Integration of Throat Microphone Recording and Bandwidth Extension for Robust Assessment of L2 Listening
Yu Xu, Nobuaki Minematsu, Daisuke Saito (Univ. of Tokyo)
pp. 37 - 42
SP2023-41
[Poster Presentation]
Self-supervised learning model based emotion transfer and intensity control technology for expressive speech synthesis
Wei Li, Nobuaki Minematsu, Daisuke Saito (Univ. of Tokyo)
pp. 43 - 48
SP2023-42
Report on Participation in Interspeech2023
Kentaro Mitsui (rinna), Kohei Matsuura (NTT)
p. 49
Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.