Awesome Speech Audio
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Tatsuya Kawahara — most-cited papers & profile · Speech Audio
← authors
·
overview
Tatsuya Kawahara
6
papers ·
11
citations ·
40
h-index
Kyoto University · Kyoto College of Graduate Studies for Informatics
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Enhancing Monotonic Multihead Attention for Streaming ASR
2020 · 10 citations
CTC-synchronous Training for Monotonic Attention Model
2020 · 1 citations
Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
2017
Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition
2019
VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording
2021
Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer
2024
Top co-authors
Masato Mimura
· 4
Hirofumi Inaguma
· 3
Katsutoshi Itoyama
· 2
Kazuyoshi Yoshii
· 2
Yoshiaki Bando
· 2
Kazuki Shimada
· 1
Shinsuke Sakai
· 1
Tomoki Honda
· 1
Topics
Speech Recognition
Speech Enhancement
Speech Translation