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
Takafumi Moriya — most-cited papers & profile · Speech Audio
← authors
·
overview
Takafumi Moriya
4
papers ·
30
citations ·
13
h-index
NTT (Japan)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition
2022 · 27 citations
Generic Speech Enhancement with Self-Supervised Representation Space Loss
2025 · 3 citations
All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR
2025
Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition
2021
Top co-authors
Hiroshi Sato
· 4
Marc Delcroix
· 3
Tsubasa Ochiai
· 3
Keisuke Kinoshita
· 2
Naoyuki Kamo
· 2
Ryo Masumura
· 2
Atsunori Ogawa
· 1
Masato Mimura
· 1
Takanori Ashihara
· 1
Tomohiro Tanaka
· 1
Topics
Speech Enhancement
Speech Recognition
Speech Translation
Audio Understanding