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
Roman Koshkin — most-cited papers & profile · Speech Audio
← authors
·
overview
Roman Koshkin
6
papers ·
0
citations ·
3
h-index
Okinawa Institute of Science and Technology Graduate University · Intuit (United States)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
2026
Distilling LLM Semantic Priors into Encoder-Only Multi-Talker ASR with Talker-Count Routing
2026
Streaming Translation and Transcription Through Speech-to-Text Causal Alignment
2026
Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
2026
SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation
2025
Top co-authors
Hao Shi
· 4
Lianbo Liu
· 4
Mengjie Zhao
· 4
Yui Sudo
· 4
Yusuke Fujita
· 4
Yuan Gao
· 3
Haesung Jeon
· 1
Jeon Haesung
· 1
Kai Washizaki
· 1
Lai Wei
· 1
Nao Yoshida
· 1
Reo Yoneyama
· 1
Topics
Speech Recognition
Text-to-Speech
Speech Translation
Audio Generation