Awesome Speech Audio
Papers
Topics
Trending
Leaderboards
Authors
Datasets
Learn
Ask AI
Map
Tools
Packs
News
Videos
All sections
Browse
Papers
The full index, filterable and sortable.
Topics
The same papers grouped by subject tag.
Trending
What moved this week, and by how much.
Authors
Who publishes here, and who they publish with.
Map
The collection laid out by embedding similarity.
Compare
Leaderboards
Benchmark tables, with the paper behind each number.
Datasets
The datasets these papers train and evaluate on.
Tools
Code and libraries released alongside the papers.
Read
Learn
Ordered routes from background reading to current work.
Ask AI
Ask a question and get answers cited to these papers.
Videos
The most-watched talks and lectures in this field.
Packs
Short curated sets built around one question.
Follow
News
Press and coverage tied back to the papers.
Blogs
Author and lab write-ups of their own work.
Newsletter
Email digest of what changed, on a schedule.
Research Radar
Paste an abstract, get matches across every collection.
Yours
Saved
Papers you bookmarked in this browser.
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
Ask AI
Yeyun Gong — most-cited papers & profile · Speech Audio
← authors
·
overview
Yeyun Gong
39
papers ·
57
citations ·
28
h-index
Microsoft Research Asia (China)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection
2025
FastSeq: Make Sequence Generation Faster
2021
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation
2022
A Self-Paced Mixed Distillation Method for Non-Autoregressive Generation
2022
P³LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training
2022
Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
2022
PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization
2023
Enhancing Large Language Model Performance with Gradient-Based Parameter Selection
2024
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training
2024
Top co-authors
Nan Duan
· 5
Peng Cheng
· 3
Weizhu Chen
· 3
Xiao Liu
· 3
Haoling Li
· 2
Weizhen Qi
· 2
Xin Zhang
· 2
Yelong Shen
· 2
Yifan Wang
· 2
Yu Yan
· 2
Zhenghao Lin
· 2
Bartuer Zhou
· 1
Topics
cs.CL
cs.AI
cs.LG