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
Keqi Deng — most-cited papers & profile · Speech Audio
← authors
·
overview
Keqi Deng
22
papers ·
45
citations ·
10
h-index
Microsoft (United States) · Institute of Technology of Cambodia · Xiamen University · University of Cambridge · Microsoft Research (United Kingdom)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
2022 · 24 citations
Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax
2023 · 9 citations
Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model
2021 · 6 citations
Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning
2021 · 4 citations
Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
2022 · 1 citations
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
2024 · 1 citations
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
2026
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
2026
OpenSTBench: Beyond Semantic Evaluation for Speech Translation
2026
UNIQUE: Universal Top-k Sparse Attention for Training-free Inference and Sparsity-aware Training
2026
Speech LLMs are Contextual Reasoning Transcribers
2026
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
2025
Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
2022
Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation
2022
Decoupled Structure for Improved Adaptability of End-to-End Models
2023
Top co-authors
Philip C. Woodland
· 8
Ruchao Fan
· 4
Gaofeng Cheng
· 3
Songjun Cao
· 3
Pengyuan Zhang
· 2
Rui Zhao
· 2
Shinji Watanabe
· 2
Xie Chen
· 2
Yike Zhang
· 2
Ziyang Ma
· 2
Ali Zare
· 1
Bing Qin
· 1
Topics
Speech Recognition
Speech Translation
Text-to-Speech
Multimodal Audio
Audio Understanding
Audio Generation
cs.CL
cs.DC
cs.LG