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
Keunwoo Choi — most-cited papers & profile · Speech Audio
← authors
·
overview
Keunwoo Choi
19
papers ·
608
citations ·
20
h-index
University of Seoul
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Automatic tagging using deep convolutional neural networks
2016 · 223 citations
Transfer learning for music classification and regression tasks
2017 · 126 citations
Text-based LSTM networks for Automatic Music Composition
2016 · 75 citations
Convolutional Recurrent Neural Networks for Music Classification
2016 · 58 citations
Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras
2017 · 58 citations
Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation
2021 · 38 citations
Semi-Supervised Music Tagging Transformer
2021 · 13 citations
Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions
2016 · 7 citations
DLR : Toward a deep learned rhythmic representation for music content analysis
2017 · 6 citations
Listen, Read, and Identify: Multimodal Singing Language Identification of Music
2021 · 3 citations
Dereverberation using joint estimation of dry speech signal and acoustic system
2020 · 1 citations
MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation
2022
Toward Universal Text-to-Music Retrieval
2022
Textless Speech-to-Music Retrieval Using Emotion Similarity
2023
Top co-authors
Mark Sandler
· 4
George Fazekas
· 3
Minz Won
· 3
Juhan Nam
· 2
Kyunghyun Cho
· 2
SeungHeon Doh
· 2
and George Fazekas
· 1
and Kyogu Lee
· 1
Ben Sangbae Chon
· 1
Chang-Bin Jeon
· 1
Deokjin Joo
· 1
György Fazekas
· 1
Topics
Audio Understanding
Music Generation
Audio Generation
Multimodal Audio
Text-to-Speech
Speech Enhancement
Speech Recognition