Skip to content
conftrace_

Seungjin Lee

4 papers · 2023–2025 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 📈 Trend Setter

Venues

Interspeech (4)

Top co-authors

Jaeyoung Roh (2) Youngmoon Jung (2) Chang Woo Han (1) WooSeok Shin (1) Sung Won Han (1) Keunseok Cho (1) Jin Sob Kim (1) Joon-Young Yang (1) Dongwon Kim (1) Changwoo Han (1)

Research topics

Deep Learning (4) Speech & Audio (4) Learning Types · Deep Learning (4) Machine Learning (3) Recognition (3) Artificial Intelligence (2) Core AI (2) Core Methods (2) Learning Types · Machine Learning (2) Architectures (1) Synthesis (1)

Keywords

keyword spotting (2) multi-task learning (1) transfer learning (1) embedding space (1) automatic speech recognition (1) open-vocabulary recognition (1) connectionist temporal classification (1) deep metric learning (1) mixture of expert (1) audio captioning (1) speech translation (1) speech representation (1) auxiliary learning (1) attention pooling (1) streaming speech recognition (1) streaming recognition (1) audio-text embedding (1) proxy loss (1) audio-text matching (1) relational proxy (1)

Papers

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Interspeech 2025 CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting Interspeech 2024 Relational Proxy Loss for Audio-Text based Keyword Spotting Interspeech 2024 Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer Interspeech 2023