음성·오디오, 학회
INTERSPEECH 논문을 낸 국내 연구실
탑티어INTERSPEECH. 2023년 이후 논문 184편, 연구실 43곳
이 학회에 논문을 낸 연구실
| 연구실 | 대학 | 탑티어 논문 | 전체 논문 | 구성원 | 비교 |
|---|---|---|---|---|---|
 Smart sound systems최정우 교수 | KAIST | 3 | 3 | 15 | |
 Statistical Artificial Intelligence Lab최재식 교수모집 안내 | KAIST | 28 | 43 | 3 | |
 Ubiquitous AI Lab. 유비쿼터스 인공지능 연구실공태식 교수신생 랩모집 안내 | UNIST | 13 | 21 | 5 |
최근 논문
- GETS: Guiding EMG-to-Speech Synthesis via Silent Speech Recognition
2026, 이교구 연구실
- K-DIALECT : Korean Dialect-Aware Face-Based Speech Synthesis
2026, Data eXperience Laboratory
- Latency-Configurable Streaming Speech Enhancement via Asymmetric Temporal Padding
2026, 지능형 반도체 및 웨어러블 디바이스
- L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification
2026, 패턴인식 및 머신러닝 연구실
- MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis
2026, 멀티모달 인공지능 연구실
- MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
2026, Smart sound systems
- MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling
2026, Music and Audio Computing Lab
- MF-EDM: Graph-based Multimodal Fusion and Emotional Dynamics Modeling for Emotion Recognition in Conversation
2026, 권가진 연구실
- NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation
2026, 인공지능 연구실
- ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge
2026, 기계 인지 및 추론 연구실
- Physics-Aware Deepfake Detection via Distance-Speech Consistency
2026, 기계 지능 연구실
- Plug-and-Steer: Decoupling Separation and Selection in Audio-Visual Target Speaker Extraction
2026, 멀티모달 인공지능 연구실
- ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion
2026, 멀티모달 인공지능 연구실
- Real-Time Speech Enhancement on Edge Devices Guided by Harmonic and Voice-Activity Cues Utilizing Skin-Attachable Accelerometer
2026, 지능형 반도체 및 웨어러블 디바이스
- Revisiting Label-Free Speaker Embedding Enhancement with vMF Profile Likelihood
2026, 강명주 연구실
- Robust Multi-Source-Free Domain Adaptation via Posterior Adjustment and Label Agreement
2026, 데이터 마이닝 연구실
- SCOLoRA: Similarity Conditioned Signed Orthogonal LoRA for Continual Speaker Adaptation
2026, 음성음향신호처리 및 머신러닝 연구실
- SDP-Codec: A Speaker-Decoupled Speech Codec with Pitch Injection for Low-Bitrate Coding and Zero-Shot Voice Conversion
2026, Music and Audio Computing Lab
- Segment-level Tree Search for Long Meeting Document Summarization
2026, Machine Learning Lab, Machine Learning Lab, Machine Learning Lab
- SISER: Speaker-Invariant Speech Emotion Recognition with Entropy-Based Adversarial Training
2026, SLP Lab.(Speech and Language Processing Lab)