Naotaka Kawata
5 papers · 2024–2026 · 2 venues · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Venues
Top co-authors
Research topics
Keywords
speaker embedding
(2)
speaker diarization
(2)
sequential output modeling
(2)
overlapped speech
(2)
autoregressive model
(1)
vision-language model
(1)
zero-shot classification
(1)
audio-visual speech recognition
(1)
multi-talker speech recognition
(1)
active speaker detection
(1)
multi-talker automatic speech recognition
(1)
unified modeling
(1)
target-speaker enrollment
(1)
multi-talker speech
(1)
contrastive learning
(1)
token sequence modeling
(1)
speech separation
(1)
automatic speech recognition
(1)
geometric structure
(1)
Papers
Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models
AAAI 2026
SOMSRED-SVC: Sequential Output Modeling with Speaker Vector Constraints for Joint Multi-Talker Overlapped ASR and Speaker Diarization
Interspeech 2025
Unified Audio-Visual Modeling for Recognizing Which Face Spoke When and What in Multi-Talker Overlapped Speech and Video
Interspeech 2025
SOMSRED: Sequential Output Modeling for Joint Multi-talker Overlapped Speech Recognition and Speaker Diarization
Interspeech 2024
Unified Multi-Talker ASR with and without Target-speaker Enrollment
Interspeech 2024