Satoshi Suzuki
10 papers · 2022–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (5) π Renaissance Researcher (6)
πΊοΈ
Taxonomy Completionist
(24)
π€
Dynamic Duo
(10)
π₯
Unstoppable
(5)
π
Century Club
(10)
ποΈ
Keyword Collector
(58)
Conferences
INTERSPEECH (5)
AAAI (2)
ICCV (2)
WACV (1)
Top co-authors
Research topics
Keywords
automatic speech recognition
(4)
autoregressive model
(2)
multi-talker speech
(2)
multi-talker speech recognition
(2)
overlapped speech
(2)
joint modeling
(2)
autoregressive modeling
(2)
knowledge distillation
(1)
attention mechanism
(1)
contrastive learning
(1)
bird's eye view
(1)
object tracking
(1)
fine-grained classification
(1)
adversarial training
(1)
label distribution learning
(1)
model robustness
(1)
deep neural network
(1)
trajectory prediction
(1)
fine-grained recognition
(1)
geometric structure
(1)
Papers
Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models
AAAI 2026
Distribution Highlighted Reference-based Label Distribution Learning for Facial Age Estimation
WACV 2026
Multimodal Fine-Grained Apparent Personality Trait Recognition: Joint Modeling of Big Five and Questionnaire Item-level Scores
AAAI 2025
MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost
ICCV 2025
Unified Multi-Talker ASR with and without Target-speaker Enrollment
INTERSPEECH 2024
End-to-End Joint Target and Non-Target Speakers ASR
INTERSPEECH 2023
Joint Autoregressive Modeling of End-to-End Multi-Talker Overlapped Speech Recognition and Utterance-level Timestamp Prediction
INTERSPEECH 2023
Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff
ICCV 2023
End-to-End Joint Modeling of Conversation History-Dependent and Independent ASR Systems with Multi-History Training
INTERSPEECH 2022
Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data
INTERSPEECH 2022