Takeharu Eda
4 papers · 2020–2025 · 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (17) π£ Hot Topic Early Bird
π
Keyword Champion
(2)
Venues
Top co-authors
Research topics
Deep Learning
(4)
Machine Learning
(3)
Application Areas
(3)
Artificial Intelligence
(2)
Core AI Β· Artificial Intelligence
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Speech & Audio
(1)
Architectures
(1)
Core AI Β· Computer Vision
(1)
Core Methods
(1)
Generation
(1)
Learning Types
(1)
Models
(1)
Recognition
(1)
Keywords
computational cost
(2)
knowledge transfer
(1)
data augmentation
(1)
prompt engineering
(1)
confidence calibration
(1)
neural network optimization
(1)
synthetic data generation
(1)
deep neural network
(1)
generative adversarial network
(1)
edge computing
(1)
multi-domain learning
(1)
inference accuracy
(1)
task-oriented dialog
(1)
joint goal accuracy
(1)
conformer model
(1)
streaming automatic speech recognition
(1)
chunked-context masking
(1)
real-time factor
(1)
cascade inference
(1)
dialog state tracking
(1)
Papers
Leveraging LLMs for Written to Spoken Style Data Transformation to Enhance Spoken Dialog State Tracking
Interspeech 2025
miniStreamer: Enhancing Small Conformer with Chunked-Context Masking for Streaming ASR Applications on the Edge
Interspeech 2023
Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems
AAAI 2021
Effective Data Augmentation with Multi-Domain Learning GANs
AAAI 2020