Takeharu Eda
3 papers · 2020–2023 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (2) π Cross-Pollinator (4) π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(15)
π£
Hot Topic Early Bird
Conferences
AAAI (2)
INTERSPEECH (1)
Top co-authors
Keywords
computational cost
(2)
knowledge transfer
(1)
data augmentation
(1)
confidence calibration
(1)
neural network optimization
(1)
deep neural network
(1)
generative adversarial network
(1)
edge computing
(1)
multi-domain learning
(1)
inference accuracy
(1)
conformer model
(1)
streaming automatic speech recognition
(1)
chunked-context masking
(1)
real time factor
(1)
cascade inference
(1)
neural network
(1)
image classification
(1)
domain fusion
(1)
Papers
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