Tetsuji Ogawa
14 papers · 2019–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Conference Polyglot (3) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Academic Marathon (5)
π
Cross-Pollinator
(6)
πΊοΈ
Taxonomy Completionist
(27)
π
Renaissance Researcher
(5)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(68)
β
The Questioner
π
Trend Setter
π₯
Unstoppable
(6)
π
Century Club
(14)
Conferences
INTERSPEECH (12)
COLING (1)
EMNLP (1)
Top co-authors
Keywords
end-to-end speech recognition
(4)
connectionist temporal classification
(4)
unsupervised learning
(3)
multi-task learning
(2)
blind source separation
(2)
speaker identification
(2)
hierarchical learning
(1)
speech recognition
(1)
text classification
(1)
knowledge transfer
(1)
crowdsourced labeling
(1)
masked language model
(1)
automatic speech recognition
(1)
adversarial training
(1)
self-supervised learning
(1)
audio source separation
(1)
source separation
(1)
speech enhancement
(1)
spoken language understanding
(1)
speech separation
(1)
Papers
Hierarchical Multi-Task Learning with CTC and Recursive Operation
INTERSPEECH 2024
Remixing-based Unsupervised Source Separation from Scratch
INTERSPEECH 2023
Unsupervised Training of Sequential Neural Beamformer Using Coarsely-separated and Non-separated Signals
INTERSPEECH 2022
Text-Only Domain Adaptation Based on Intermediate CTC
INTERSPEECH 2022
Can Humans Correct Errors From System? Investigating Error Tendencies in Speaker Identification Using Crowdsourcing
INTERSPEECH 2022
Confusion Detection for Adaptive Conversational Strategies of An Oral Proficiency Assessment Interview Agent
INTERSPEECH 2022
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
EMNLP 2022
Efficient and Stable Adversarial Learning Using Unpaired Data for Unsupervised Multichannel Speech Separation
INTERSPEECH 2021
VocalTurk: Exploring Feasibility of Crowdsourced Speaker Identification
INTERSPEECH 2021
Exploiting Narrative Context and A Priori Knowledge of Categories in Textual Emotion Classification
COLING 2020
Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
INTERSPEECH 2020
Mentoring-Reverse Mentoring for Unsupervised Multi-Channel Speech Source Separation
INTERSPEECH 2020
Speaker Adversarial Training of DPGMM-Based Feature Extractor for Zero-Resource Languages
INTERSPEECH 2019
Multi-Channel Speech Enhancement Using Time-Domain Convolutional Denoising Autoencoder
INTERSPEECH 2019