Kazuhiro Nakadai
12 papers · 2016–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🌍 Conference Polyglot (3) 🏃 Academic Marathon (9) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (4)
🌍
Conference Polyglot
(3)
🏃
Academic Marathon
(9)
🧭
Keyword Pioneer
🧬
Topic Evolution
🔥
Unstoppable
(5)
📈
Trend Setter
💎
Century Club
(11)
🚀
Conference Pioneer
🗃️
Keyword Collector
(63)
Conferences
INTERSPEECH (8)
COLING (2)
AAAI (1)
ACL (1)
Top co-authors
Keywords
source separation
(2)
end-to-end speech recognition
(2)
deep neural network
(2)
sign language translation
(2)
connectionist temporal classification
(2)
streaming automatic speech recognition
(2)
sound source localization
(1)
signal processing
(1)
transfer learning
(1)
multilingual processing
(1)
multimodal learning
(1)
speech separation
(1)
sound localization
(1)
weakly-supervised learning
(1)
visual speech recognition
(1)
named entity recognition
(1)
audio source separation
(1)
acoustic model
(1)
latent variable model
(1)
attention mechanism
(1)
Papers
Unsupervised Single-Channel Audio Separation with Diffusion Source Priors
AAAI 2026
Improvement in Sign Language Translation Using Text CTC Alignment
COLING 2025
Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model
ACL 2025
SEDA: Simple and Effective Data Augmentation for Sign Language Understanding
COLING 2024
Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimation
INTERSPEECH 2023
miniStreamer: Enhancing Small Conformer with Chunked-Context Masking for Streaming ASR Applications on the Edge
INTERSPEECH 2023
Weakly-Supervised Neural Full-Rank Spatial Covariance Analysis for a Front-End System of Distant Speech Recognition
INTERSPEECH 2022
Empirical Sampling from Latent Utterance-wise Evidence Model for Missing Data ASR based on Neural Encoder-Decoder Model
INTERSPEECH 2022
Streaming Automatic Speech Recognition with Re-blocking Processing Based on Integrated Voice Activity Detection
INTERSPEECH 2022
Assessment of von Mises-Bernoulli Deep Neural Network in Sound Source Localization
INTERSPEECH 2021
Node Pruning Based on Entropy of Weights and Node Activity for Small-Footprint Acoustic Model Based on Deep Neural Networks
INTERSPEECH 2017
Localizing Bird Songs Using an Open Source Robot Audition System with a Microphone Array
INTERSPEECH 2016