Tetsuji Ogawa 研究室

主宰者：Tetsuji Ogawa

早稲田大学

AI 要約（直近 5 年の研究成果）

本研究室は、音声・音響信号を対象とした機械学習に関する研究を展開しています。特に、リアルタイム音声認識、音声分離、話者判定・識別といった音声処理の基本的な課題に取り組んでいます。これらの研究では、Transformerなどのニューラルネットワークアーキテクチャを用いて、長時間の音声信号の構造を効果的に捉える手法を開発しています。音声認識の領域では、処理の遅延を最小化しながら高い精度を保つストリーミング処理の実現、および事前学習済み言語モデルとの統合を通じた認識精度の向上に注力しています。また音声分離では、ノイズ除去や残響除去、複数話者の分離と抽出を統合的に行うモデルの構築や、教師なし学習による改善手法を提案しています。さらに、話者判定や歌唱者認識など、音声の個人特性に関わる課題にも取り組んでいます。加えて、本研究室は音声以外の信号処理にも対象を拡げており、風力発電機の異常検知、ドローン画像からの建物検出、熱画像を用いた歩行パターン認識など、様々な実世界課題に機械学習手法を応用しています。これらの応用研究では、限られたデータでの学習、環境変動への頑健性、モデルの説明可能性といった実務的な課題の解決を重視しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（47 件）

[2026] Uncertainty-Based Streaming ASR With Evidential Deep Learning
DOI: https://doi.org/10.1109/ojsp.2026.3657308
[2026] A Dual-Model Deep Learning Framework with Consensus-Based Ensemble for Advanced Persistent Threat Detection in Industrial Internet of Things Networks
DOI: https://doi.org/10.1109/access.2026.3704915
[2025] End-to-End Speech Translation Guided by Robust Translation Capability of Large Language Model
DOI: https://doi.org/10.21437/interspeech.2025-317
[2025] Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition
DOI: https://doi.org/10.21437/interspeech.2025-2572
[2025] A Comparative Study on Positional Encoding for Time-Frequency Domain Dual-Path Transformer-Based Source Separation Models
DOI: https://doi.org/10.23919/eusipco63237.2025.11226241
[2025] Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model for Guiding End-to-End Speech Recognition
DOI: https://doi.org/10.1109/icassp49660.2025.10890174
[2025] Video-Based Vibration Analysis for Predictive Maintenance: A Motion Magnification and Random Forest Approach
DOI: https://doi.org/10.5220/0013715900003982
[2024] WindVibraTransformer: A Foundational Model for Precise and Robust Wind Turbine Condition Monitoring via Vibration Signals
DOI: https://doi.org/10.1109/icmla61862.2024.00101
[2024] Exploring Robust and Explainable Design for Facial Expression-Based Emotional State Estimation in Children with Profound Intellectual Multiple Disabilities
DOI: https://doi.org/10.23919/eusipco63174.2024.10715148
[2024] Normal with Occasional Anomalies: Feature Extraction for Detecting Non-Stationary Abnormal Events in Wind Turbines
DOI: https://doi.org/10.23919/eusipco63174.2024.10715327

続きを表示（残り 37 件）

[2024] Exploring Impact of Prioritizing Intra-Singer Acoustic Variations on Singer Embedding Extractor Construction for Singer Verification
DOI: https://doi.org/10.1109/o-cocosda64382.2024.10800601
[2024] Parody Detection Using Source-Target Attention with Teacher-Forced Lyrics
DOI: https://doi.org/10.1109/icassp48485.2024.10446577
[2023] A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, And Extraction
DOI: https://doi.org/10.1109/asru57964.2023.10389724
[2023] Learning Discriminative Feature Representations via Metric Learning for Early Operation of Wind Turbine Anomaly Detection Systems
DOI: https://doi.org/10.1109/icmla58977.2023.00197
[2023] Lightweight Multiscale Attention-Aware Method for Semantic Segmentation of Urban Structural Buildings in Drone Aerial Imagery
DOI: https://doi.org/10.1109/miucc58832.2023.10278371
[2023] Voice or Content? — Exploring Impact of Speech Content on Age Estimation from Voice
DOI: https://doi.org/10.23919/eusipco58844.2023.10290106
[2023] Spotting Parodies: Detecting Alignment Collapse Between Lyrics and Singing Voice
DOI: https://doi.org/10.23919/eusipco58844.2023.10290010
[2023] Mask-CTC-Based Encoder Pre-Training for Streaming End-to-End Speech Recognition
DOI: https://doi.org/10.23919/eusipco58844.2023.10290112
[2023] Thermal Gait Dataset for Deep Learning-Oriented Gait Recognition
DOI: https://doi.org/10.1109/ijcnn54540.2023.10191513
[2023] Narrow Down Forecast Range: Using Knowledge of Past Operations and Attribute-Dependent Thresholding in Good Fishing Ground Prediction
DOI: https://doi.org/10.1109/oceanslimerick52467.2023.10244346
[2023] BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder
DOI: https://doi.org/10.1109/icassp49357.2023.10095186
[2023] Neural Diarization with Non-Autoregressive Intermediate Attractors
DOI: https://doi.org/10.1109/icassp49357.2023.10094824
[2023] Self-Remixing: Unsupervised Speech Separation VIA Separation and Remixing
DOI: https://doi.org/10.1109/icassp49357.2023.10095596
[2023] Intermpl: Momentum Pseudo-Labeling With Intermediate CTC Loss
DOI: https://doi.org/10.1109/icassp49357.2023.10097071
[2023] Conversation-Oriented ASR with Multi-Look-Ahead CBS Architecture
DOI: https://doi.org/10.1109/icassp49357.2023.10094614
[2023] A Lightweight Transfer Learning-Based Model for Building Classification in Aerial Imagery
DOI: https://doi.org/10.1109/iccrd56364.2023.10080643
[2023] Self-Conditioning via Intermediate Predictions for End-to-End Neural Speaker Diarization
DOI: https://doi.org/10.1109/access.2023.3340307
[2023] Masry: A Text-to-Speech System for the Egyptian Arabic
DOI: https://doi.org/10.5220/0012244300003543
[2022] PostMe: Unsupervised Dynamic Microtask Posting For Efficient and Reliable Crowdsourcing
DOI: https://doi.org/10.1109/bigdata55660.2022.10020590
[2022] Refinement of Utterance Fluency Feature Extraction and Automated Scoring of L2 Oral Fluency with Dialogic Features
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980148
[2022] Inlier Modeling-Based Good Fishing Ground Detection for Efficient Bullet Tuna Trolling Using Meteorological and Oceanographic Information
DOI: https://doi.org/10.1109/oceanschennai45887.2022.9775305
[2022] Do You Know How Humans Sound? Exploring a Qualification Test Design for Crowdsourced Evaluation of Voice Synthesis Quality
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9979812
[2022] Design of Discriminators in GAN-Based Unsupervised Learning of Neural Post-Processors for Suppressing Localized Spectral Distortion
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9979833
[2022] Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
DOI: https://doi.org/10.1109/icassp43922.2022.9746580
[2022] Remix-Cycle-Consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation
DOI: https://doi.org/10.1109/icassp43922.2022.9746655
[2022] Sequential Fish Catch Counter Using Vision-based Fish Detection and Tracking
DOI: https://doi.org/10.1109/oceanschennai45887.2022.9775327
[2021] Multi-Source Domain Generalization Using Domain Attributes for Recurrent Neural Network Language Models
DOI: https://doi.org/10.1587/transinf.2021edp7081
[2021] VocalTurk: Exploring Feasibility of Crowdsourced Speaker Identification
DOI: https://doi.org/10.21437/interspeech.2021-464
[2021] Efficient and Stable Adversarial Learning Using Unpaired Data for Unsupervised Multichannel Speech Separation
DOI: https://doi.org/10.21437/interspeech.2021-523
[2021] Improved Mask-CTC for Non-Autoregressive End-to-End ASR
DOI: https://doi.org/10.1109/icassp39728.2021.9414198
[2021] Analysis of Multimodal Features for Speaking Proficiency Scoring in an Interview Dialogue
DOI: https://doi.org/10.1109/slt48900.2021.9383590
[2021] Scrambling Parameter Generation to Improve Perceptual Information Hiding
DOI: https://doi.org/10.2352/issn.2470-1173.2021.11.hvei-155
[2021] Feature Representation Learning for Calving Detection of Cows Using Video Frames
DOI: https://doi.org/10.1109/icpr48806.2021.9413019
[2021] Crowdsourced Verification for Operating Calving Surveillance Systems at an Early Stage
DOI: https://doi.org/10.1109/icpr48806.2021.9412488
[2021] Toward Building a Data-Driven System For Detecting Mounting Actions of Black Beef Cattle
DOI: https://doi.org/10.1109/icpr48806.2021.9412975
[2021] SIA-GAN: Scrambling Inversion Attack Using Generative Adversarial Network
DOI: https://doi.org/10.1109/access.2021.3112684
[2021] Actual State of Information Needs and Communication in Large Disaster Areas: A Case Study of Tomioka Town

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（47 件）

科研費（0 件）

所属学会・役職（0 件）