pith. sign in

Tetsuji Ogawa

Identifiers

  • name variant Tetsuji Ogawa 0.60 · backfill

Papers (22)

  1. Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition eess.AS · 2025 · author #6
  2. A Comparative Study on Positional Encoding for Time-frequency Domain Dual-path Transformer-based Source Separation Models eess.AS · 2025 · author #2
  3. End-to-End Speech Recognition with Pre-trained Masked Language Model eess.AS · 2024 · author #2
  4. A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and Extraction eess.AS · 2023 · author #6
  5. Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition eess.AS · 2023 · author #2
  6. Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition cs.SD · 2023 · author #4
  7. Remixing-based Unsupervised Source Separation from Scratch eess.AS · 2023 · author #2
  8. Neural Diarization with Non-autoregressive Intermediate Attractors eess.AS · 2023 · author #5
  9. Video Surveillance System Incorporating Expert Decision-making Process: A Case Study on Detecting Calving Signs in Cattle cs.HC · 2023 · author #6
  10. Deep Multi-stream Network for Video-based Calving Sign Detection cs.CV · 2023 · author #3
  11. Self-Remixing: Unsupervised Speech Separation via Separation and Remixing eess.AS · 2022 · author #2
  12. Conversation-oriented ASR with multi-look-ahead CBS architecture cs.SD · 2022 · author #3
  13. InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss eess.AS · 2022 · author #2
  14. BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder eess.AS · 2022 · author #2
  15. BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model eess.AS · 2022 · author #4
  16. Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation eess.AS · 2022 · author #2
  17. An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR cs.SD · 2021 · author #3
  18. Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units eess.AS · 2021 · author #3
  19. Exploring Effectiveness of Inter-Microtask Qualification Tests in Crowdsourcing cs.HC · 2020 · author #5
  20. Improved Mask-CTC for Non-Autoregressive End-to-End ASR eess.AS · 2020 · author #4
  21. Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict eess.AS · 2020 · author #4
  22. Block-wise Scrambled Image Recognition Using Adaptation Network cs.CV · 2020 · author #4

Mentions

  • 2506.07515 #6 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2504.19605 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2309.10524 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2410.00528 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2310.08277 #6 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2309.04654 #4 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2309.00376 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2211.10194 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2210.16663 #4 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2211.00795 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2211.00792 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2303.06806 #5 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2302.08493 #3 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2301.03926 #6 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2211.00858 #3 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2203.14080 #2 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2110.04109 #3 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2110.10402 #3 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2010.13270 #4 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2012.10999 #5 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2005.08700 #4 · arxiv_oai · confidence 0.70 Tetsuji Ogawa
  • 2001.07761 #4 · arxiv_oai · confidence 0.70 Tetsuji Ogawa

Frequent Coauthors