pith. sign in

Takafumi Moriya

Identifiers

  • name variant Takafumi Moriya 0.60 · backfill

Papers (33)

  1. Progressive Alignment Objectives for Aligner-Encoder based ASR eess.AS · 2026 · author #3
  2. Chunkwise Aligners for Streaming Speech Recognition eess.AS · 2026 · author #2
  3. Generic Speech Enhancement with Self-Supervised Representation Space Loss eess.AS · 2025 · author #4
  4. Microphone Array Geometry Independent Multi-Talker Distant ASR: NTT System for the DASR Task of the CHiME-8 Challenge eess.AS · 2025 · author #7
  5. Guided Speaker Embedding eess.AS · 2024 · author #2
  6. Investigation of Speaker Representation for Target-Speaker Speech Processing cs.SD · 2024 · author #2
  7. Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding eess.AS · 2024 · author #1
  8. Alignment-Free Training for Transducer-based Multi-Talker ASR eess.AS · 2024 · author #1
  9. NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge eess.AS · 2024 · author #7
  10. Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings eess.AS · 2024 · author #3
  11. Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation cs.CL · 2024 · author #3
  12. SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling eess.AS · 2024 · author #2
  13. Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over eess.AS · 2024 · author #5
  14. Factor-Conditioned Speaking-Style Captioning cs.CL · 2024 · author #2
  15. What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis cs.CL · 2024 · author #3
  16. Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters cs.SD · 2024 · author #6
  17. Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition eess.AS · 2023 · author #2
  18. SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge? cs.CL · 2023 · author #2
  19. Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization cs.CL · 2023 · author #3
  20. End-to-End Joint Target and Non-Target Speakers ASR cs.CL · 2023 · author #13
  21. Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data eess.AS · 2023 · author #1
  22. Improving Scheduled Sampling for Neural Transducer-based ASR eess.AS · 2023 · author #1
  23. Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss eess.AS · 2023 · author #5
  24. Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models cs.CL · 2023 · author #2
  25. Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model cs.SD · 2023 · author #4
  26. Leveraging Large Text Corpora for End-to-End Speech Summarization cs.CL · 2023 · author #3
  27. On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis cs.CL · 2022 · author #7
  28. Streaming Target-Speaker ASR with Neural Transducer eess.AS · 2022 · author #1
  29. Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models cs.CL · 2022 · author #2
  30. Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations eess.AS · 2022 · author #5
  31. Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition eess.AS · 2022 · author #6
  32. Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition cs.CL · 2021 · author #5
  33. Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition eess.AS · 2021 · author #5

Mentions

  • 2507.07631 #4 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2502.09859 #7 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2410.12182 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2410.11243 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2409.20313 #1 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2409.20301 #1 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2409.05554 #7 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2408.17142 #3 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2306.08374 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2408.00205 #3 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2407.01857 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2406.18972 #5 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2406.18910 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2401.17632 #3 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2401.05111 #6 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2310.11010 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2304.11976 #4 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2306.04233 #3 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2306.02273 #13 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2305.15971 #1 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2305.15958 #1 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2305.14723 #5 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2305.05201 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2303.00978 #3 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2210.15937 #7 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2209.04175 #1 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2207.06867 #2 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2206.08174 #5 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2201.03881 #6 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2106.00949 #5 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2107.01569 #5 · arxiv_oai · confidence 0.70 Takafumi Moriya
  • 2606.24147 #3 · arxiv_oai · confidence 0.70 Takafumi Moriya

Frequent Coauthors