pith. sign in

Mark Hasegawa-Johnson

Identifiers

  • name variant Mark Hasegawa-Johnson 0.60 · backfill

Papers (21)

  1. SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment eess.AS · 2026 · author #2
  2. Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding cs.CV · 2026 · author #6
  3. FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations eess.AS · 2026 · author #5
  4. PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning cs.CL · 2026 · author #6
  5. Few-Shot Accent Synthesis for ASR with LLM-Guided Phoneme Editing cs.SD · 2026 · author #3
  6. In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions eess.AS · 2026 · author #4
  7. Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech eess.AS · 2026 · author #5
  8. MetaSICL: Adapting Audiroty LLM via Meta Speech In-Context Learning cs.SD · 2026 · author #4
  9. AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss eess.AS · 2019 · author #5
  10. When CTC Training Meets Acoustic Landmarks eess.AS · 2018 · author #5
  11. Improved ASR for Under-Resourced Languages Through Multi-Task Learning with Acoustic Landmarks cs.CL · 2018 · author #4
  12. Bayesian Models for Unit Discovery on a Very Low Resource Language cs.CL · 2018 · author #5
  13. Deep Learning Based Speech Beamforming cs.CL · 2018 · author #6
  14. Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop cs.CL · 2018 · author #4
  15. Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition cs.CL · 2018 · author #6
  16. Acoustic Landmarks Contain More Information About the Phone String than Other Frames for Automatic Speech Recognition with Deep Neural Network Acoustic Model eess.AS · 2017 · author #4
  17. Dilated Recurrent Neural Networks cs.AI · 2017 · author #9
  18. Performance Improvements of Probabilistic Transcript-adapted ASR with Recurrent Neural Network and Language-specific Constraints cs.CL · 2016 · author #3
  19. Landmark-based consonant voicing detection on multilingual corpora cs.CL · 2016 · author #3
  20. Semantic Image Inpainting with Deep Generative Models cs.CV · 2016 · author #5
  21. Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation cs.SD · 2015 · author #3

Mentions

  • 2606.02615 #5 · arxiv_oai · confidence 0.70 Mark Hasegawa-Johnson
  • 1502.04149 #3 · backfill · confidence 0.70 Mark Hasegawa-Johnson
  • 2606.02220 #2 · arxiv_oai · confidence 0.70 Mark Hasegawa-Johnson
  • 2606.00564 #6 · arxiv_oai · confidence 0.70 Mark Hasegawa-Johnson
  • 2601.18904 #4 · arxiv_oai · confidence 0.70 Mark Hasegawa-Johnson

Frequent Coauthors