pith. sign in

Tom Ko

Identifiers

  • name variant Tom Ko 0.60 · backfill

Papers (32)

  1. Controllable Accent Normalization via Discrete Diffusion eess.AS · 2026 · author #3
  2. Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent cs.CL · 2024 · author #3
  3. Learning Retrieval Augmentation for Personalized Dialogue Generation cs.CL · 2024 · author #5
  4. Selective Prompting Tuning for Personalized Conversations with LLMs cs.CL · 2024 · author #3
  5. Speech Translation with Large Language Models: An Industrial Practice cs.CL · 2023 · author #3
  6. RepCodec: A Speech Representation Codec for Speech Tokenization eess.AS · 2023 · author #3
  7. Recent Advances in Direct Speech-to-text Translation cs.CL · 2023 · author #5
  8. MOSPC: MOS Prediction Based on Pairwise Comparison cs.SD · 2023 · author #4
  9. PolyVoice: Language Models for Speech to Speech Translation cs.CL · 2023 · author #5
  10. CTC-based Non-autoregressive Speech Translation cs.CL · 2023 · author #8
  11. DUB: Discrete Unit Back-translation for Speech Translation cs.CL · 2023 · author #3
  12. WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research eess.AS · 2023 · author #5
  13. M3ST: Mix at Three Levels for Speech Translation cs.CL · 2022 · author #4
  14. Leveraging per Image-Token Consistency for Vision-Language Pre-training cs.CV · 2022 · author #2
  15. Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention eess.AS · 2022 · author #8
  16. Personalized Dialogue Generation with Persona-Adaptive Attention cs.CL · 2022 · author #3
  17. CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning cs.SD · 2022 · author #3
  18. A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis eess.AS · 2022 · author #2
  19. Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation cs.CL · 2022 · author #3
  20. GigaST: A 10,000-hour Pseudo Speech Translation Corpus cs.CL · 2022 · author #3
  21. Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data cs.SD · 2022 · author #6
  22. LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT eess.AS · 2022 · author #8
  23. SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing eess.AS · 2021 · author #8
  24. Multi-View Self-Attention Based Transformer for Speaker Recognition eess.AS · 2021 · author #6
  25. An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning eess.AS · 2021 · author #9
  26. CL4AC: A Contrastive Loss for Audio Captioning eess.AS · 2021 · author #4
  27. Token-Level Supervised Contrastive Learning for Punctuation Restoration cs.CL · 2021 · author #2
  28. Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation cs.CL · 2021 · author #4
  29. Auto-KWS 2021 Challenge: Task, Datasets, and Baselines cs.SD · 2021 · author #6
  30. AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification cs.AI · 2020 · author #2
  31. MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization cs.CV · 2020 · author #3
  32. An Investigation of Few-Shot Learning in Spoken Term Classification cs.CL · 2018 · author #2

Mentions

  • 2407.21646 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2309.00169 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2303.17395 #5 · arxiv_oai · confidence 0.70 Tom Ko
  • 2406.18847 #5 · arxiv_oai · confidence 0.70 Tom Ko
  • 2406.18187 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2210.15088 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2312.13585 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2211.15398 #2 · arxiv_oai · confidence 0.70 Tom Ko
  • 2210.04062 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2306.11646 #5 · arxiv_oai · confidence 0.70 Tom Ko
  • 2306.10493 #4 · arxiv_oai · confidence 0.70 Tom Ko
  • 2306.02982 #5 · arxiv_oai · confidence 0.70 Tom Ko
  • 2204.03939 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2210.16428 #8 · arxiv_oai · confidence 0.70 Tom Ko
  • 2305.17358 #8 · arxiv_oai · confidence 0.70 Tom Ko
  • 2305.11411 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2107.09099 #2 · arxiv_oai · confidence 0.70 Tom Ko
  • 2212.03657 #4 · arxiv_oai · confidence 0.70 Tom Ko
  • 2208.02189 #2 · arxiv_oai · confidence 0.70 Tom Ko
  • 2203.17113 #6 · arxiv_oai · confidence 0.70 Tom Ko
  • 2203.15610 #8 · arxiv_oai · confidence 0.70 Tom Ko
  • 2110.07205 #8 · arxiv_oai · confidence 0.70 Tom Ko
  • 2205.08993 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 2110.05036 #6 · arxiv_oai · confidence 0.70 Tom Ko
  • 2107.09990 #4 · arxiv_oai · confidence 0.70 Tom Ko
  • 2108.02752 #9 · arxiv_oai · confidence 0.70 Tom Ko
  • 2104.03815 #4 · arxiv_oai · confidence 0.70 Tom Ko
  • 2104.00513 #6 · arxiv_oai · confidence 0.70 Tom Ko
  • 2010.13130 #2 · arxiv_oai · confidence 0.70 Tom Ko
  • 2009.13735 #3 · arxiv_oai · confidence 0.70 Tom Ko
  • 1812.10233 #2 · arxiv_oai · confidence 0.70 Tom Ko
  • 2603.14275 #3 · arxiv_oai · confidence 0.70 Tom Ko

Frequent Coauthors