pith. sign in

Shiyin Kang

Identifiers

  • name variant Shiyin Kang 0.60 · backfill

Papers (30)

  1. SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis eess.AS · 2026 · author #9
  2. How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue cs.CL · 2026 · author #5
  3. StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model cs.SD · 2026 · author #10
  4. Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-trained BERT eess.AS · 2025 · author #3
  5. An End-to-End Approach for Chord-Conditioned Song Generation cs.SD · 2024 · author #8
  6. SongCreator: Lyrics-based Universal Song Generation cs.SD · 2024 · author #8
  7. Foundation Models for Music: A Survey cs.SD · 2024 · author #30
  8. ChatMusician: Understanding and Generating Music Intrinsically with LLM cs.SD · 2024 · author #34
  9. SCNet: Sparse Compression Network for Music Source Separation eess.AS · 2024 · author #4
  10. Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generation cs.SD · 2024 · author #8
  11. AdaMesh: Personalized Facial Expressions and Head Poses for Adaptive Speech-Driven 3D Facial Animation cs.CV · 2023 · author #6
  12. Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts cs.SD · 2023 · author #7
  13. Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information cs.SD · 2023 · author #7
  14. Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis cs.SD · 2023 · author #6
  15. Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information cs.SD · 2023 · author #5
  16. MSStyleTTS: Multi-Scale Style Modeling with Hierarchical Context Information for Expressive Speech Synthesis cs.SD · 2023 · author #6
  17. GTN-Bailando: Genre Consistent Long-Term 3D Dance Generation based on Pre-trained Genre Token Network cs.SD · 2023 · author #8
  18. CB-Conformer: Contextual biasing Conformer for biased word recognition cs.SD · 2023 · author #6
  19. Context-aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook Speech Synthesis cs.SD · 2023 · author #5
  20. Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis cs.SD · 2022 · author #6
  21. Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion cs.SD · 2022 · author #5
  22. Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis cs.SD · 2022 · author #5
  23. FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement cs.SD · 2022 · author #5
  24. VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis cs.SD · 2021 · author #5
  25. Adversarially learning disentangled speech representations for robust multi-factor voice conversion eess.AS · 2021 · author #5
  26. Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams eess.AS · 2020 · author #3
  27. Transferring Source Style in Non-Parallel Voice Conversion eess.AS · 2020 · author #3
  28. Audio-visual Recognition of Overlapped speech for the LRS2 dataset eess.AS · 2020 · author #6
  29. DurIAN: Duration Informed Attention Network For Multimodal Synthesis cs.CL · 2019 · author #9
  30. Maximizing Mutual Information for Tacotron eess.AS · 2019 · author #3

Mentions

  • 2604.19635 #10 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2310.07236 #6 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2501.01102 #3 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2409.06029 #8 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2409.06307 #8 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2408.14340 #30 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2309.11977 #7 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2402.16153 #34 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2401.13276 #4 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2401.07532 #8 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2308.16836 #7 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2308.16593 #6 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2308.16577 #5 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2307.16012 #6 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2304.12704 #8 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2304.09607 #6 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2304.06359 #5 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2204.02743 #6 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2203.12201 #5 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2203.12188 #5 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2203.12813 #5 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2102.00184 #5 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2107.03298 #5 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2006.11610 #3 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2005.09178 #3 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2001.01656 #6 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 1909.01145 #3 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 1909.01700 #9 · arxiv_oai · confidence 0.70 Shiyin Kang
  • 2605.16964 #9 · arxiv_oai · confidence 0.70 Shiyin Kang

Frequent Coauthors