Haobin Tang

Haobin Tang

University of Science and Technology of China

Haobin Tang is currently a speech algorithm engineer at Taotian Co., Ltd. in Hangzhou. He was a graduate student at the University of Science and Technology of China (USTC) and previously worked as an intern at PAT (Shenzhen) Co., Ltd. He was selected to participate in the joint cultivation laboratory program between PAT (Shenzhen) Co., Ltd and USTC for the class of 2021. His research interests focus on expressive speech synthesis and automatic speech recognition.

Interests
  • Expressive TTS
  • ASR

Publications

  1. ED-TTS: Multi-Scale Emotion Modeling Using Cross-Domain Emotion Diarization for Emotional Speech Synthesis, (2024), †First Author, In ICASSP2024 (CCF-B)
  2. EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis, (2023), †First Author, In INTERSPEECH2023 (CCF-C)
  3. SAR: Self-Supervised Anti-Distortion Representation for End-To-End Speech Model (2023), In IJCNN2023 (CCF-C)
  4. Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy, (2023), ‡Co-first Author, In ICASSP2023 (CCF-B)
  5. QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis, (2023), †First Author, In ICASSP2023 (CCF-B)
  6. Speech Augmentation Based Unsupervised Learning for Keyword Spotting (2022), In IJCNN2022 (CCF-C)

中文期刊文章

  1. 表现性语音合成综述, (2023), †First Author, 《大数据》,9 (06),（CCF-T2）