Skip to content

@thuhcsi THUHCSI

Change the repository type filter

All

    Repositories list

    93 repositories

    • SpeechCraft

      Public
      The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.
      Python
      •7•183•5•0•Updated Feb 4, 2026Feb 4, 2026

    • Melos

      Public
      Melos: Sentence-to-section Training with Multi-task Learning for LLM-Driven Song Generation
      JavaScript
      •0•0•0•0•Updated Jan 30, 2026Jan 30, 2026

    • HASap

      Public
      Official repository for HASAP: HASap: Hierarchical Acoustic-Semantic Annotation Pipeline for Scripted Speech Data
      Python
      •0•0•0•0•Updated Jan 28, 2026Jan 28, 2026

    • thuhcsi.github.io

      Public
      https://thuhcsi.github.io/
      HTML
      •
      Other
      •2•4•0•0•Updated Sep 20, 2025Sep 20, 2025

    • icme2025-AutoStyle-TTS

      Public
      AutoStyle-TTS:Retrieval-Augmented Generation based Automatic Style Matching Text-to-Speech Synthesis
      JavaScript
      •1•0•0•0•Updated Jun 26, 2025Jun 26, 2025

    • icme2025-MMTTS

      Public
      HTML
      •1•0•0•0•Updated Jun 25, 2025Jun 25, 2025

    • AdaMesh

      Public
      Python
      •2•18•2•0•Updated Jun 14, 2025Jun 14, 2025

    • StarVC

      Public
      HTML
      •0•0•0•0•Updated May 28, 2025May 28, 2025

    • WAKE

      Public
      Python
      •2•10•2•0•Updated May 28, 2025May 28, 2025

    • interspeech2025-SSD

      Public
      HTML
      •
      MIT License
      •0•0•0•0•Updated May 20, 2025May 20, 2025

    • PerTTS

      Public
      HTML
      •0•0•0•0•Updated Mar 10, 2025Mar 10, 2025

    • TES-VC

      Public template
      Create a site or blog from your GitHub repositories with GitHub Pages.
      JavaScript
      •
      MIT License
      •9.1k•0•0•0•Updated Mar 1, 2025Mar 1, 2025

    • NeuFA

      Public
      Neural network-based forced alignment with bidirectional attention mechanism
      Python
      •8•78•5•0•Updated Jan 17, 2025Jan 17, 2025

    • dpss-exp3-VC-BNF

      Public
      Voice Conversion Experiments for THUHCSI Course : <Digital Processing of Speech Signals>
      Python
      •10•18•0•0•Updated Nov 27, 2024Nov 27, 2024

    • VoxInstruct

      Public
      VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
      Python
      •
      MIT License
      •6•96•4•0•Updated Nov 9, 2024Nov 9, 2024

    • CoVoC2024

      Public
      HTML
      •0•0•0•0•Updated Nov 6, 2024Nov 6, 2024

    • dpss-exp2-HMM

      Public
      ex2 for dpss
      Python
      •1•7•0•0•Updated Nov 5, 2024Nov 5, 2024

    • SongCreator

      Public
      JavaScript
      •0•0•1•0•Updated Oct 30, 2024Oct 30, 2024

    • MagicMan

      Public
      Official repository for paper "MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement"
      Python
      •
      MIT License
      •12•319•6•1•Updated Sep 16, 2024Sep 16, 2024

    • BinaryAUD

      Public
      HTML
      •0•0•0•0•Updated Sep 10, 2024Sep 10, 2024

    • mst-fastspeech2

      Public
      Python
      •
      MIT License
      •1•4•0•0•Updated Jul 29, 2024Jul 29, 2024

    • SECap

      Public
      Python
      •12•177•3•0•Updated Jul 9, 2024Jul 9, 2024

    • S2G-MDDiffusion

      Public
      Python
      •
      MIT License
      •7•133•4•0•Updated Jul 8, 2024Jul 8, 2024

    • interspeech2024-CSG

      Public
      Please visit https://thuhcsi.github.io/interspeech2024-CSG
      SCSS
      •
      Creative Commons Zero v1.0 Universal
      •1•0•0•0•Updated Jun 12, 2024Jun 12, 2024

    • interspeech2024-SponLMTTS

      Public
      HTML
      •0•0•0•0•Updated Jun 12, 2024Jun 12, 2024

    • NeuCoSVC

      Public
      Python
      •43•298•4•0•Updated May 22, 2024May 22, 2024

    • SCNet

      Public
      Python
      •
      MIT License
      •1•9•1•0•Updated Apr 18, 2024Apr 18, 2024

    • secap_slate

      Public
      SCSS
      •
      Creative Commons Zero v1.0 Universal
      •0•0•0•0•Updated Jan 5, 2024Jan 5, 2024

    • secap_demo

      Public
      SCSS
      •
      Creative Commons Zero v1.0 Universal
      •0•0•0•0•Updated Jan 5, 2024Jan 5, 2024

    • icassp2023-coherent-tts

      Public
      Please visit https://thuhcsi.github.io/icassp2023-coherent-tts
      SCSS
      •
      Creative Commons Zero v1.0 Universal
      •0•2•0•0•Updated Nov 11, 2023Nov 11, 2023