THUHCSI

Human-Computer Speech Interaction Lab at Tsinghua University

FIT Building, Tsinghua University, Beijing

Pinned Repositories

Crystal
Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.
Language:C++220 16 268
Crystal.TTVS
Crystal TTVS engine is a real-time audio-visual Multilingual speech synthesizer with a 3D expressive avatar.
Language:C++84 9 218
FlatTN
Chinese Text Normalization and Dataset
Language:Python78 2 414
icassp2021-emotion-tts
Please visit: https://thuhcsi.github.io/icassp2021-emotion-tts/
Language:Python33 2 513
MagicMan
Official repository for paper "MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement"
Language:Python208 20 76
NeuCoSVC
Language:Python249 6 937
NeuFA
Neural network-based forced alignment with bidirectional attention mechanism
Language:Python70 5 108
SECap
Language:Python131 3 911
SpanPSP
Language:Python74 2 919
VAENAR-TTS
The official implementation of VAENAR-TTS, a VAE based non-autoregressive TTS model.
Language:Python145 8 1020

THUHCSI's Repositories

thuhcsi/NeuCoSVC
Language:Python249 6 937
thuhcsi/MagicMan
Official repository for paper "MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement"
Language:Python208 20 76
thuhcsi/SECap
Language:Python131 3 911
thuhcsi/LightGrad
Language:Python64 0 1211
thuhcsi/S2G-MDDiffusion
Language:Python60 1 102
thuhcsi/SnakeGAN
Please visit https://thuhcsi.github.io/SnakeGAN/
Language:Python36 3 17
thuhcsi/DiffVar
Language:Python30 1 15
thuhcsi/SpeechCraft
The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.
26 3 0
thuhcsi/VoxInstruct
VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
15 2 1
thuhcsi/Contextual-Biasing-Dataset
open-source Mandarian biased word dataset
10 1 20
thuhcsi/mm2022-conversational-tts
Language:Python9 1 0
thuhcsi/ExpressiveBailando
7 1 01
thuhcsi/SCNet
Language:Python6 0 10
thuhcsi/mst-fastspeech2
Language:Python4 3 01
thuhcsi/dpss-exp2-HMM-2023
ex2 for dpss 2023
Language:Python2 0 0
thuhcsi/icassp2023-coherent-tts
Please visit https://thuhcsi.github.io/icassp2023-coherent-tts
Language:SCSS2 0 00
thuhcsi/melody-unsupervised-pretraining-svs
Language:SCSS1 0 00
thuhcsi/Semi-Supervised-MDD
Language:Python1 0 0
thuhcsi/StyleDub
Please visit https://thuhcsi.github.io/StyleDub/
Language:Python1 1 01
thuhcsi/secap_demo
Language:SCSS0 1 00
thuhcsi/secap_slate
Language:SCSS0 0 00
thuhcsi/icassp2024-msvalle
Language:SCSS0 0
thuhcsi/interspeech2023-DiffVar
Language:HTML0 0
thuhcsi/interspeech2023-NS-Extractor
demo page for lin9x's NS-Extractor
Language:HTML0 1
thuhcsi/interspeech2023-spontaneousTTS
Language:HTML0 0
thuhcsi/interspeech2024-CSG
Please visit https://thuhcsi.github.io/interspeech2024-CSG
Language:SCSS0 0
thuhcsi/interspeech2024-SponLMTTS
Language:HTML0 0
thuhcsi/ls_slate
Language:SCSS0 0
thuhcsi/Self-Supervised-MDD
Language:Python0 0
thuhcsi/TASLP-MSStyleTTS
Please visit https://thuhcsi.github.io/TASLP-MSStyleTTS
Language:SCSS1 01