zxxwxyyy / sonique
Video Background Music Generation Using Unpaired Audio-Visual Data
☆21Updated last month
Related projects ⓘ
Alternatives and complementary repositories for sonique
- 60k hours of phoneme-aligned audio from audio books☆18Updated 3 months ago
- [ACMMM'2024] Generative Expressive Conversational Speech Synthesis☆25Updated 2 weeks ago
- ☆41Updated 3 weeks ago
- music semantic understanding evaluation benchmark☆25Updated last year
- Codebase and project page for EDMSound☆29Updated 11 months ago
- Please visit https://thuhcsi.github.io/SnakeGAN/☆36Updated last year
- ☆34Updated 4 months ago
- ☆40Updated 5 months ago
- Stable Audio UnOffical Implementation: Latent Diffusion for Audio Generation☆23Updated 8 months ago
- PyTorch implementation of the ICASSP-24 paper: "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Superv…☆30Updated 10 months ago
- ☆41Updated last year
- The MIR-MLPop dataset and the official implementation of the paper "MIR-MLPop: A Multilingual Pop Music Dataset with Time-Aligned Lyrics …☆22Updated 6 months ago
- Implementation of Multi-Source Music Generation with Latent Diffusion.☆16Updated 2 months ago
- Contains the code associated with the ICLR submission for our text-to-speech diffusion model☆51Updated last year
- GPT-style network for phonemization with durations of text☆62Updated 7 months ago
- The source code for the paper XiaoiceSing2 (interspeech2023)☆44Updated 9 months ago
- Bilingual Singing Voice Synthesis☆13Updated 7 months ago
- ☆21Updated 6 months ago
- Adaptive Vocoder for Custom Voice☆58Updated 2 years ago
- Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986☆37Updated 3 weeks ago
- A unified model for zero-shot singing voice conversion and synthesis☆21Updated last year
- Implementation of the paper, T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis, ac…☆25Updated 5 months ago
- Robust Singing Voice Transcription and MIDI Extraction☆55Updated 3 months ago
- Findings of ACL 2023 | AlignSTS: a speech-to-singing (STS) model based on modality disentanglement and cross-modal alignment☆65Updated 4 months ago
- ☆16Updated 6 months ago
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆37Updated last year
- A spoken version of the textual story cloze benchmark☆14Updated last year
- VAE modified from Descript Audio Codec, which replaces the RVQ with VAE☆54Updated 7 months ago