york135 / CTC_CE_for_AST
The official repo/implementation of the paper "Training a Singing Transcription Model Using Connectionist Temporal Classification Loss and Cross-entropy Loss"
☆11Updated 11 months ago
Related projects: ⓘ
- Please visit https://thuhcsi.github.io/SnakeGAN/☆36Updated 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 4 months ago
- Official PyTorch implementation of "RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutiv…☆39Updated 6 months ago
- TAPE: An End-to-End Timbre-Aware Pitch Estimator☆19Updated 9 months ago
- ☆19Updated last year
- A pretrained model for "A Phoneme-informed Neural Network Model for Note-level Singing Transcription", ICASSP 2023☆24Updated last year
- Cover Song Detection System☆10Updated 5 years ago
- Spherical residual vector quantization (SRVQ)☆26Updated 3 weeks ago
- Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986☆25Updated 4 months ago
- ☆18Updated 5 years ago
- Reproduction of paper: Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorizatio…☆17Updated 5 years ago
- This is the official train-dev-test release of the Interspeech2024 Discrete Speech Representation Challenge.☆30Updated 7 months ago
- MusicYOLO framework uses the object detection model, YOLOx, to locate notes in the spectrogram.☆12Updated 2 years ago
- ☆41Updated 2 months ago
- [ISMIR 2022] Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription☆44Updated 4 months ago
- ☆42Updated last year
- ARCH: Audio Representations benCHmark☆25Updated 3 weeks ago
- ☆11Updated 3 years ago
- Unofficial implementation of NANSY++ in Pytorch Lightning☆46Updated 6 months ago
- The Multi-band Excited WaveNet☆13Updated last year
- ☆93Updated 3 weeks ago
- MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]☆35Updated 2 weeks ago
- Code for the paper "MULTI-BAND MASKING FOR WAVEFORM-BASED SINGING VOICE SEPARATION" that was accepted on EUSIPCO2022☆15Updated 2 years ago
- 60k hours of phoneme-aligned audio from audio books☆18Updated last month
- Official repository for the paper Singing Voice Graph Modeling for SingFake Detection (Interspeech 2024).☆18Updated 3 months ago
- ☆47Updated 10 months ago
- ☆41Updated last month
- A toy-like Text-to-Speech for Chinese/Mandarin synthesize, inspired by Tacotron & FastSpeech2 & RefineGAN.☆15Updated 2 years ago
- Repository for ISMIR 2022 tutorial T3(M): Designing Controllable Synthesis System for Musical Signals☆27Updated last year
- ☆29Updated this week