zhanxiage1994 / merlin_workdemo
a work demo for test-to-speech (contain train and test step)
☆9Updated 6 years ago
Related projects: ⓘ
- Chinese Prosodic Structure Prediction☆10Updated 5 years ago
- [InterSpeech 2020] "Improving the Speaker Identity of Non-Parallel Many-to-Many VoiceConversion with Adversarial Speaker Recognition" by …☆39Updated last year
- ☆33Updated this week
- Reproduction of paper: Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorizatio…☆17Updated 5 years ago
- Model Fusion Based Prosody Prediction☆17Updated 6 years ago
- Materials accompanying the paper "Phonological features for 0-shot multilingual speech synthesis"☆31Updated 4 years ago
- Audio LPC (linear prediction code) using mel spectorgram, compatible for LPCNet☆61Updated 3 years ago
- Convert WSJ sphere format to waveform and do data simulation.☆16Updated 4 years ago
- ☆31Updated last year
- 基于随机森林和条件随机场的中文韵律预测模型☆26Updated last month
- TTS-frontend with Bert and CRF/lstm (For Tacotron)☆48Updated 4 years ago
- ICASSP 2021 accepted papers in term of voice conversion (VC)☆18Updated 3 years ago
- Simulation of parallel synthesis with LPCNet vocoder☆14Updated 4 years ago
- Predict prosody labels for Chinese sentences.☆41Updated 2 years ago
- Supporting code for the paper "A study on more realistic room simulation for far-field keyword spotting".☆28Updated 3 years ago
- kaldi cnn-tdnnf baseline☆13Updated 3 years ago
- Implementation of the subscale framework from the WaveRNN paper, building on top of Fatchord's WaveRNN repo☆17Updated 3 years ago
- List of NN based singal processing papers☆17Updated last year
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis☆37Updated 3 years ago
- torch version of LPCNet☆19Updated 4 years ago
- 一个开源的中文歌声合成数据集。An open-source Chinese singing synthesizing dataset.☆20Updated 5 years ago
- Code for calculate DNS_MOS.☆27Updated last year
- Computes the MWER (minimum WER) Loss with beam search and negative sampling strategy.☆17Updated last year
- ☆23Updated this week
- Production first, nn-based on-device signal processing toolkit.☆63Updated last year
- ☆28Updated this week
- ☆18Updated this week
- GlottDNN vocoder and tools for training DNN excitation models☆32Updated 3 years ago
- ☆10Updated 4 years ago
- PyTorch implementation of WASE described in our ICASSP 2021: "Wase: Learning When to Attend for Speaker Extraction in Cocktail Party Envi…☆23Updated 2 years ago