wassname / phoneme2grapheme
Teaching machines to spell with deep learning (acc=>80%) e.g. a model hears "pɹˈaʊd˺ɚ" and writes "prowder" (but it should be "prouder")
☆19Updated 7 years ago
Related projects: ⓘ
- Attention, I'm Trying to Speak: End-to-end speech synthesis (CS224n '18)☆52Updated 5 years ago
- Demos, pretrained models, and (WIP) code supporting Representation Mixing☆51Updated 5 years ago
- ☆15Updated 6 years ago
- Cross-lingual Voice Conversion☆96Updated 6 years ago
- Multi-lingual Text Processing☆95Updated 5 years ago
- A monster repo for random research, not organized in any particular way☆13Updated 7 years ago
- FFTNet vocoder implementation☆81Updated 5 years ago
- Tensorflow Implementation of Expressive Tacotron☆197Updated 5 years ago
- Code for end-to-end ASR with neural networks, build with TensorFlow☆108Updated 5 years ago
- Wavenet and its applications with Tensorflow☆56Updated 6 years ago
- An LSTM RNN for restoring missing punctuation in unsegmented text.☆79Updated 7 years ago
- A fast cnn-based vocoder☆78Updated 4 years ago
- ☆24Updated 5 years ago
- pytorch tacotron2 https://arxiv.org/pdf/1712.05884.pdf☆43Updated 6 years ago
- Unsupervised word segmentation and clustering of speech☆13Updated 7 years ago
- ☆36Updated this week
- A Pytorch implementation of WaveVAE ("Parallel Neural Text-to-Speech")☆120Updated 6 months ago
- Tensorflow with KenLM integrated for beam search scoring☆34Updated 7 years ago
- How to run GPU accelerated Signal Processing in TensorFlow☆23Updated 5 years ago
- Tensor2tensor experiment with SpecAugment☆47Updated 5 years ago
- This repository contains the code to reproduce the core results from the paper "Scalable Factorized Hierarchical Variational Autoencoders…☆52Updated 6 years ago
- Collection of machine learning demos for Automatic Speech Recognition☆55Updated 2 years ago
- ☆21Updated 6 years ago
- Vocode spectrograms to audio with generative adversarial networks☆63Updated 5 years ago
- TACOTRON: TOWARDS END-TO-END SPEECH SYNTHESIS☆16Updated 6 years ago
- Walk through insanely commented code for an advanced recurrent model in TensorFlow☆50Updated 6 years ago
- All you need to get started for the Zero Speech Challenge 2017☆46Updated 5 years ago
- A recipe for creating a Speaker Identification system built on Kaldi.☆15Updated 4 years ago
- Correspondence and autoencoder neural network training for speech using Pylearn2.☆13Updated 8 years ago
- Code for "Online and Linear Time Attention by Enforcing Monotonic Alignments"☆92Updated 6 years ago