kamperh / speech_correspondence
Correspondence and autoencoder neural network training for speech using Pylearn2.
☆13Updated 8 years ago
Related projects ⓘ
Alternatives and complementary repositories for speech_correspondence
- ABX and kaldi experiments on speech corpora made easy☆31Updated last month
- Unsupervised word segmentation and clustering of speech☆13Updated 7 years ago
- Dialect identification using Siamese network☆15Updated 6 years ago
- Source code for "Unsupervised Lexicon Discovery from Acoustic Input ", Lee et al, 2015 TACL☆10Updated 8 years ago
- ☆22Updated 7 years ago
- This repository contains the code and supplementary result for the paper "Unpaired Speech Enhancement by Acoustic and Adversarial Supervi…☆28Updated 5 years ago
- Zero-Resource Speech Discovery, Search, and Evaluation Tools☆29Updated 9 years ago
- ☆45Updated 5 years ago
- NMT based punctuation prediction system using lexical and acoustic features .☆14Updated 4 years ago
- ☆15Updated 6 years ago
- Meta-embeddings are a probabilistic generalization of embeddings in machine learning.☆23Updated 5 years ago
- Code for AccentDB.☆19Updated 3 years ago
- Dynamic time warping (DTW) functions for specifically speech alignment.☆27Updated 6 months ago
- An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 trai…☆54Updated 4 years ago
- This repository contains the code to reproduce the core results from the paper "Scalable Factorized Hierarchical Variational Autoencoders…☆52Updated 6 years ago
- Convert words to numbers☆20Updated 2 years ago
- readers that enable reading kaldi ark in tensorflow☆17Updated 6 years ago
- ☆12Updated 6 years ago
- All you need to get started for the Zero Speech Challenge 2017☆46Updated 5 years ago
- MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.☆78Updated 5 years ago
- Hybrid speech synthesiser☆28Updated 5 years ago
- THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is c…☆33Updated 6 years ago
- An open-source tool for automatic speech recognition ASR quality estimation.☆23Updated 4 years ago
- ☆27Updated 7 years ago
- This is an implementation of "Generative adversarial network-based postfilter for statistical parametric speech synthesis"☆16Updated 6 years ago
- This is the home directory to speaker diarization module being developed for Hetergeneous News data in RedHen Labs as a GSOC Project☆10Updated 9 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 3 months ago
- Voxceleb1 i-vector based speaker recognition system☆43Updated 6 years ago
- This is now the official location of the Kaldi project.☆13Updated 5 years ago