kamperh / speech_correspondence
Correspondence and autoencoder neural network training for speech using Pylearn2.
☆13Updated 8 years ago
Related projects: ⓘ
- Unsupervised word segmentation and clustering of speech☆13Updated 7 years ago
- ☆12Updated this week
- ☆22Updated 7 years ago
- All you need to get started for the Zero Speech Challenge 2017☆46Updated 5 years ago
- ABX and kaldi experiments on speech corpora made easy☆31Updated last year
- Source code for "Unsupervised Lexicon Discovery from Acoustic Input ", Lee et al, 2015 TACL☆10Updated 8 years ago
- This repository contains the code and supplementary result for the paper "Unpaired Speech Enhancement by Acoustic and Adversarial Supervi…☆28Updated 4 years ago
- ☆45Updated 5 years ago
- ☆15Updated 6 years ago
- Zero-Resource Speech Discovery, Search, and Evaluation Tools☆29Updated 9 years ago
- Dialect identification using Siamese network☆15Updated 6 years ago
- Unsupervised Speaker Clustering & Speaker Recognition☆12Updated 5 years ago
- Dynamic time warping (DTW) functions for specifically speech alignment.☆26Updated 4 months ago
- readers that enable reading kaldi ark in tensorflow☆17Updated 6 years ago
- ☆12Updated 6 years ago
- Meta-embeddings are a probabilistic generalization of embeddings in machine learning.☆23Updated 5 years ago
- Voxceleb1 i-vector based speaker recognition system☆41Updated 6 years ago
- Example scripts that illustrate how to use Kaldi+CNTK for speech recognition.☆10Updated 8 years ago
- A set of scripts to use in preparing a corpus for speech-to-text processing with the Kaldi Automatic Speech Recognition Library.☆14Updated 4 years ago
- ☆27Updated 7 years ago
- This repository contains the code to reproduce the core results from the paper "Scalable Factorized Hierarchical Variational Autoencoders…☆52Updated 6 years ago
- A recipe for creating a Speaker Identification system built on Kaldi.☆15Updated 4 years ago
- THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is c…☆32Updated 6 years ago
- Network specification and demo☆35Updated 7 years ago
- Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation☆15Updated 4 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
- NMT based punctuation prediction system using lexical and acoustic features .☆14Updated 4 years ago
- This is an implementation of "Generative adversarial network-based postfilter for statistical parametric speech synthesis"☆16Updated 6 years ago
- Multilingual acoustic word embedding approaches applied and evaluated on GlobalPhone data.☆10Updated 3 years ago
- Run speaker recognition algorithms - Mirrored from https://gitlab.idiap.ch/bob/bob.bio.spear☆19Updated last year