cvqluu / Factorized-TDNNLinks
PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
☆147Updated 5 years ago
Alternatives and similar repositories for Factorized-TDNN
Users that are interested in Factorized-TDNN are comparing it to the libraries listed below
Sorting:
- Tensorflow implementation of x-vector topology on top of Kaldi recipe☆119Updated 5 years ago
- Time delay neural network (TDNN) implementation in Pytorch using unfold method☆202Updated 5 years ago
- A pytorch implementation of xvector embedding☆79Updated 5 years ago
- python codes to extract MFCC and FBANK speech features for Kaldi☆66Updated 6 years ago
- Implementation of Neural PLDA (NPLDA) model (A discriminative backend for Speaker Verification)☆99Updated 5 years ago
- ☆99Updated 7 years ago
- Some useful features of speech process, such as MFCC, gammatone filterbank, GFCC, spectrum(power spectrum and log-power spectrum), Amplit…☆128Updated 4 years ago
- Speech separation with utterance-level PIT experiments☆104Updated 6 years ago
- Ideal Ratio Mask (IRM) Estimation based Speech Enhancement using LSTM☆118Updated 5 years ago
- PyTorch implementation of Densely Connected Time Delay Neural Network☆87Updated 2 years ago
- ☆60Updated 4 years ago
- Neural speaker recognition/verification system based on Kaldi and Tensorflow☆32Updated 4 years ago
- Pytorch implementation of "Generalized End-to-End Loss for Speaker Verification"☆102Updated 6 years ago
- Extract xvector and ivector under kaldi☆109Updated 6 years ago
- Speech enhancement system for the CHiME-5 dinner party scenario☆109Updated 4 months ago
- Robust Speech Recognition Using Generative Adversarial Networks (GAN)☆59Updated 5 years ago
- An LDA/PLDA estimator using KALDI in python for speaker verification tasks☆100Updated 8 years ago
- Conferencing Speech Challenge☆96Updated 4 years ago
- A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.☆136Updated 5 years ago
- A personal toolkit for single/multi-channel speech recognition & enhancement & separation.☆143Updated last year
- A pure python module for reading and writing kaldi ark files☆259Updated 3 months ago
- A PyTorch implementation of "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" (see recipes in aps framework https:/…☆212Updated last year
- MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement (ICML 2019, with Travel awar…☆138Updated 4 years ago
- [ICASSP2021] Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech…☆55Updated 4 years ago
- Voxceleb1 i-vector based speaker recognition system☆43Updated 7 years ago
- Share some recent speaker recognition papers and their implementations.☆90Updated 5 years ago
- Libri-CSS: dataset and evaluation pipeline☆145Updated 2 years ago
- Neural network supported GEV beamformer☆205Updated 7 years ago
- Implementation of audio degradation processes☆103Updated 9 years ago
- Implementation of the paper "Attentive Statistics Pooling for Deep Speaker Embedding" in Pytorch☆44Updated 5 years ago