Fine-tuning wav2vec2 to for Pathological Speech Processing
-
Updated
Dec 1, 2023 - Jupyter Notebook
Fine-tuning wav2vec2 to for Pathological Speech Processing
Convert kaldi feature extraction and nnet3 models into Tensorflow Lite models. Currently aimed at converting kaldi's x-vector models and diarization pipelines to tensorflow models.
We extract the x-vector and i-vector of five Kurdish Dialects and use these vectors to recognition Kurdish dialects.
DNN embeddings extraction from audio and speech recordings using PyTorch.
Custom Kaldi recipes for DNN feature extraction on public and non-public audio corpora. Medical speech and computational paralinguistics related.
Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP 2020
Implementation of the paper "Spoken Language Recognition using X-vectors" in Pytorch
PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
Time delay neural network (TDNN) implementation in Pytorch using unfold method
Add a description, image, and links to the x-vector topic page so that developers can more easily learn about it.
To associate your repository with the x-vector topic, visit your repo's landing page and select "manage topics."