A PyTorch-based Speech Toolkit
-
Updated
Aug 5, 2024 - Python
A PyTorch-based Speech Toolkit
DELTA is a deep learning based natural language and speech processing platform.
SincNet is a neural architecture for efficiently processing raw audio samples.
In defence of metric learning for speaker recognition
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
UniSpeech - Large Scale Self-Supervised Learning for Speech
Official repository for RawNet, RawNet2, and RawNet3
Tensorflow implementation of "Generalized End-to-End Loss for Speaker Verification"
This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.
Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196
Speaker embedding (d-vector) trained with GE2E loss
Simple d-vector based Speaker Recognition (verification and identification) using Pytorch
Time delay neural network (TDNN) implementation in Pytorch using unfold method
target speaker extraction and verification for multi-talker speech
PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
🔈 Deep Learning & 3D Convolutional Neural Networks for Speaker Verification
speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts with actual speaker names
Add a description, image, and links to the speaker-verification topic page so that developers can more easily learn about it.
To associate your repository with the speaker-verification topic, visit your repo's landing page and select "manage topics."