A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

In defence of metric learning for speaker recognition

The authors' implementation of the "Neural Head Reenactment with Latent Pose Descriptors" (CVPR 2020) paper.

[WACV 2024] "CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer"

Speaker identification with VGGVox network

Python toolkit for speech processing

Code and data repository for paper "VoxCeleb enrichment for Age and Gender recognition" submitted at ASRU 2021

Voice gender classifier using ECAPA-TDNN

Luigi pipeline to download VoxCeleb(2) audio from YouTube and extract speaker segments

Voxceleb1 i-vector based speaker recognition system

Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker Verification (SV).

[IJCAI2022] Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast

[ICASSP'23] Online speaker clustering

[ICASSP'24] Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Speaker Verification

kaldi based x-vector trained on Cn-Celeb

Our codebase for the 2020 VGG Speaker Recognition Challenge. Contains source for our ML pipeline and training/experimentation infrastructure

This project partially embodies the state-of-the-art practices in speaker verification technology up until 2020, while attaining the state-of-the-art performance on the VoxCeleb1 test sets.

SOTA method for self-supervised speaker verification leveraging a large-scale pretrained ASR model.

Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification, ISCA Interspeech 2025

Few-shot learning experiments mostly on speaker recognition.

Voice Face Association Learning Paper List

This repo contains the project of the relative subject "Sound and Image Technology" which was taught in the academic calendar year of 2019-20 in the department of electrical and computer engineering in Aristotle university of Thessaloniki

The FishBoardMix corpus is designed to explore Speaker-Age estimation technology.

A benchmark analysis of some Speaker Verification techniques based on Deep Learning.

2018 Lenovo AI Lab Summer Intern

⚡ Build and edit your applications easily with Trainer, using Lovable or your favorite IDE, while leveraging Node.js and npm for efficient development.

ECAPA-TDNN + Integrated Gradients to explain speaker verification and the impact of pitch-shift anonymization on LibriSpeech (with EER and IG heatmaps)

Implementation of [1706.08612] VoxCeleb: a large-scale speaker identification dataset

This Roblox script operates smoothly during standard sessions, enabling players to utilize automation features without performance issues while engaging in fish-based objectives, and includes the Tower Defense Simulator Script for Auto Farm, Infinite Coins, Gems, Money, and more