kaldi-asr/kaldi is the official location of the Kaldi project.

Speech synthesis, voice conversion, self-supervised learning, music generation,Automatic Speech Recognition, Speaker Verification, Speech Synthesis, Language Modeling

DELTA is a deep learning based natural language and speech processing platform.

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

SincNet is a neural architecture for efficiently processing raw audio samples.

PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.

In defence of metric learning for speaker recognition

The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech processing systems, ranging from speech recognition (both HMM/DNN and end-to-end), speaker recognition, speech enhancement, speech separation, multi-microphone speech processing, and many others.

Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196

Author's repository for reproducing RawNet 1 and 2 papers with pre-trained model weights and speaker embeddings, which directly extracts speaker embeddings from raw waveforms. RawNet2 is implemented in PyTorch and RawNet1 is implemented in PyTorch and Keras.

This repository contains audio samples and supplementary materials accompanying publications related to the speaker-id team at Google.

Time delay neural network (TDNN) implementation in Pytorch using unfold method

🔈 Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi

Share some recent speaker recognition papers and their implementations.

Simple d-vector based Speaker Recognition (verification and identification) using Pytorch

Pytorch implementation of "Generalized End-to-End Loss for Speaker Verification"

A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.

A program for automatic speaker identification using deep learning techniques.

An LDA/PLDA estimator using KALDI in python for speaker verification tasks

This repo contains my attempt to create a Speaker Recognition and Verification system using SideKit-1.3.1

target speaker extraction and verification for multi-talker speech

Keras Implementation of Deepmind's WaveNet for Supervised Learning Tasks

Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)

【仅作为交流学习使用】机器智能--相关书目及经典论文包括AutoML、情感分类、语音识别、声纹识别、语音合成实验代码等

Pytorch implementation of Generalized End-to-End Loss for speaker verification

Pytorch implementation of Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs (Interspeech, 2020)

mirror of VoxCeleb dataset - a large-scale speaker identification dataset

Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP 2020