Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

The PyTorch-based audio source separation toolkit for researchers

A PyTorch-based Speech Toolkit

Mother of All BCI Benchmarks

A personal toolkit for single/multi-channel speech recognition & enhancement & separation.

Acoustic testing and source mapping software

Domain Adaptive Neural Networks with DJP-MMD

Awesome Knowledge Distillation

[arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis

A comprehensive survey of deep metric learning and related works

Paper by Miyato et al. https://openreview.net/forum?id=B1QRgziT-

IEEE/ACM TASLP 2020: SBERT-WK: A Sentence Embedding Method By Dissecting BERT-based Word Models

Deep Discriminative Embeddings for Duration Robust Speaker Verification

Code release for Discriminative Adversarial Domain Adaptation (AAAI2020).

PyTorch code for softmax variants: center loss, cosface loss, large-margin gaussian mixture, COCOLoss, ring loss

Code repository for our paper entilted "Metric Learning with HORDE: High-Order Regularizer for Deep Embeddings" accepted at ICCV 2019.

Official implementation of the paper "GANprintR: Improved Fakes and Evaluation of the State-of-the-Art in Face Manipulation Detection"

SE-Resnet+AMSoftmax for Speaker Verification

Similarity Learning applied to Speaker Verification and Semantic Textual Similarity

Code for ICCV2019 paper《Adversarial Learning with Margin-based Triplet Embedding Regularization》

Evaluating different Lp Norms with the triplet loss function.

MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks

PyTorch implementation of LF-MMI for End-to-end ASR

PyTorch implementation of various methods for continual learning (XdG, EWC, online EWC, SI, LwF, DGR, DGR+distill, RtF, iCaRL).

PyTorch implementation Large-Margin Softmax (L-Softmax) loss

Tensoflow implementation of InsightFace (ArcFace: Additive Angular Margin Loss for Deep Face Recognition).

Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)

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