joaoantoniocn / AM-SincNet
The Additive Margin SincNet (AM-SincNet) is a new approach for speaker recognition problems which is based in the neural network architecture SincNet and the additive margin softmax (AM-Softmax) loss function. It uses the architecture of the SincNet, but with an improved AM-Softmax layer.
☆43Updated last year
Alternatives and similar repositories for AM-SincNet:
Users that are interested in AM-SincNet are comparing it to the libraries listed below
- Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP…☆59Updated 4 years ago
- VoxSRC Challenge☆31Updated 5 years ago
- The Additive Margin MobileNet1D is a new light weight deep learning model for Speaker Recognition which is based on the MobileNetV2 archi…☆30Updated last year
- Development Toolkit for the VoxCeleb Speaker Recognition Challenge 2020☆42Updated 4 years ago
- PyTorch implementation of a self-attentive speaker embedding☆17Updated 5 years ago
- Tensor2tensor experiment with SpecAugment☆46Updated 5 years ago
- Code and instruction on replicating the experiments done in paper: Unified Hypersphere Embedding for Speaker Recognition☆31Updated 5 years ago
- Transformer-based online speech recognition system with TensorFlow 2☆26Updated 4 years ago
- ☆25Updated 3 years ago
- Pytorch implementation of Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs (Interspeech, 2020)☆73Updated 4 years ago
- End-to-end diarization loss☆22Updated 3 years ago
- DCASE2020 Challenge Task 1 baseline system☆25Updated 4 years ago
- Implementation of the paper "Keyword Transformer: A Self-Attention Model for Keyword Spotting"☆23Updated 3 years ago
- fast SpecAugmentation code with numpy and scipy☆30Updated 5 years ago
- DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020☆22Updated 4 years ago
- Meta-embeddings are a probabilistic generalization of embeddings in machine learning.☆22Updated 6 years ago
- ☆17Updated 6 years ago
- Voxceleb1 i-vector based speaker recognition system☆43Updated 6 years ago
- Deep multi-metric learning for text-independent speaker verification☆24Updated 5 years ago
- an Audio-Visual Voice Activity Detection using Deep Learning☆48Updated 5 years ago
- Augmentation adversarial training for self-supervised speaker recognition☆77Updated 3 years ago
- Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion☆39Updated 2 years ago
- Code for the paper: "Leveraging speaker attribute information using multi task learning for speaker verification and diarization" present…☆25Updated 2 years ago
- Implementation for paper "iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric L…☆54Updated last year
- Coordinate-wise meta-learner for speaker adaptation of ASR models.☆20Updated 5 years ago
- GPU accelerated implementation of i-vector extractor training using PyTorch. Requires Kaldi for feature extraction and UBM training. An e…☆64Updated 5 years ago
- A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.☆136Updated 5 years ago
- Discriminative Neural Clustering for Speaker Diarisation☆78Updated 2 years ago
- Text to Speech Synthesis based on controllable latent representation☆14Updated 5 years ago
- Author's repository for reproducing DcaseNet, an integrated pre-trained DNN that performs acoustic scene classification, audio tagging, a…☆39Updated 3 years ago