clam004 / unsupervised-speech-representation-learningLinks
This is a intuitive explanation of Representation Learning with Contrastive Predictive Coding using code provided by jefflai108 that uses CPC to learn representations of sound files for the purpose of speech recognition
☆10Updated 4 years ago
Alternatives and similar repositories for unsupervised-speech-representation-learning
Users that are interested in unsupervised-speech-representation-learning are comparing it to the libraries listed below
Sorting:
- Feature extractor for DL speech processing.☆66Updated 3 years ago
- (Hybrid) BYOL-S feature extractor using serab-byols package in pytorch.☆27Updated last year
- Official Implementation of Mockingjay in Pytorch☆54Updated 2 years ago
- Emotion detection in audio utilising self-supervised representations trained with Contrastive Predictive Coding (CPC).☆43Updated 3 years ago
- Enable RNNLM lattice rescoring with Pytorch [kaldi]☆12Updated 5 years ago
- Mispronunciation detection code for jingju singing voice☆20Updated 6 years ago
- A Kaldi/ESPnet based approach to perform automatic speech recognition on low resource languages☆9Updated 4 years ago
- follow NVIDIA, simplify it and support data parallel.☆13Updated 5 years ago
- Transformer-based online speech recognition system with TensorFlow 2☆26Updated 4 years ago
- BERT and LSTM baseline models of the ZeroSpeech Challenge 2021☆60Updated 2 years ago
- Keras-based python framework to compute phonological posterior probabilities from audio files☆44Updated 2 years ago
- Code for the paper "Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks".☆13Updated 2 years ago
- Pre-training Cross-modal Transformer for Audio-and-Language Representations☆39Updated 4 years ago
- asr2k☆51Updated last year
- Implementation of the DIVA model of speech acquisition and production using PyTorch☆21Updated 2 years ago
- A new metric for evaluating end-to-end speech recognition and disfluency removal systems☆19Updated 4 years ago
- ☆14Updated 2 years ago
- The Additive Margin SincNet (AM-SincNet) is a new approach for speaker recognition problems which is based in the neural network architec…☆45Updated last year
- Analysis and investigating the confounding effect of accents in end-to-end Automatic Speech Recognition models.☆15Updated 5 years ago
- Official PyTorch implementation of TTS Style Transfer☆24Updated 3 years ago
- PyTorch implementation of automatic speech recognition models.☆38Updated 4 years ago
- Pytorch code for the paper 'Attention-based Atrous Convolutional Neural Networks: Visualisation and Understanding Perspectives of Acousti…☆14Updated 4 years ago
- Source code of paper <End-to-End Language Diarization for Bilingual Code-switching Speech>☆19Updated 3 years ago
- ☆36Updated 3 years ago
- MaSS - Multilingual corpus of Sentence-aligned Spoken utterances☆50Updated 10 months ago
- Code for the paper: How Much Context Does My Attention-Based ASR System Need?☆10Updated 2 months ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago
- The official repository for Audio ALBERT☆65Updated 3 years ago
- Code for DeCoAR (ICASSP 2020) and BERTphone (Odyssey 2020)☆103Updated 2 years ago
- Multilingual and code-switching ASR challenges for low resource Indian languages.☆21Updated 3 years ago