alecokas / BiLatticeRNN-Confidence
Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks https://arxiv.org/abs/1910.11933 or https://ieeexplore.ieee.org/document/9053264
☆16Updated 4 years ago
Related projects: ⓘ
- Python wrapper for kaldi's arpa2fst☆38Updated last year
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 2 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆37Updated 4 years ago
- CMU multilingual speech repository☆31Updated 2 years ago
- ☆16Updated 2 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- Recurrent Neural Aligner☆49Updated 4 years ago
- This repository describes our reproducible framework for assessing self-supervised representation learning from speech☆51Updated 2 years ago
- APAM toolkit is built on PyTorch and provides recipes to adapt pretrained acoustic models with a variety of sequence discriminative train…☆14Updated 3 years ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆60Updated 6 months ago
- Computes the MWER (minimum WER) Loss with beam search and negative sampling strategy.☆17Updated last year
- ☆75Updated 2 years ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆47Updated 2 months ago
- Pypi installable TDNN and TDNN-F layers for PyTorch based acoustic model training☆38Updated 3 years ago
- Implementation of CTC alignment-based single step non-autoregressive transformer☆11Updated last year
- ☆22Updated 5 years ago
- Phonetically-Oriented Word Error Rate☆31Updated 5 years ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- Non-Autoregressive Predictive Coding☆50Updated 3 years ago
- HMM, CTC, RNN-Transducer, forward-backward algorithm☆19Updated last year
- ☆16Updated 4 years ago
- ☆48Updated 3 years ago
- A collection of papers related to speech model compression☆24Updated last year
- ☆69Updated this week
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆65Updated 3 years ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated 6 months ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆43Updated last year
- A SPMI Lab toolkit for language models.☆11Updated 7 years ago
- Implementation of the paper "Confidence estimation for attention based sequence to sequence models for speech recognition"☆15Updated 3 years ago
- unsupervised ASR (mainly phone classifier) using EODM and GAN☆12Updated 3 years ago