smallsmartao / ICSRC_2022_baseline
☆15Updated 2 years ago
Alternatives and similar repositories for ICSRC_2022_baseline:
Users that are interested in ICSRC_2022_baseline are comparing it to the libraries listed below
- End-to-End Speech Processing Toolkit☆13Updated last month
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆21Updated 5 months ago
- Python wrapper for kaldi's arpa2fst☆38Updated 3 months ago
- Implementation of CTC alignment-based single step non-autoregressive transformer☆13Updated last year
- This repository contains the code for our upcoming paper An Investigation of End-to-End Models for Robust Speech Recognition at ICASSP 20…☆47Updated 2 months ago
- AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data☆30Updated last year
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 4 years ago
- Speech samples and code of BEdit-TTS☆32Updated last year
- CMU multilingual speech repository☆31Updated 2 years ago
- ☆25Updated 4 months ago
- Code for synchronising all CHiME-5 audio signals for use in CHiME-6☆18Updated 5 years ago
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago
- ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS☆28Updated last year
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆57Updated last year
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- End-to-end MOdeling of ASR (Automatic Speech Recognition)☆33Updated 2 years ago
- ☆43Updated last year
- A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…☆33Updated last year
- ☆33Updated 3 years ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- ☆15Updated 8 months ago
- ☆16Updated 2 years ago
- A CSRankings-like index for speech researchers☆33Updated 4 months ago
- Efficient Neural Architecture Search via Straight-Through Gradients☆13Updated 4 years ago
- This repository is the official implementation of unimodal aggregation (UMA) for automaticspeech recognition (ASR).☆24Updated 2 months ago
- ☆36Updated 2 years ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- The project for speech translation☆11Updated last year
- PyTorch implementation of WASE described in our ICASSP 2021: "Wase: Learning When to Attend for Speaker Extraction in Cocktail Party Envi…☆24Updated 3 years ago
- ☆75Updated 2 years ago