MingLunHan / CIF-HieraDist
[INTERSPEECH 2023] Knowledge Transfer from Pre-trained Language Models to Cif-based Recognizers via Hierarchical Distillation
☆40Updated last year
Alternatives and similar repositories for CIF-HieraDist
Users that are interested in CIF-HieraDist are comparing it to the libraries listed below
Sorting:
- [ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-…☆71Updated 4 months ago
- The baseline system for the ICASSP2024 ICMC-ASR Challenge.☆50Updated last year
- ☆43Updated 2 years ago
- Code for paper "Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition"☆41Updated last year
- wav2vec2 audio classification for prosodic boundary detection and other tasks☆42Updated last year
- ☆55Updated last month
- ☆125Updated 3 years ago
- ☆33Updated 4 years ago
- PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASS…☆104Updated 3 years ago
- Script to perform statistical significance test between ASR hypotheses.☆22Updated 7 years ago
- This repository contains a set of codes to run (i.e., train, perform inference with, evaluate) a diarization method called EEND-vector-cl…☆78Updated 2 years ago
- This Repository surveys the paper focusing on Prompting and Adapters for Speech Processing.☆108Updated last year
- This repository contains code for applying Data2Vec to pretrain Keyword Transformer model as described in "Improving Label-Deficient Keyw…☆28Updated 2 months ago
- The project is associated with the recently-launched INTERSPEECH 2025 Workshop on Multilingual Conversational Speech Language Model (MLC-…☆34Updated this week
- BLSP: Bootstrapping Langauge-Speech Pre-training via Behavior Alignment of Continuation Writing☆50Updated last year
- ☆66Updated last week
- AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data☆31Updated last year
- 语音识别 论文 前沿☆46Updated 3 years ago
- 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
- Layer-wise analysis of self-supervised pre-trained speech representations☆103Updated 6 months ago
- SLT 2024 Challenge: Post-ASR-Speaker-Tagging☆14Updated 11 months ago
- ☆11Updated 2 years ago
- Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition☆10Updated 8 months ago
- The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to pro…☆118Updated 2 years ago
- Source for the Interspeech 2024 Paper "Scaling up masked audio encoder learning for general audio classification"☆65Updated 3 weeks ago
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆22Updated 7 months ago
- ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS☆28Updated 2 years ago
- ☆75Updated 3 years ago
- ☆56Updated last month
- 《SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks》Speech processing with prompting paradigm☆81Updated last year