NKU-HLT / PB-DSRLinks
[Interspeech 2024] Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptation
☆12Updated last year
Alternatives and similar repositories for PB-DSR
Users that are interested in PB-DSR are comparing it to the libraries listed below
Sorting:
- public child-adult speaker diarization/classification model and codes☆16Updated 7 months ago
- UT-Sarulab MOS prediction system using SSL models☆282Updated last year
- ☆12Updated last month
- An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement☆177Updated 3 months ago
- The official repository of Dynamic-SUPERB.☆196Updated 5 months ago
- ☆173Updated last year
- A collection of dataset consists of a total of 8 English speech datasets for SER☆30Updated 10 months ago
- SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods☆19Updated 3 months ago
- ☆11Updated 11 months ago
- [INTERSPEECH 2023] Knowledge Transfer from Pre-trained Language Models to Cif-based Recognizers via Hierarchical Distillation☆40Updated 2 years ago
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆223Updated last year
- ☆90Updated 7 months ago
- Layer-wise analysis of self-supervised pre-trained speech representations☆120Updated last year
- UTokyo-SaruLab MOS Prediction System☆262Updated last month
- ☆12Updated 7 months ago
- Script to perform statistical significance test between ASR hypotheses.☆22Updated 8 years ago
- This Repository surveys the paper focusing on Prompting and Adapters for Speech Processing.☆112Updated 2 years ago
- ☆55Updated last year
- Audio Codec Speech processing Universal PERformance Benchmark☆278Updated this week
- Reference-aware automatic speech evaluation toolkit☆170Updated 11 months ago
- ☆154Updated 2 years ago
- ☆61Updated last year
- Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition☆15Updated last year
- SLT 2024 Challenge: Post-ASR-Speaker-Tagging☆15Updated last year
- ☆19Updated last year
- Dataset☆24Updated 4 months ago
- [TASLP 2024] Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation☆32Updated last year
- This is the official repo of our work titled "The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio".☆64Updated 11 months ago
- The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.☆173Updated 7 months ago
- This repository contains a set of codes to run (i.e., train, perform inference with, evaluate) a diarization method called EEND-vector-cl…☆76Updated 3 years ago