VLSP 2025 Evaluation Campaign
The VLSP 2025 evaluation campaign deals with several shared-tasks for text and speech processing.
- Speech Quality Assessment
- Automatic Speech Recognition and Speech Emotion Recognition
- Vietnamese Spoofing-Aware Speaker Verification
- Vietnamese Voice Conversion
- DRiLL: The challenge of Deep Retrieval in the expansive Legal Landscape
- Vietnamese Legal Assistant with Small Language Models
- Numerical Reasoning QA
- Temporal QA
- Semantic Parsing
- Medical domain MT with Limited-Pretraining models
- Multimodal Legal QA on Traffic Sign Rules
VLSP shared tasks aim at promoting the most efficient methods for these important tools. The organization of these campaigns with sponsorships from academia and industry permits to building and offering to the VLSP community gold datasets for training and testing Vietnamese text and speech processing systems.
The participants in the evaluation campaign will be asked to present their system in a dedicated paper.
Sponsors and Partners
