STOP

The 'STOP' dataset is used to evaluate Named Entity correction in Automatic Speech Recognition systems by providing a benchmark for assessing improvements in Word Error Rate and Named Entity hit ratio.

Papers using STOP (6)

DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction2025STOP: A dataset for Spoken Task Oriented Semantic Parsing2022Tensor decomposition for minimization of E2E SLU model toward on-device processing2023Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding2023Augmenting text for spoken language understanding with Large Language Models2023Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis2023