speechocean-762

The 'speechocean762' dataset is a benchmark used to evaluate Automatic Speech Recognition (ASR) models, containing diverse speech samples for assessing pronunciation quality and feature extraction capabilities.

Papers using speechocean-762 (12)

Speechblender: Speech Augmentation Framework For Mispronunciation Data Generation2022 · 2 citesAcoustic Feature Mixup For Balanced Multi-aspect Pronunciation Assessment2024 · 1 citesGoodness-of-pronunciation without phoneme time alignment2026Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunities2026English Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLM2025CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment2025Zero-Shot Text-to-Speech as Golden Speech Generator: A Systematic Framework and its Applicability in Automatic Pronunciation Assessment2024SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation2022 · 2 citesA Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment2023Zero-Shot Automatic Pronunciation Assessment2023L1-aware Multilingual Mispronunciation Detection Framework2023Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment2024