Speechocean-762
Emerging13papers using it
2022first seen
The 'Speechocean-762' dataset contains 5,000 utterances used to evaluate L2 English pronunciation across multiple aspects, including accuracy, fluency, prosody, and completeness.
Papers using Speechocean-762 (13)
- A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language RationalesGoodness-of-pronunciation without phoneme time alignmentZero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and OpportunitiesEnglish Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLMCBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency AssessmentZero-Shot Text-to-Speech as Golden Speech Generator: A Systematic Framework and its Applicability in Automatic Pronunciation AssessmentAutomatic Pronunciation Assessment using Self-Supervised Speech
Representation LearningSpeechBlender: Speech Augmentation Framework for Mispronunciation Data
GenerationA Hierarchical Context-aware Modeling Approach for Multi-aspect and
Multi-granular Pronunciation AssessmentZero-Shot Automatic Pronunciation AssessmentL1-aware Multilingual Mispronunciation Detection FrameworkAcoustic Feature Mixup for Balanced Multi-aspect Pronunciation
AssessmentTransformer-Based Multi-Aspect Multi-Granularity Non-Native English
Speaker Pronunciation Assessment