SpeechEditBench provides seven atomic editing tasks, compositional multi-operation instructions, and an anchor-based protocol yielding target success, preservation success, and joint success metrics; evaluations show no model excels across dimensions and compositional editing is especially difficult
Naturalvoices: A large-scale, sponta- neous and emotional podcast dataset for voice conversion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.AS 2years
2026 2representative citing papers
Emotion-embedding cosine similarity (EMO-SIM) fails to track emotion under speaker or wording changes and misaligns with human perception, so it is unreliable for evaluating expressive speech generation.
citing papers explorer
-
SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
SpeechEditBench provides seven atomic editing tasks, compositional multi-operation instructions, and an anchor-based protocol yielding target success, preservation success, and joint success metrics; evaluations show no model excels across dimensions and compositional editing is especially difficult
-
The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation
Emotion-embedding cosine similarity (EMO-SIM) fails to track emotion under speaker or wording changes and misaligns with human perception, so it is unreliable for evaluating expressive speech generation.