CHAINS
Emerging4papers using it
2024first seen
The 'CHAINS' dataset is a benchmark used to evaluate the intelligibility of whispered-to-normal speech conversion methods.
Papers using CHAINS (4)
- FlowW2N: Whispered-to-Normal Speech Conversion via Flow-MatchingState-Space Models in Efficient Whispered and Multi-dialect Speech RecognitionLeveraging Self-Supervised Models for Automatic Whispered Speech
RecognitionQuartered Spectral Envelope and 1D-CNN-based Classification of Normally
Phonated and Whispered Speech