🧪 Test?View on arXiv
Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking
Author1, Author2, Author3, Author4, Author5
speech recognitionacoustic analysislanguage processing
2609.12122
Builder Relevance
2h ago70%
Abstract
This paper presents a scalable method to measure consonant contributions to word intelligibility using acoustic masking.
Reality Card
Core Claim
The study introduces a method to quantify consonant contributions to intelligibility through mask-induced misrecognition rates, validated across multiple languages and ASR architectures.
Method / Result
Consonant contribution scores were derived from the mask-induced misrecognition rate (MMR), showing that phoneme frequency negatively correlates with MMR.
Limitations
The consonant rankings are language-dependent, which may limit the generalizability of the findings across different languages.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.