Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models
A new research paper analyzes demographic biases in phoneme-based Automatic Speech Recognition (ASR) systems, specifically those generating International Phonetic Alphabet (IPA) transcriptions. The study evaluates two open-source systems, WhisperIPA and ZIPA, using diverse speech corpora and demographically annotated English data. Findings indicate persistent performance disparities across various demographic groups, including gender, accent, ethnicity, and age, even when accounting for linguistically similar phoneme substitutions. AI
IMPACT Highlights potential biases in IPA transcription models, informing the development of more inclusive and robust phoneme-based ASR systems.