Extracting accent features in spoken Brazilian Portuguese without sociolinguistic labels
Researchers have developed a new method to extract accent features from spoken Brazilian Portuguese without relying on sociolinguistic labels. This approach uses acoustic labels and a phoneme-based forced aligner to isolate regional accent landmarks. The resulting targeted feature set demonstrates superior effectiveness in capturing dialectal variance compared to general-purpose speech models, especially when using minimal and objective data. AI
IMPACT This research could lead to more accurate and data-efficient accent classification systems for speech technologies.