Sociolinguistic Variation and Automatic Speech Recognition: Challenges and Approaches

Failing to account for sociolinguistic variation can result in accuracy differences between groups and generally worsens performance for members of minority groups. How to handle sociolinguistic variation in ASR systems, especially systems trained via deep learning, is an area of active research. This talk will introduce current approaches from natural language processing and discuss their benefits and drawbacks.

• Link to program
• Link to slides