Satoshi Nakamoto Blog

Category : category-/Science/Computer Science

AI Apps artificial intelligence ASR automatic speech recognition big data category-/Computers & Electronics category-/Science/Computer Science Dev IBM Machine Learning paper Research voice

New IBM technique cuts AI speech recognition training time from a week to 11 hours

Reliable, robust, and generalizable speech recognition is an ongoing challenge in machine learning. Traditionally, training natural language understanding models requires corpora containing thousands of hours