- Advances in deep learning and signal processing that are making speech recognition leap forward -
Takuya Yoshioka, Media Information Laboratory
Today, speech recognition technology that transforms spoken words into texts is rapidly coming into everyday life. The surge in commercial applications of the speech recognition technology is driven by advances in an artificial intelligence technology called deep learning. This talk will review how deep learning has been used and changed the way in which speech recognition is performed based on our experiences. This talk will further describe microphone array processing technologies that will make speech recognition available in a wide range of situations and discuss the future of the speech recognition technology and how it will impact our lives.