Azure Speech Service Vision Keynote Demo // Microsoft Build 2019
- Sonia Dara, Heiko Rahmel, Yousaf Sajid | Microsoft Research
Our latest research progress enables dynamic creation of a virtual microphone array with a set of existing devices equipped with ordinary microphones. It helps our customers more easily transcribe conversations at anytime anywhere. Also, Azure speech service can automatically generate custom speech models using Office 365 data to deliver more accurate transcription on organization-specific vernacular such as technical terms and people names.
Learn more about new advancements in spoken language processing >
Watch Next
-
Multimodal & Embodied Intelligence (S2)
- Rajiv Ratn Shah,
- Tanuja Ganu,
- Mercy Ranjit
-
Multimodal & Embodied Intelligence (S1), Panel on Multimodal AI: Progress, Pitfalls, Possibilities
- Madhava Krishna,
- Sriram Ganapathy,
- Somak Aditya
-
Session on Compute & Trust (Security)
- Krishna Pillutla,
- Danish Pruthi
-
Panel: Is Retrieval Relevant in the Age of Reasoning?
- Himanshu Tyagi,
- Ravishankar Krishnaswamy,
- Mrinal Kanti Das
-
Session on Reasoning
- Hongxiang Fan,
- Nagarajan Natarajan
-
Human-Centered AI: Design, Deployment & Healthcare
- Manik Gupta,
- Anirudha Joshi,
- Aaditeshwar Seth
-
-
-
-
