Tech Showcase: Customizing Speech Recognition for Higher Accuracy Transcriptions
Two of the most important components of speech recognition systems are the acoustic model and the language model. Those models behind Microsoft’s speech recognition engine have been optimized for certain usage scenarios, such as interacting with Cortana on a smart phone, searching the web by voice, or sending text messages to a friend. But if a user has specific needs, such as recognizing domain-specific vocabulary or the ability to understand accents, then the acoustic and language models need to be customized. This demo shows the benefits of customizing acoustic and language models to improve the accuracy of speech recognition for lectures. Using the Custom Speech Service (Cognitive Service) technics, the demo shows how the technology can tune speech recognition for specific topic and lecturers.
- Date:
- Speakers:
- Mike Seltzer
- Affiliation:
- Microsoft
-
-
Mike Seltzer
Principal Researcher
-
-
Series: Microsoft Research Faculty Summit
-
-
Quantum Computing and Workforce, Curriculum, and Application Development: Case study
Speakers:- Krysta M. Svore,
- Martin Roetteler
-
-
-
-
Crowd, Cloud and the Future of Work: Updates from human AI computation
Speakers:- Besmira Nushi,
- Vani Mandava
-
-
-
-
-
Empowering People to Achieve More: How Useful a Concept is Productivity?
Speakers:- Brendan Murphy
-
-
Productivity in Software Development
Speakers:- Neel Sundaresan,
- Margaret-Anne Storey,
- Prem Kumar Devanbu
-
-
-
-
-
-
-
Accessible Virtual Reality
Speakers:- Eyal Ofek
-
Calendar.help: A Virtual Meeting Scheduling Assistant
Speakers:- Pamela Bhattacharya
-
Visual Studio IntelliCode
Speakers:- Mark Wilson-Thomas
-
Microsoft Teams: Collaborate with Any Researcher Anywhere
Speakers:- Jethro Seghers
-
Project Alava: Programming Webs of Microcontrollers
Speakers:- James Devine,
- Teddy Seyed
-
AI in PowerPoint
Speakers:- Kostas Seleskerov