- what’s new
- Health & Fitness
- gift ideas
- Buying Guide
- Quick Reads
Microsoft has announced a preview of its very own voice recognition software, the Custom Recognition Intelligence Service (CRIS). CRIS is a customizable tool similar to Apple’s SIRI in providing speech-to-text functions. CRIS technology makes it easy for users to customize speech recognition in their phones in noisy environments such as malls or other public spaces. It can also be used to enhance apps that have trouble in recognizing voices by non native speakers or people with speech disabilities.
Microsoft has also opened up public previews for two sets of APIs that will offer developers the technology to differentiate between audio recordings and videos. While the speech APIs will be able to verify and indentify the speaker, video APIs will be able to detect faces and stabilize video content.
These new technology falls under Microsoft’s Project Oxford, an initiative that gives third party developers access to Microsoft’s artificial intelligence. With developers being allowed to take advantage of Microsoft’s tech research, it promises tremendous improvements in the field of speaker recognition.