Microsoft Cognitive Services are a set of APIs, SDK and services offered by Microsoft that can be leveraged by developers to make their applications more intelligent, engaging and intuitive. These machine learning APIs enable developers to add various intelligent features to their applications, including but not limited to emotion detection, facial, speech and vision recognition, and speech and language understanding.
One such cognitive service provided by Microsoft Cognitive Services is the Bing Speech API. The speech API allows developers to integrate and use speech-enabled features in their applications. The Bing Speech API includes both, Speech-to-Text (speech recognition) and Text-to-Speech (speech synthesis). Speech-to-Text, as the name suggests, converts human speech or spoken words to text that can be used as a command or input, whereas Text-to-Speech converts written text to audio that can be used in the form of an output.
Yesterday, Microsoft announced via a blog post that the Bing Speech API is extending its Text-to-Speech support for six additional languages, bringing the total number of languages supported to 34.
The six new Text-to-Speech languages include:
- Bulgarian (language code: bg-BG)
- Croatian (hr-HR)
- Malaysia (ms-MY)
- Slovenian (sl-SI)
- Tamil (ta-IN)
- Vietnamese (vi-VN)
Qinying Liao, senior program manager at Microsoft for AI Core – Speech, states in the post that the 34 languages are available in 48 locales and 78 voice fonts. Also, the Text-to-Speech API can be used on its own or can be combined with other Cognitive Services, such as the Speech-to-Text and language understanding APIs to create comprehensive voice-driven online or on-device solution.
Additionally, these new Text-to-Speech languages will become available through the Microsoft Translator Speech API and the Microsoft Translator apps by the end of February 2018, making these new languages available for developers to integrate into their applications that use the Translator speech API as well as end users who use the Translator apps and Translator live feature.
Head to the Cognitive Services Speech API page to see the speech recognition in action.
2 Comments - Add comment