Microsoft Introduces Indian English, Hindi To Its Neural Text To Speech Service

Microsoft recently introduced the addition of languages — Indian English and Hindi to its Neural Text to Speech (Neural TTS) service language set, alongside the 15 new dialects added to the service. These are enabled with state-of-the-art AI audio quality.

Neural TTS is a part of the Azure Cognitive Services and converts text to lifelike speech for a more natural interface. It even provides customisable voices, fine-tuned auto control and flexible deployment from cloud to edge.

With a natural-sounding speech that matches the stress patterns and intonation of human voices. The company shared that Neural TTS reduces listening fatigue drastically when users are interacting with AI systems.

It is used extensively by companies in the telecom, media and entertainment, retail, manufacturing and other domains to communicate with the customers. For instance, Udaan, India’s largest online business-to-business (B2B) marketplace, is using Text to Speech in Azure to develop conversational interfaces for their voice assistants.

Our text-to-speech services have played a key role in democratising information reach and empowering people and organisations,” said Sundar Srinivasan, General Manager, Microsoft India (R&D) Pvt. Ltd.

He added that inclusion of English (India) and Hindi languages will further democratise their continued commitment to refining speech and voice-based services for personal and business use in India.

“We will continue to drive further advancements in speech services to empower people wherever they are to access information easily,” he said.

Microsoft’s Neural TTS can be used to make interactions with chatbots and virtual assistants more natural and engaging. It is also being used to convert digital texts such as e-books into audiobooks and being deployed for in-car navigation systems.

The company uses deep neural networks to overcome the limits of traditional text-to-speech systems in matching the patterns of stress and pitch in spoken language. It therefore helps in enabling human-like natural and clear articulation, which is better than other similar services.

Neural TTS offers these benefits while maintaining comprehensive privacy and enterprise-grade security through data encryption.

The other new languages introduced are Arabic (Egypt and Saudi Arabia), Danish, Finnish, Catalan, Polish, Dutch, Portuguese, Russian, Thai, Swedish, and Chinese (Cantonese Traditional and Taiwanese Mandarin).

With these additions, the company now support 110 voices and over 45 languages and variants.

Overall, Microsoft TTS supports 110 voices and over 45 languages and variants.

More Great AIM Stories

Srishti Deoras
Srishti currently works as Associate Editor at Analytics India Magazine. When not covering the analytics news, editing and writing articles, she could be found reading or capturing thoughts into pictures.

More Stories

MORE FROM AIM
Yugesh Verma
Complete Tutorial on Parts Of Speech (PoS) Tagging

Classifying words in their part of speech and providing them labels according to their part of speech is called part of speech tagging or POS tagging OR POST.  Hence the set of labels/tags is called a tagset. Next in the article, we will discuss how we can implement that POST part of any NLP task

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM