'Help Alexa learn more Indian languages' Says Puneesh Kumar

As Alexa in Hindi celebrates its first anniversary in India, the company is hopeful that her knowledge graph will
'Help Alexa learn more Indian languages' Says Puneesh Kumar

NEW DELHI: As Alexa in Hindi celebrates its first anniversary in India, the company is hopeful that her knowledge graph will improve and it will talk to millons of people in several regional languages in the near future. Today, users from India make hundreds of thousands of requests in a day to Alexa in Hindi and Hinglish.

"I can't speculate on our future roadmap but I can tell you the Alexa service is getting smarter every day and we're working hard to continue to increase her knowledge graph," Puneesh Kumar, Country Leader for Alexa, Amazon India said.

"We also encourage more Indian customers to try Cleo skill and help Alexa learn more Indian languages," he added.

The language-learning skill called Cleo helps customers respond to Alexa in Hindi, Tamil, Marathi, Kannada, Bengali, Telugu, Gujarati and other languages.

The more Indians use Cleo skill, the more the company will improve Alexa's speech recognition and natural language processing (NLP) in order to prepare its smart assistant on various Echo range of devices, and third-party ones too, speak in other languages as well.

Today, users ask Alexa for diverse Hindi content such as chutkule, shayaris, kahaniya, Kabirkedohe, Panchatantra stories, Bollywood dialogues and more.

"The customers can switch between English and Hindi when talking to Alexa without changing the language setting from Hindi to English and the other way around every time," Kumar said.

The complexity and variety of questions in Hindi or Hinglish by customers is 50 per cent higher than the range of questions asked by customers to Alexa in English. This makes it extremely challenging for the speech science teams to ensure Alexa's understanding of user requests is optimum.

"The Alexa Speech Science team has used the latest advances in deep neural networks, multi-dialect training, and semi-supervised learning to reduce Automatic Speech Recognition (ASR) errors by more than 40 per cent since launch of Hindi last year," Kumar informed. (IANS)

Top Headlines

No stories found.
Sentinel Assam
www.sentinelassam.com