Speech Technologies for North Eastern Languages

under the project

Speech Technologies in Indian Languages of NLTM

The aim of this project is to develop a robust and scalable spoken keyword spotting system (KWS). The further aim of this project is to implement a KWS-driven healthcare information dissemination system in langauges such as, Assamese, Bangla, Bodo, Manipuri, Hindi, Indian English, Mizo, Nagamese and Nepali. A tertiary aim of this project is the creation of a multi-purpose speech database of three North-East Indian languages: Mizo, Nepali & Nagamese

DELIVERABLES

  • API for spoken keyword spotting (KWS) system

  • Localization of health-related information in seven languages (Assamese, Bangla, Bodo, Manipuri, Mizo, Nagamese, Nepali)

  • Speech based Health information Dissemination System (HiDS)

  • Speech corpora of 150 hours each for Mizo, Nagamese and Nepali