Home India Ministry of Electronics and Information Technology Signing of Memorandum of Understanding (MoU) between Digital...
Date: 2026-01-21 Category: Press Release State: Union Government Country: India

Signing of Memorandum of Understanding (MoU) between Digital India BHASHINI Division and Survey of India for Toponymic Data Digitisation

Issued by Ministry of Electronics and Information Technology · Not Applicable

Research with AI Agent Chat with Document Generate Summary Translate Helpful Share Add to Project Create Task

Executive Summary & Key Takeaways

**Executive Summary** This document details a Memorandum of Understanding (MoU) signed on January 20, 2026, between the Digital India BHASHINI Division (DIBD) and the Survey of India (SoI). The MoU aims to support the digitization, transcription, and standardization of geographical place names (toponyms) using AI-based speech and language technologies in alignment with the National Geospatial Policy, 2022. The collaboration seeks to create accurate, multilingual, and standardized toponymic datasets. **Key Points / Main Content** * **Purpose and Scope:** * The MoU focuses on digitizing, transcribing, and standardizing geographical place names (toponyms). * It will support the creation of accurate, multilingual and standardized toponymic datasets. * Aims to align with the National Geospatial Policy, 2022. * **Roles and Responsibilities:** * SoI is the national nodal agency for standardizing and maintaining geographical names and undertakes large-scale toponymic field surveys to collect place names in local vernacular languages for integration into national mapping systems. * BHASHINI will use its speech-to-text and language processing capabilities to convert audio recordings of place names into structured digital text. * BHASHINI will contribute its speech and language AI portfolio to support data creation, annotation and validation pipelines, enabling large-scale conversion of human speech into high-quality geospatial language datasets. * **Expected Outcomes:** * Development of the National Geographical Name Information System (NGNIS) by enabling efficient processing of field-collected audio data into local language scripts. * Enhanced speed, accuracy, and scale of toponym data processing through automatic speech recognition, language normalization, and validation workflows. * Strengthened audio documentation of place names, preserving correct pronunciation and local linguistic variations. * Improved reliability of place-name datasets used across Open Series Maps, governance platforms and public information systems. * Comprehensive and validated Toponymy Database covering more than 16 lakh locations * **Alignment with National Vision:** * The MoU reinforces the role of language technologies in strengthening India's geospatial ecosystem. * Ensures place names across regions and dialects are accurately captured, preserved, and standardized. * Aligns with the Government of India's vision of building indigenous, AI-enabled digital infrastructure rooted in Indian linguistic realities. **Impact Analysis** **Stakeholder: Digital India BHASHINI Division (DIBD)** * **Impact:** DIBD will contribute its speech and language AI portfolio to support data creation, annotation and validation pipelines. This collaboration reinforces BHASHINI's approach of embedding language AI across national digital public infrastructure systems. * **Action Required:** DIBD needs to deploy its AI tools and expertise to support data creation, annotation, and validation for the toponymic data digitization project. **Stakeholder: Survey of India (SoI)** * **Impact:** SoI, as the national nodal agency for standardization and maintenance of geographical names, will be able to leverage BHASHINI's technology to expedite the digitization process. * **Action Required:** SoI needs to integrate BHASHINI’s capabilities to convert audio recordings into structured digital text, supporting the creation of a comprehensive Toponymy Database. **Stakeholder: General Public/Citizens** * **Impact:** The standardization of toponyms will improve the reliability of place-name datasets used across governance platforms and public information systems. * **Action Required:** No direct action required from the public; benefit from improved data reliability and accessibility. **Stakeholder: Governance and Disaster Management Entities** * **Impact:** Accurate and standardized toponymic data will aid in disaster management, infrastructure planning, and citizen services. * **Action Required:** Utilize the improved toponymic datasets for better planning and response in disaster management and governance.

Key Entities Referenced

Digital India BHASHINI Division: Division under the Ministry of Electronics and Information Technology (MeitY) focused on language AI, partnering to contribute speech and language AI for toponymic data digitization. Survey of India: The national nodal agency for standardization and maintenance of geographical names, collaborating to digitize toponymic data. National Geospatial Policy, 2022: A policy document setting the context for the collaboration on toponymic data. National Geographical Name Information System (NGNIS): A system whose development the collaboration aims to support through efficient processing of field-collected audio data.
Official Source Record View Original Source →
See Full Document Text
Ministry of Electronics & IT Signing of Memorandum of Understanding (MoU) between Digital India BHASHINI Division and Survey of India for Toponymic Data Digitisation प्रव तथ: 21 JAN 2026 2:30PM by PIB Delhi The Digital India BHASHINI Division (DIBD), Ministry of Electronics and Information Technology (MeitY), signed a Memorandum of Understanding (MoU) with the Survey of India (SoI) on 20 January 2026 to support the digitisation, transcription and standardisation of geographical place names (toponyms) using AI-based speech and language technologies. The collaboration will strengthen the creation of accurate, multilingual and standardised toponymic datasets aligned with the National Geospatial Policy, 2022. The Survey of India, as the national nodal agency for standardisation and maintenance of geographical names, undertakes large-scale toponymic field surveys to collect place names in local vernacular languages for integration into national mapping systems. Under this collaboration, BHASHINI’s speech-to-text and language processing capabilities will be used to convert large volumes of audio recordings of place names into structured digital text, supporting the creation of a comprehensive and validated Toponymy Database covering more than 16 lakh locations. The collaboration will support the development of the National Geographical Name Information System (NGNIS) by enabling efficient processing of field-collected audio data into local language scripts, Devanagari, Roman and other formats, ensuring consistency across national maps, digital platforms and governance systems. The integration of automatic speech recognition, language normalisation and validation workflows will significantly enhance the speed, accuracy and scale of toponym data processing. The initiative will also strengthen audio documentation of place names, preserving correct pronunciation and local linguistic variations, while enabling systematic standardisation through alignment with the Survey of India Toponymy Manual and Bureau of Indian Standards (BIS) code of practices. This will improve the reliability of place-name datasets used across Open Series Maps, governance platforms and public information systems. Through this partnership, the Digital India BHASHINI Division will contribute its speech and language AI portfolio to support data creation, annotation and validation pipelines, enabling large- scale conversion of human speech into high-quality geospatial language datasets. The collaboration reflects BHASHINI’s approach of embedding language AI across national digital public infrastructure systems where linguistic accuracy is critical for service delivery and decision-making. The MoU reinforces the role of language technologies in strengthening India’s geospatial ecosystem, ensuring that place names across regions and dialects are accurately captured, preserved and standardised for governance, disaster management, infrastructure planning and citizen services. The collaboration aligns with the Government of India’s vision of building indigenous, AI-enabled digital infrastructure rooted in Indian linguistic realities.**** MSZ (रलीज़ आईडी: 2216831) आगंतुक पटल : 270 इस वज्ञ को इन भाषाओ ंम पढ़: Urdu , ही

Continue your research