The largest academic centre of speech and language technology in South Asia, conducting research on both basic and applied aspects of language technology.
Anusaaraka is a machine translation tool being developed by the Chinmaya International Foundation (CIF), International Institute of Information Technology, Hyderabad (IIIT-H) and University of Hyderabad (Department of Sanskrit Studies).
Paninian Grammar · Sanskrit Processing · Language Translation
Explore lab Information Retrieval and Extraction LabThe Information Retrieval and Extraction Lab (iREL) focuses on solving research problems in the areas of Information Retrieval (IR), Extraction (IE) and Access (IA).
Information Retrieval · Social Media Analysis · Text Summarization · Text Generation
Explore lab Speech and Vision ResearchThe Speech Processing Lab (SPL) conducts goal-led research in speech and spoken language technologies, with a focus on Indian languages. The lab builds intelligent systems for automatic speech recognition (ASR), text-to-speech synthesis (TTS), speech translation, spoken and audio retrieval, speech biometrics, speaker and language identification, and emotion recognition, including a phonetic engine and secure voice-based access to information. Its research addresses the challenges of multilinguality, diverse accents, low-resource languages, and real-world acoustic conditions. By combining fundamental research with practical applications, the lab aims to build accessible and inclusive speech technologies for education, healthcare, digital governance, and human-computer interaction.
Speech Recognition · Text-to-Speech Synthesis · Speaker Recognition · Language Identification · Emotion Recognition
Explore lab Machine Translation and Natural Language ProcessingThe MT-NLP Lab at LTRC, IIIT-H, focuses on a wide range of NLP problems including syntax and parsing, semantics, discourse processing, machine translation, and computational models inspired by linguistics and machine learning.
Computational Grammatical Model · Parsing · Machine Translation · Semantics · Dialogue and Discourse Analysis
Explore labTo mark its Silver Jubilee, LTRC launched free-to-download BhashaVerse language resources and machine translation models. The multitask encoder-decoder model can translate across 36 Indian languages including Tulu, Bodo, Bhojpuri, Magahi, and Santhali.
ReleaseLanguage Technologies Research Centre celebrated 25 years of completion with a two-day event featuring talks and panel discussions on the vision, mission, evolution and future of language technologies.
EventLTRC announced the development of BhashaVerse LLM decoder model for 36 Indian languages for summarisations, Q&A and more. Also released 10 billion Bhashik datasets for Indian language pairs.
ReleaseA community of 19 faculty and 69 research students working across our labs.
No events scheduled this month.
This month
The 14th edition of the Summer School Series focused on Speech Large Language Models (Speech LLMs). Includes a 2-day pre-school session, expert lectures, hands-on sessions, and guided projects.
LTRC, IIIT Hyderabad
Learn moreFrom undergraduate foundations to doctoral seminars, the LTRC curriculum spans the breadth of natural language processing, speech and language technology — taught by the same faculty who lead the centre's research.
Explore our research, meet the people behind it, or get in touch with the centre.
