Welcome!

Welcome to the webpage of Multimodal Information Processing Systems (MiPS) Lab. Our primary focus is on acquisition, processing, summarization, and delivery of multimodal information (audio, video, images, text, and other sensory forms of information) to users in simple and appropriate versions. Our focus is on conducting research on developing socially relevant applications which span the broad areas of speech, audio, music, video, multimedia,Indian language text. Our specific areas of focus include Sensor Array and Multi Channel Signal Processing, Spatial Audio Processing, 3D printed Bionic Ears, Augmented and Virtual Reality, Multimodal Signal Processing and Information Fusion, and Speech Signal Processing and Recognition of Indian Languages, and ICT for development of Socially Relevant Applications. The Lab is equipped with State of the Art Audio-Visual Arrays, Voice Servers, 3D printing facility, Loud speaker Arrays, song other equipment. Several applications like Digital Mandi for the Indian Kisan, Intelligent Video Retrieval, Audio and Video Analyser,have been developed at the Lab and transferred to Industry like BSNL and LG. We are also proud of our alumni are now working as faculty at IITs and NITs..

News

 

Paper accepted at IEEE/ACM Transaction on Acoustics,Speech and Language Processing, sep 2019. Congrats Vishnu!
Aditya Raikar successfully defends his M S(R) thesis. Congrats Aditya!
Artificial Intelligence and Machine Learning for Future 5G Wireless Networks @ IEEE-BIS Seminar 2018 (Press Coverage)
Invited Lectures on Spatial Audio Processing at WiSSAP 2017, Tutorial on Array Signal Processing at NCC 2017
Development of Bionic Ears for Spatial Audio Applications
Technology Transfer of Digital Mandi System to BSNL : A White Paper
Broad Band Applications for Model Village (Photos) (Economic Times Telecom - Interview)
SMS Compression for Indian Languages
Digital Mandi for Indian Kisan Launch, Coverage in The Hindu

More News...