News - Events

   Speech & Audio
   Pervasive Computing

   Mobile Multimodal Mandi
   Intelligent Video Retrieval
   Dynamic Camera Steering

Industrial Collaborators
[Lab WiKi]

 Paper on Music Tempo Estimation accepted Interspeech 2017. Congrats Sheyan and Prof. Tanaya.
 Journal paper accepted at Multimedia Tools and Applications, Springer. Congrats Dr. Waquar Ahmad.
 One accepted paper at ICASSP 2017. Congrats Vishnu.
 Dr. Lalan Kumar, Alumni of MIPS lab is now Asst. Professor in EE at IIT Delhi.
 Yoshitaka Ohshio from Ritsumeikan University Japan is on a short internship at the Lab.
   Welcome Yoshi!

 Development MiPS Lab Mannequin with Bionic Ears for spatial audio applications completed.
   Congrats to Sandeep.

 Two Papers on Spatial Audio accepted at EUSIPCO 2016. Congrats Sandeep, Lavisha, and Rishika.
 Two Accepted Papers at SPCOM 2016. Congrats to Sandeep, Sourya, and Shivam.
 Paper on Near Field Beamforming in SH Domain Accepted at IEEE Transactions on Signal Processing.
   Congrats to Lalan.

 Two Accepted Papers at ICASSP 2016. Congrats to Isha and Lalan.
 Waquar Ahmad successfully defends his Ph.D thesis. Congrats Dr. Waquar Ahmad.
 Dr. Hegde chaired a Session on Computational Auditory Scene Analysis at Interspeech 2015-Dresden
 Panel Presentation on Broad Band Applications for Model Village at Telecom Summit 2015 by
   Dr.Rajesh Hegde [
more news...

Research at MiPS Lab focuses on two major but highly correlated scientific areas namely, Digital Signal Processing (DSP) and Human computer Interaction (HCI) using multiple modes of information. The other area of research focus at MiPS Lab is multi media signal processing which will feed into the efficient design of multi modal interfaces.

The following are the topics of research interest :
 Speech Signal Processing and Recognition
 Multi modal Signal Processing (Speech, Video, and Text)
 Fusion and Fission of Multi modal information
 Multi modal Information Retrieval using Speech and Video Signal Processing
 Pervasive Computing
 Application of Signal processing in Wireless Networks

The following are the current target applications :
 A Composite Multi modal data collection, summarization, delivery and retrieval testbed that can help common as well as the city folk in India
 Multi modal Video retrieval using other modalities like speech and text.
 Multi modal Data access and delivery on cell phones on a service based or personalized model
 Speech enhancement algorithms for use on mobile devices

Research at MiPS Lab is currently funded by Department of Electronics & Information Technology (Deity), Department of Science & Technology (DST), Bharat Sanchar Nigam Limted (BSNL), Samsung Research Institute , LG Soft India . We are looking for sponsors who would like to pursue a relation with MiPS Lab@IIT Kanpur.