Mandar Gogate
mandar gogate

Dr. Mandar Gogate

Senior Research Fellow

 0131 455 4793

  M.Gogate@napier.ac.uk

   

Biography

Dr Mandar Gogate is an EPSRC Research Fellow at Edinburgh Napier University’s School of Computing specialising in real-time speech enhancement, multimodal signal processing, and machine learning. Mandar graduated with a B.Eng (highest 1st Class Honours with distinction) in Electrical and Electronic Engineering at India’s top Birla Institute of Technology & Science, Pilani. He was awarded a PhD degree in Computing Science by Edinburgh Napier University in 2020.

Previously, he worked as an invited Research Scientist at Amazon and ENSTA ParisTech - École Nationale Supérieure de Techniques Avancées, Paris, France where he researched multimodal robotic sensor fusion technologies, incremental learning and dynamic advertising. He has also been an invited visiting research fellow at Sonova AG (Switzerland), MIT (Synthetic Intelligence Lab), and University of Oxford (Computational Neuroscience Lab).

His research interests are interdisciplinary, and include: real-time audio-visual enhancement, multimodal fusion, incremental learning, natural language processing, computer vision, sentiment and emotion analysis, privacy-preserving machine learning, explainable and ‘human-in-the-loop’ artificial intelligence, IoT, wireless sensing and 5G communications. Real-world applications range from cognitive robotics and assistive healthcare technologies to ​​automated social media analytics for security, business intelligence and industry 4.0.

School

Research Groups

Research Areas

Esteem

Conference Organising Activity

  • Interspeech 2024 Satellite Workshop - 3rd COG-MHEAR Audio-Visual Speech Enhancement Challenge (AVSEC-3)

 

Spin-outs and Licences

  • Patent: Deep Cognitive Neural Network (DCNN)

 

Visiting Positions

  • Academia Sinica, Taipei, Taiwan

 

Filter by

Date


51 results

Robust Real-time Audio-Visual Speech Enhancement based on DNN and GAN

Journal Article
Gogate, M., Dashtipour, K., & Hussain, A. (in press)
Robust Real-time Audio-Visual Speech Enhancement based on DNN and GAN. IEEE Transactions on Artificial Intelligence, https://doi.org/10.1109/tai.2024.3366141
The human auditory cortex contextually integrates audio-visual (AV) cues to better understand speech in a cocktail party situation. Recent studies have shown that AV speech en...

A hybrid dependency-based approach for Urdu sentiment analysis

Journal Article
Sehar, U., Kanwal, S., Allheeib, N. I., Almari, S., Khan, F., Dashtipur, K., …Khashan, O. A. (2023)
A hybrid dependency-based approach for Urdu sentiment analysis. Scientific Reports, 13, Article 22075. https://doi.org/10.1038/s41598-023-48817-8
In the digital age, social media has emerged as a significant platform, generating a vast amount of raw data daily. This data reflects the opinions of individuals from diverse...

Formulations and Algorithms to Find Maximal and Maximum Independent Sets of Graphs

Conference Proceeding
Heal, M., Dashtipour, K., & Gogate, M. (2023)
Formulations and Algorithms to Find Maximal and Maximum Independent Sets of Graphs. In Proceedings, 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022. https://doi.org/10.1109/csci58124.2022.00097
We propose four algorithms to find maximal and maximum independent sets of graphs. Two of the algorithms are non-polynomial in time, mainly binary programming and non-convex m...

Towards Pose-Invariant Audio-Visual Speech Enhancement in the Wild for Next-Generation Multi-Modal Hearing Aids

Conference Proceeding
Gogate, M., Dashtipour, K., & Hussain, A. (2023)
Towards Pose-Invariant Audio-Visual Speech Enhancement in the Wild for Next-Generation Multi-Modal Hearing Aids. In 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). https://doi.org/10.1109/icasspw59220.2023.10192961
Classical audio-visual (AV) speech enhancement (SE) and separation methods have been successful at operating under constrained environments; however, the speech quality and in...

Sentiment Analysis Meets Explainable Artificial Intelligence: A Survey on Explainable Sentiment Analysis

Journal Article
Diwali, A., Saeedi, K., Dashtipour, K., Gogate, M., Cambria, E., & Hussain, A. (in press)
Sentiment Analysis Meets Explainable Artificial Intelligence: A Survey on Explainable Sentiment Analysis. IEEE Transactions on Affective Computing, https://doi.org/10.1109/taffc.2023.3296373
Sentiment analysis can be used to derive knowledge that is connected to emotions and opinions from textual data generated by people. As computer power has grown, and the avail...

Towards Individualised Speech Enhancement: An SNR Preference Learning System for Multi-Modal Hearing Aids

Conference Proceeding
Kirton-Wingate, J., Ahmed, S., Gogate, M., Tsao, Y., & Hussain, A. (2023)
Towards Individualised Speech Enhancement: An SNR Preference Learning System for Multi-Modal Hearing Aids. In K. Dashtipour (Ed.), Proceedings of the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). https://doi.org/10.1109/icasspw59220.2023.10193122
Since the advent of deep learning (DL), speech enhancement (SE) models have performed well under a variety of noise conditions. However, such systems may still introduce sonic...

Live Demonstration: Real-time Multi-modal Hearing Assistive Technology Prototype

Conference Proceeding
Gogate, M., Hussain, A., Dashtipour, K., & Hussain, A. (2023)
Live Demonstration: Real-time Multi-modal Hearing Assistive Technology Prototype. In IEEE ISCAS 2023 Symposium Proceedings. https://doi.org/10.1109/iscas46773.2023.10182070
Hearing loss affects at least 1.5 billion people globally. The WHO estimates 83% of people who could benefit from hearing aids do not use them. Barriers to HA uptake are multi...

Live Demonstration: Cloud-based Audio-Visual Speech Enhancement in Multimodal Hearing-aids

Conference Proceeding
Bishnu, A., Gupta, A., Gogate, M., Dashtipour, K., Arslan, T., Adeel, A., …Ratnarajah, T. (2023)
Live Demonstration: Cloud-based Audio-Visual Speech Enhancement in Multimodal Hearing-aids. In IEEE ISCAS 2023 Symposium Proceedings. https://doi.org/10.1109/iscas46773.2023.10182060
Hearing loss is among the most serious public health problems, affecting as much as 20% of the worldwide population. Even cutting-edge multi-channel audio-only speech enhancem...

AVSE Challenge: Audio-Visual Speech Enhancement Challenge

Conference Proceeding
Aldana Blanco, A. L., Valentini-Botinhao, C., Klejch, O., Gogate, M., Dashtipour, K., Hussain, A., & Bell, P. (2023)
AVSE Challenge: Audio-Visual Speech Enhancement Challenge. In 2022 IEEE Spoken Language Technology Workshop (SLT) (465-471). https://doi.org/10.1109/slt54892.2023.10023284
Audio-visual speech enhancement is the task of improving the quality of a speech signal when video of the speaker is available. It opens-up the opportunity of improving speech...

A Novel Frame Structure for Cloud-Based Audio-Visual Speech Enhancement in Multimodal Hearing-aids

Conference Proceeding
Bishnu, A., Gupta, A., Gogate, M., Dashtipour, K., Adeel, A., Hussain, A., …Ratnarajah, T. (2022)
A Novel Frame Structure for Cloud-Based Audio-Visual Speech Enhancement in Multimodal Hearing-aids. In 2022 IEEE International Conference on E-health Networking, Application & Services (HealthCom). https://doi.org/10.1109/healthcom54947.2022.9982772
In this paper, we design a first of its kind transceiver (PHY layer) prototype for cloud-based audio-visual (AV) speech enhancement (SE) complying with high data rate and low ...

Current Post Grad projects

Previous Post Grad projects