Publications

• Semantic Scholar

Note

Please note that some of the published papers may be copyrighted by the respective publishing organizations, such as IEEE, Elsevier, and Wiley etc. as cited. You are advised to contact the publishing organization for final versions of the papers.

Patents

• Granted US10878807B2: "System and method for implementing a vocal user interface by combining a speech to text system and a speech to intent system". [Also granted in Europe]
• Granted US11049495B2: "Method and device for automatically learning relevance of words in a speech recognition system"
• Approved for grant US20210056958A1: "System and method for tone recognition in spoken languages"
• Approved for grant US20210055778A1: "A low-power keyword spotting system"
• Application WO2021030918A1: "User-defined keyword spotting"
• Application WO2021226709A1: "Neural architecture search with imitation learning"

Ph.D. Thesis

Vikrant Singh Tomar, McGill University, "Discriminative Manifold Learning for Automatic Speech Recognition".

Publications

• Farzaneh S Fard and Vikrant Singh Tomar, "Expediting discovery in Neural Architecture Search by Combining Learning with Planning", ICASSP 2021

• Mohamed Mhiri, Sam Myer, Vikrant Tomar, "A low latency ASR-free end to end spoken language understanding system", Interspeech 2020

• Hanwook Chung, Vikrant Tomar and Benoit Champagne, "Deep convolutional neural network-based inverse filtering approach for speech de-reverberation}", 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP){target=_blank

• Farzaneh S Fard, Arash Rad, Vikrant Singh Tomar, "Nasil: Neural Architecture Search with Imitation Learning", IEEE ICASSP 2020

• Loren Lugosch, Mirco Ravanelli, Patrick Ignoto, Vikrant Singh Tomar, Yoshua Bengio, "Speech Model Pre-training for End-to-End Spoken Language Understanding", Interspeech 2019

• Loren Lugosch, Sam Myer and Vikrant Singh Tomar, "DONUT: CTC-based Query-by-Example Keyword Spotting", NeurIPS 2018 Interpretability and Robustness for Audio, Speech and Language Workshop

• Loren Lugosch and Vikrant Singh Tomar, "Tone recognition using lifters and CTC", InterSpeech 2018

• Sam Myer and Vikrant Singh Tomar, "Efficient keyword spotting using time delay neural networks", InterSpeech 2018

• Vincent Renkens, Vikrant Singh Tomar and Hugo Van Hamme, "Incrementally learn the relevance of words in a dictionary for spoken language acquisition", IEEE Spoken Language Technology 2016

• Vikrant Singh Tomar and Richard C. Rose, "Graph based manifold regularized deep neural networks for automatic speech recognition", arXiv:1606.05925, 2016 Code on Github

• Vikrant Singh Tomar and Richard C. Rose, "Manifold Regularized Deep Neural Networks", InterSpeech 2014, Singapore. Code on Github

• Vikrant Singh Tomar and Richard C. Rose, "A family of discriminative manifold learning algorithms and their application to speech recognition", IEEE\/ACM Transactions on Audio, Speech and Language Processing, vol. 22, no. 1, Jan 2014. DOI: 10.1109/TASLP.2013.2286906

• Vikrant Singh Tomar and Richard C. Rose, "Locality Sensitive Hashing for Fast Computation of Correlational Manifold Learning based Feature space Transformations", InterSpeech 2013, Lyon, France

• Vikrant Singh Tomar and Richard C. Rose, "Efficient manifold learning for speech Recognition using locality sensitive hashing", ICASSP 2013, Vancouver, Canada

• Vikrant Singh Tomar and Richard C. Rose, "Noise aware manifold learning for robust speech recognition", ICASSP 2013, Vancouver, Canada.

• Vikrant Singh Tomar and Richard C. Rose, "A Correlational Discriminant Approach to Feature Extraction for Robust Speech Recognition", InterSpeech 2012, Portland, Oregon, USA

• Vikrant Singh Tomar and Richard C. Rose, "Application of a Locality Preserving Discriminant Analysis Approach to ASR 2012, Montreal, QC, Canada. }",The 11th International Conference on Information Sciences, Signal Processing and their Applications (ISSPA){target=_blankDownload presentation .pdf

• Vikrant Tomar and H. A. Patil, "On the Development of Variable length Teager Energy Operator (VTEO){target=_blank}", Interspeech 2008, Brisbane, Australia, pp.1056 - 1059

• H. Venkataraman, D. Gandhi, and Vikrant Tomar," Multi-hop Multi-band Intelligent Relay-Based Architecture for LTE-Advanced Multi-hop Wireless Cellular Networks", Springer Wireless Personal Communications, 2013. DOI 10.1007/s11277-013-1352-0

• Vikrant Tomar, H. Asnani, A. Karandikar, and P. Kapadia, "Traffic Analysis of a Short Message Service Network", IEEE NCC 2010

• Vikrant Tomar, H. Asnani, A. Karandikar, V. Chander, S. Agrawal, and P. Kapadia, "Social Network Analysis of the Short Message Service", IEEE NCC 2010 , 29-31 Jan. 2010 DOI: 10.1109/NCC.2010.5430162

• Vikrant Tomar, D. Gandhi and C. Vijaykumar, "Digital Signal Processing for Gene Prediction", TENCON 2008 - 23rd IEEE Region 10 Conference, 19-21 Nov. 2008, Hydrabad, India, 2008. DOI: 10.1109/TENCON.2008.4766648

Other Publications/Reports

• Vikrant Singh Tomar, "Speaker Variability in Automatic Speech Recognition"

• Vikrant Singh Tomar, "Blind Dereverberation using Maximum Kurtosis of the Speech Residual" download presentation .pdf

• Vikrant Singh Tomar, "Discriminant Feature Space Transformations for Automatic Speech Recognition" download presentation .pdf