Dr

Pulkit Sharma PhD

Post-doctoral Research Assistant

  • Biography
  • Research
  • Publications

Biography

Dr Pulkit Sharma undertook his doctoral research in the School of Computing and Electrical Engineering at the Indian Institute of Technology (IIT) in Mandi, India, submitting in 2017. This followed his M.E. degree in Electronics and Communication Engineering from Panjab University, India, in 2012.

Pulkit's doctoral work focused on the use of sparse representation-based signal processing to derive features for speech recognition and footprint reduction of speech synthesis systems. During his PhD, he demonstrated the effectiveness of deep sparse representations to derive discriminative features for speech recognition.

Pulkit joined the Computational Health Informatics Lab to develop systems based on machine learning for analysing data from electronic healthcare records, in collaboration with the Oxford University Hospitals NHS Foundation Trust.

Personal website
Google Scholar

Research Interests

  • Healthcare Informatics
  • Representation Learning
  • Speech Signal Processing
  • Sparse Representations
  • Compressed Sensing

Related Academics

Selected Publications

Journals

  • A. Thakur, V. Abrol, P. Sharma and P. Rajan, “ Compressed Convex Spectral Embedding for bird species classification.”, The Journal of the Acoustical Society of America, vol. 143, 2018.
  • P. Sharma, V. Abrol, Nivedita and A. K. Sao, "Reducing footprint in unit selection based text-to-speech system using compressed sensing and sparse representation'', Computer Speech and Language, Elsevier, 2018.
  • P. Sharma, V. Abrol, A. D. Dileep and A. K. Sao, "Sparse coding based features for speech units classification", Computer Speech and Language, Elsevier, vol. 47, pp. 333-350, 2018.
  • P. Sharma, V.Abrol, and A. K. Sao, "Deep sparse representation based features for speech recognition", IEEE/ACM Transactions on Audio Speech and Language Processing, vol. 25, pp. 2162-2175, 2017.
  • V. Abrol, P. Sharma and A. K. Sao, "Greedy double sparse dictionary for sparse representation of speech signals", Speech Communication, Elsevier vol. 85, pp 71-82, 2016.
  • V. Abrol, P. Sharma and A. K. Sao, "Greedy dictionary learning for kernel sparse representation based classifier", PR Letters, Elsevier vol. 78, pp. 64 - 69, 2016.
  • V. Abrol, P. Sharma and A. K. Sao, "Voiced/Nonvoiced detection in compressively sensed speech signals", Speech Communication, Elsevier vol. 72, pp. 194 - 207, 2015.

Conferences

  •  P. Sharma, V. Abrol and A. Thakur, "ASe: Acoustic scene embedding using Deep archetypal analysis and GMM", in Proc. ISCA 19th Annual Conference (INTERSPEECH), 2018, Hyderabad, India.
  • A. Thakur, V. Abrol, P. Sharma and P. Rajan, "Deep Convex Representations: Feature Representations for Bioacoustics Classification", in Proc. ISCA 19th Annual Conference (INTERSPEECH), 2018, Hyderabad, India.
  • A. Thakur, V. Abrol, P. Sharma and P. Rajan, “ Compressed Convex Spectral Embedding for bird species classification”, in Proc. IEEE 43rd International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, Calgary, Canada.
  • V. Abrol, P. Sharma, and A. Thakur, "Gaussian mixture modeling and archetypal analysis (GMM-AA) based system for acoustic scene classification", Tech report DCASE 2017.
  • A. Thakur, V. Abrol, P. Sharma, and P. Rajan, "Renyi entropy based mutual information for bird vocalization segmentation", MLSP 2017, Tokyo, Japan.
  • V. Abrol, P. Sharma, A. Thakur, P. Rajan, A. D. Dileep and A. K. Sao, "Archetypal analysis based sparse convex sequence kernel for bird activity detection", in Proc. EURASIP 25 th European Signal Processing Conference (EUSIPCO), 2017, Kos Island, Greece.
  • P. Sharma, V. Abrol, A. D. Dileep and A. K. Sao, "Class specific GMM based sparse feature for speech unit classification", in Proc. EURASIP 25 th European Signal Processing Conference (EUSIPCO), 2017, Kos Island, Greece.
  • V. Abrol, P. Sharma and A. K. Sao, "Finding Archetypes by Exploiting Sparsity of Convex Representations", in Proc. 6th Signal Processing with Adaptive Sparse Structured Representations (SPARS) workshop ", 2017, Lisbon, Portugal.
  • V. Abrol, P. Sharma and A. K. Sao, "Fast exemplar selection algorithm for matrix approximation and representation: A variant oASIS algorithm", in Proc. 42nd International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, New Orleans, USA.
  • V. Abrol, P. Sharma, Shahrooz F. Roohi, A. K. Sao and Ashraf A. Kassim, "Fast and robust fMRI unmixing using hierarchical dictionary learning", in Proc. 23rd International Conference on Image Processing (ICIP), 2016, Phoenix, USA.
  • V. Abrol, P. Sharma and A. K. Sao, "Making Sense of Randomness: Fast Signal Recovery from Compressive Samples", in Proc. 24th European Signal Processing Conference (EUSIPCO), 2016, Budapest, Hungary.
  • P. Sharma and V. Abrol and A. Sachdev and A. D. Dileep and A. K. Sao, "Speech emotion recognition using kernel sparse representation based classifier", in Proc. 24th European Signal Processing Conference (EUSIPCO), 2016, Budapest, Hungary.
  • V. Abrol, P. Sharma and A. K. Sao, "Randomness is sufficient! Approximate recovery from CS samples", in Proc. 3rd International Traveling Workshop on Interactions between Sparse Models and technology (iTWIST), 2016, Aalborg, Denmark.
  • P. Sharma, V. Abrol and A. K. Sao, "Learned dictionaries for sparse representation based unit selection speech synthesis", in Proc. 22nd IEEE National Conference on Communication (NCC), 2016, Guwahati, India.
  • P. Sharma, V. Abrol, A. D. Dileep and A. K. Sao, "Sparse coding based features for speech units classification", in Proc. ISCA 16th Annual Conference (INTERSPEECH), 2015, Dresden, Germany.
  • P. Sharma, V. Abrol and A. K. Sao, "Compressed sensing for unit selection based Speech Synthesis", in Proc. 23rd European Signal Processing Conference (EUSIPCO), 2015, Nice, France.
  • P. Sharma, V. Abrol and A. K. Sao, "Supervised speech enhancement using compressed sensing", in Proc. 21st IEEE National Conference on Communication (NCC), 2015, Mumbai, India.
  • V. Abrol, P. Sharma and A. K. Sao, "Speech enhancement using compressed sensing", in Proc. ISCA 14th Annual Conference (INTERSPEECH), August, 2013, Lyon, France.