Jitendra Kumar Dhiman

PhD 2021

Biography

Jitendra Kumar Dhiman received the B.Tech. degree in Electronics and Telecommunication Engineering from the Institution of Electronics and Telecommunication Engineering (IETE), Delhi, in 2010, and the M.Tech. degree in Signal Processing from the Indian Institute of Technology Hyderabad in 2013.He subsequently worked as a Project Assistant in the Spectrum Lab, Department of Electrical Engineering, Indian Institute of Science (IISc), Bangalore, where he contributed to a Department of Electronics and Information Technology (DeitY)–funded project focused on prosody modification of speech. He later enrolled for a Ph.D. in the same laboratory, where his research addressed key challenges in speech signal processing and related machine learning techniques.Following his academic training, he joined Samsung Research and Development Lab, Bangalore, where he worked as a Chief Engineer, contributing to advanced research and development in speech and audio technologies. He is currently working as a Senior Lead Engineer in the Audio Research and Development Group at Qualcomm, where he is involved in the design and development of state-of-the-art audio and speech processing solutions.His research interests include speech signal processing, audio signal processing, and machine learning. He is a recipient of the Best Poster Award at the IISc EECS Divisional Symposium in 2018 and the Pratiksha Trust Travel Fellowship in 2019.

Publications

2020

Speech Commun. 20

Musical noise suppression using a low-rank and sparse matrix decomposition approach

J. Sadasivan, J. K. Dhiman, and C. S. Seelamantula

Speech Communication, 2020

BIB URL

@article{sadasivan2020musical,
  author = {Sadasivan, J. and Dhiman, J. K. and Seelamantula, C. S.},
  journal = {Speech Communication},
  pages = {41--52},
  title = {Musical noise suppression using a low-rank and sparse matrix decomposition approach},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:4fGpz3EwCPoC},
  volume = {125},
  year = {2020}
}

2019

ICASSP 19

A Spectro-temporal Technique for Estimating Aperiodicity and Voiced/unvoiced Decision Boundaries of Speech Signals

J. K. Dhiman, and C. S. Seelamantula

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019

BIB URL

@inproceedings{dhiman2019spectro,
  author = {Dhiman, J. K. and Seelamantula, C. S.},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {A Spectro-temporal Technique for Estimating Aperiodicity and Voiced/unvoiced Decision Boundaries of Speech Signals},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:VaXvl8Fpj5cC},
  year = {2019}
}

INTERSPEECH 19

On the Suitability of the Riesz Spectro-Temporal Envelope for WaveNet Based Speech Synthesis

J. K. Dhiman , N. Adiga, and C. S. Seelamantula

In INTERSPEECH, 2019

BIB URL

@inproceedings{dhiman2019suitability,
  author = {Dhiman, J. K. and Adiga, N. and Seelamantula, C. S.},
  booktitle = {INTERSPEECH},
  pages = {944--948},
  title = {On the Suitability of the Riesz Spectro-Temporal Envelope for WaveNet Based Speech Synthesis},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:Dip1O2bNi0gC},
  year = {2019}
}

2018

INTERSPEECH 18

Multicomponent 2-D AM-FM Modeling of Speech Spectrograms

J. K. Dhiman, N. Sharma, and C. S. Seelamantula

In INTERSPEECH, 2018

BIB URL

@inproceedings{dhiman2018multicomponent,
  author = {Dhiman, J. K. and Sharma, N. and Seelamantula, C. S.},
  booktitle = {INTERSPEECH},
  pages = {736--740},
  title = {Multicomponent 2-D AM-FM Modeling of Speech Spectrograms},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:ILKRHgRFtOwC},
  year = {2018}
}

2017

INTERSPEECH 17

A Spectro-Temporal Demodulation Technique for Pitch Estimation

J. K. Dhiman , N. Adiga, and C. S. Seelamantula

In INTERSPEECH, 2017

BIB URL

@inproceedings{dhiman2017spectro,
  author = {Dhiman, J. K. and Adiga, N. and Seelamantula, C. S.},
  booktitle = {INTERSPEECH},
  pages = {2306--2310},
  title = {A Spectro-Temporal Demodulation Technique for Pitch Estimation},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:yB1At4FlUx8C},
  year = {2017}
}

INTERSPEECH 17

Time-Frequency Coherence for Periodic-Aperiodic Decomposition of Speech Signals

K. Vijayan, J. K. Dhiman, and C. S. Seelamantula

In Interspeech, 2017

BIB URL

@inproceedings{vijayan2017time,
  author = {Vijayan, K. and Dhiman, J. K. and Seelamantula, C. S.},
  booktitle = {Interspeech},
  pages = {329--333},
  title = {Time-Frequency Coherence for Periodic-Aperiodic Decomposition of Speech Signals},
  url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:nrtMV_XWKgEC},
  year = {2017}
}