Mrinmoy Bhattacharjee

Mrinmoy Bhattacharjee
Indian Institute of Technology Guwahati | IIT Guwahati · Electronics and Electrical Engineering (EEE)

Doctor of Philosophy

About

11
Publications
1,100
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
18
Citations
Introduction
I am currently pursuing a Ph. D. degree from the Indian Institute of Technology Guwahati. My Ph.D. thesis is based on the analysis of speech and music signals in movie audio for genre classification of movies. My research interests include speech/music classification, foreground/background audio separation, shouted speech detection, dialect identification, and speaker verification/identification. I regularly employ various signal processing and machine/deep learning based solutions in my work.
Additional affiliations
January 2016 - present
Indian Institute of Technology Guwahati
Position
  • Researcher
January 2016 - December 2020
Indian Institute of Technology Guwahati
Position
  • PhD (Pursuing)
August 2014 - December 2015
Indian Institute of Technology Guwahati
Position
  • Assistant Project Engineer
Education
January 2016 - May 2020
Indian Institute of Technology Guwahati
Field of study
  • Pattern Recognition
July 2012 - July 2014
National Institute of Technology Raipur
Field of study
  • Computer Technology
May 2007 - July 2011
Assam University
Field of study
  • Information Technology

Publications

Publications (11)
Article
Detection of speech and music is an essential preprocessing step for many high-level audio-based applications like speaker diarization and music information retrieval. Researchers have previously used various magnitude-based features in this task. In comparison, the phase spectrum has received lesser attention. The phase of a signal is believed to...
Article
Detection of speech and music signals in isolated and overlapped conditions is an essential preprocessing step for many audio applications. Speech signals have wavy and continuous harmonics, while music signals exhibit horizontally linear and discontinuous harmonic patterns. Music signals also contain more percussive components than speech signals,...
Conference Paper
Full-text available
Shouted speech detection is an essential pre-processing step in conventional speech processing systems such as speech and speaker recognition, speaker diarization, and others. Excitation source plays an important role in shouted speech production. This work explores feature computed from the Integrated Linear Prediction Residual (ILPR) signal for s...
Article
Spectrograms of speech and music contain distinct striation patterns. Traditional features represent various properties of the audio signal but do not necessarily capture such patterns. This work proposes to model such spectrogram patterns using a novel Spectral Peak Tracking (SPT) approach. Two novel time-frequency features for speech vs. music cl...
Chapter
Full-text available
Automatic shouted speech detection systems usually model its spectral characteristics to differentiate it from normal speech. Mostly hand-crafted features have been explored for shouted speech detection. However, many works on audio processing suggest that approaches based on automatic feature learning are more robust than hand-crafted feature engi...
Preprint
Full-text available
Distinct striation patterns are observed in the spectrograms of speech and music. This motivated us to propose three novel time-frequency features for speech-music classification. These features are extracted in two stages. First, a preset number of prominent spectral peak locations are identified from the spectra of each frame. These important pea...
Conference Paper
Full-text available
Recently Wireless Sensor Networks (WSNs) have garnered a great interest among the research community. WSNs are heavily energy constrained and hence redundant nodes in the network must be allowed to sleep so that the network lifetime may be enhanced. Recently a lot of work has been done to determine the amount of redundancy inherent in a WSN. This p...

Network

Cited By