2018

• Nov 16:  Gave lab-talk on “Attention in neural network”.
• Sep 27: Paper Glottal inverse filtering using probabilistic weighted linear prediction accepted in IEEE/ACM Transactions on Audio, Speech, and Language Processing-2019.
• Sep 2-5:  Gave a poster presentation in Interspeech 2018, Hyderabad, India.
• July 23: Started internship in TCS research working on sleep arousal detection problem.
• July 22: “Effect of source filter interaction on isolated vowel-consonant-vowel perception” accepted for publication in JASA-EL 2018.
• June 4:  “Automatic glottis localization and segmentation in stroboscopic videos using deep neural network” and “Reconstructing neutral speech from prosthetic esophageal speech” accepted for publication in the proceedings of INTERSPEECH 2018.
• May-9: Paper PSFM- a probabilistic source-filter model for noise robust glottal closure instant detection” accepted in IEEE/ACM Transactions on Audio, Speech, and Language Processing-2018.
• Jan-20: Gave chirping talk in WISSAP-2018.

2017

• DEC-29: Gave a lab talk on “Key ideas in Connectionist temporal classification”.
• AUG-31: Gave oral presentation in EUSIPCO 2017, Kos island Greece.
  1. Pitch Prediction from Mel-generalized Cepstrum – a Computationally Efficient Pitch Modeling Approach for Speech Synthesis
• AUG-29: Gave two poster presentation in EUSIPCO 2017, Kos island Greece.
  1. Automatic Prediction of Spirometry Readings from Cough and Wheeze for Monitoring of Asthma Severity
  2. Low Resource Point Process Models for Keyword Spotting Using Unsupervised Online Learning (paper by Sadhu et.al)

• AUG-24: Gave two oral-presentation in INTERSPEECH 2017, Stockholm, Sweden
  1.  A dual source-filter model of snore audio for snorer group classification
  2. Phoneme state posteriorgram features for speech based automatic classification of speakers in cold and healthy condition. (paper by Kalkunte et.al)

• May 25: “Automatic Prediction of Spirometry Readings from Cough and Wheeze for Monitoring of Asthma Severity” and “Pitch Prediction from Mel-generalized Cepstrum – a Computationally Efficient Pitch Modeling Approach for Speech Synthesis” have been accepted for publication in the proceedings of EUSIPCO 2017.
• May 22: A dual source-filter model of snore audio for snorer group classification accepted for publication in the proceedings of INTERSPEECH 2017.
• Apr 21: Lab talk on “WaveNet: A Generative Model for Raw Audio”
• Mar 4: Gave oral presentation in NCC 2017, IITM Chennai, India
  1. Pitch Prediction from Mel-Frequency Cepstral Coefficients Using Sparse Spectrum Recovery
• Jan 24: “Pitch Prediction from Mel-Frequency Cepstral Coefficients Using Sparse Spectrum Recovery” have been accepted for publication in the proceedings of NCC 2017.

2016

• Dec 16: Lab talk on “Why does deep and cheap learning work so well?-Part II”
• Oct 28: Lab talk on “Why does deep and cheap learning work so well?-Part I”
• June 17: Lab talk on “Survey of methods for Speaker Verification–Part II”
• Feb 5:  Lab talk on “Survey of methods for Speaker Verification–Part I”

2015

• Dec 11: Lab talk on “Parametric Voice Conversion Based on Bilinear Frequency Warping Plus Amplitude Scaling”
• Sep 11: Lab talk on “Fundamentals of HMM-based speech synthesis”