Submitted papers
Journal Submitted Papers:
- TV Sreenivas and Ch. Srikanth Raj: ''Comparison of greedy reconstruction algorithms for CS signal
- recovery," submitted to IET Signal Processing, Dec 2010.
- Mrugesh R Gajjar, TV Sreenivas and R Govindarajan, ''Fast Computation of Gaussian Likelihoods using Low-rank Matrix Approximations," submitted to Computer, Speech and Language (AP), Jun 2010.
- M.R. Gajjar, T.V. Sreenivas and R. Govindarajan, “Fast acoustic likelihood computation through optimum low-rank approximation of likelihood matrix,” submitted to IEEE Signal Proc. Letters, May 2009.
- Achintya Kundu, Saikat Chatterjee, and TV Sreenivas: “Split Vector Enhancement of Noisy Speech Using Gaussian Mixture Model,” IEEE Tr. Audio, Speech and Lang. Proc., under review, May 2008.
- Chandra Sekhar, S. and TV Sreenivas: “Multiband AM-FM quantization using perceptual criteria,” revision under review, IEEE Tr. Audio, Speech and Lang. Proc., Dec 2008.
- Saikat Chatterjee and TV Sreenivas: “Low complexity and scalable VQ of wideband LSFs using GMM with uncorrelated Gaussians,” revision under review, IEEE Tr. Audio, Speech and Lang. Proc., Mar 2008.
- Achintya Kundu, Saikat Chatterjee and TV Sreenivas: “ Transform Domain Split Vector Enhancement of Noisy Speech Using Gaussian Mixture Model,” submitted to IEEE Signal Proc. Letters, Apr 2008.
- Saikat Chatterjee and TV Sreenivas: “Analysis-by-synthesis Based Switched Transform Domain Split VQ Using Gaussian Mixture Model,” submitted to IEEE Sig. Proc. Letters Feb 2008.
- Chandra Sekhar S and TV Sreenivas: “Zero-crossing based envelope and frequency estimation,” IEEE Trans. Audio, Speech and Lang. Proc., Jan 2007. (not accepted)
- Basavaraja SV and TV Sreenivas: “Acoustic Sub-word units and Robust Language Modeling for Spoken Language Identification,” not accepted IEEE Trans. Audio, Speech and Lang. Proc., Feb 2007.
- Suresh K and TV Sreenivas: “Direct MDCT domain psychoacoustic modeling,” not accepted EURASIP J. App. Signal Proc., Jan 2007.
- Saikat Chatterjee and TV Sreenivas: “Delay-less Quantization of Correlated Gaussian Random Variables using Conditional PDF,” submitted to DSP Review Journal, Jan 2007.
- Harash K. Sharma and TV Sreenivas: “Experimental Evaluation of Discriminant Measures for Speaker Segmentation,” IEEE Signal Processing Letters, March 2005. (not accepted)
- Prasanta K. Ghosh, Anindya Sarkar and TV Sreenivas: “ALCR and ESTL: Novel temporal features and their application to speech segmentation,” submitted to Signal Processing (Elsevier), May 2006.
- Prasanta K. Ghosh and TV Sreenivas: “Extrema based unwarping for time-varying pitch estimation,” IEEE Signal Proc. Letters, Sep 2005. (not accepted)
- Prasanta K. Ghosh and TV Sreenivas: “Signal reconstruction from non-uniform samples and its application to speech coding,” Revision submitted to Signal Processing Journal (Elsevier), Feb 2006.
- Saikat Chatterjee and TV Sreenivas: “Transparent quality LSF quantization using 2-D DPCM and MIHMW distance measure,” IEEE Trans. Speech and Audio Proc., July 2005. (not accepted)
- A Sreenivasa Murthy, S Chandra Sekhar and TV Sreenivas: “Adaptive window minimum mean square error estimation,” submitted to IEEE Trans. Signal Proc., Apr 2004. (not accepted)
- S Chandra Sekhar and TV Sreenivas: “Time-varying filtering for improved IF estimation,” submitted to IEE Electronic Letters,, May 2004.
- Mukundh N and TV Sreenivas: ‘Product-HMM: A novel class of HMMs for sub-sequence modelling,’ submitted to J. Acoust. Soc. Am., March 2002. (not accepted)
- GSV Uma Kishore and TV Sreenivas: ‘Robust word boundary detection in noise,’ submitted to IEEE Signal Proc. Letters, Jan 2002.
- TV Sreenivas and S Stalin, ‘Pruned neural network dichotomizer for phoneme classification,’ submitted to IEE Proc. Vision, Image and Signal Processing. (not accepted)
- TV Sreenivas and S Stalin, ‘Decision region expansion in neural network classifiers,’ submitted to Pattern Recognition Letters Feb 1996. (not accepted)
- AS Prabhavathy and TV Sreenivas, ‘Robust frequency estimation using multi-level crossing intervals,’ submitted to J. Acoust. Soc. Am.
- TV Sreenivas and RJ Niederjohn, ‘Growing Line Segment (GLS) algorithm for determining formant contours from noisy spectral data,’ submitted to Speech Communication.
Conference Submitted Papers:
- Neeraj K. Sharma. and T.V. Sreenivas, ''Enhanced Stochastic Resonance model for Multi-tone Detection,"submitted to Proc. IEEE Int Conf. Acoust. Speech, Signal Proc.(ICASSP), Kyoto, Mar 2012.
- Harshavardhan, S. and T.V. Sreenivas, ''REGION SHRINKING AND NON-LINEAR OPTIMIZATION
- FRAMEWORK FOR REVERBERANT SPEECH SOURCE LOCALIZATION," submitted to Proc. IEEE
- Int Conf. Acoust. Speech, Signal Proc.(ICASSP), Kyoto, Mar 2012.
- Harshavardhan, S. and T.V. Sreenivas, ''CONFIDENCE OF TIME DELAY ESTIMATES: A NOVEL
- APPROACH AND APPLICATION TO ACOUSTIC SOURCE LOCALIZATION," submitted to IEEE
- Asilomar Conf. Signals, Systems, and Computers, Nov. 2011
- Harshavardhan, S. and T.V. Sreenivas, ''LOCALIZATION THROUGH REGION SHRINKING USING
- SIGN OF TIME DELAY ESTIMATES," submitted to IEEE Asilomar Conf. Signals, Systems, and
- Computers, Nov. 2011.
- T. Vijaykumar, Harshavardhan, S. T.V. Sreenivas, ''A GMM BASED MAXIMUM LIKELIHOOD AP-
- PROACH TO GLOBAL SEGMENTATION OF POLYPHONIC MUSIC," submitted to Interspeech, Aug
- 2011.
- Neeraj K. Sharma and T.V. Sreenivas, ''Stochastic Resonance Based Multitone Detection: An Auditory Model Linkage," submitted to Interspeech, Aug. 2011.
- Sayan Ghosh, K. Vijay Girish and T.V. Sreenivas, ''Relationship Between Indian Languages Using Bigram Language Models," submitted to Interspeech, Aug. 2011.
- Harshavardhan, S. and T.V. Sreenivas, ''INSIGHTS INTO RANDOM PLACEMENT OF MULTIPLE
- MICROPHONES FOR SOURCE LOCALIZATION" submitted to ICASSP 2011, Prague, Czek Republic.
- Tarun, K. and T.V. Sreenivas, ''Multi Sensor Compressvie Sensing of Reverberant Speech," submitted to Proc. INTERSPEECH, Chiba, Sep 2010.
- Manasa, M. and T.V Sreenivas, “Eigenspace based MLLR sub-matrix for improved Speaker Adaptation,” submitted to Interspeech 2009.
- Narayana, K.V.S. and T.V Sreenivas, “Robust Speech Recognition Using Spectro-Temporal Features and GMM Based Speech Enhancement,” submitted to Interspeech 2009.
- M.R. Gajjar, T.V Sreenivas and R. Govindarajan, “Fast acoustic likelihood computation using low-rank matrix approximation,” submitted to Interspeech 2009.
- T.V. Sreenivas and Nadir, C.I. “Matrix Quantization based speech enhancement and second stage Wiener filtering,” submitted to IEEE Int Conf. Acoust. Speech, Signal Proc., Taipei, Taiwan, Apr 2009.
- S.V. Basavaraja, T.V. Sreenivas, Sridhar G., “VOCAL/NON-VOCAL CLASSIFICATION AND SEGMENTATION OF MUSIC SIGNALS USING A DISCRIMINANT CODEBOOK APPROACH,” submitted to IEEE Int Conf. Acoust. Speech, Signal Proc., Taipei, Taiwan, Apr 2009.
- P Srinivas, V Ramasubramanian and TV Sreenivas: “Stochastic pronunciation modeling based on pruned ergodic-HMM,” submitted to IEEE Int Conf. Acoust. Speech, Signal Proc., Taipei, Taiwan, Apr 2009.
- Nishanth Ulhas Nair and T.V. Sreenivas, “SELECTIVE TRAINING FOR HIDDEN MARKOV MODELS USING VIRTUAL PATTERNS,” submitted to INTERSPEECH 2008, Brisbane, Australia, 2008.
- Saikat Chatterjee and T.V. Sreenivas, “Analysis-by-synthesis Based Switched Transform Domain Split VQ,” submitted to INTERSPEECH 2008, Brisbane, Australia, 2008.
- Krishna Nand, K. and TV Sreenivas: “INSIGHT INTO NATURE OF CONSTRAINTS IN ITERATIVE WIENER FILTERING FOR SPEECH ENHANCEMENT,” submitted to IEEE Int. Conf. Acoust. Speech and Signal Proc., 2008.
- Sriram Ganapathy and TV Sreenivas: “Eigenvoice adaptation of acoustic sub-word models,” submitted to IEEE Int. Conf. Acoust. Speech and Signal Proc., 2008.
- Nishanth Nair and TV Sreenivas: “CONSTRAINED MULTI PATTERN VITERBI ALGORITHM FOR JOINT DECODING OF MULTIPLE NOISY SPEECH PATTERNS,” submitted to IEEE Int. Conf. Acoust. Speech and Signal Proc., 2008.
- Narayana KVS and TV Sreenivas: “NOISE ROBUSTNESS OF AM-FM DECOMPOSITION USING ZERO CROSSING INTERVALS AND LOCAL PEAKS,” submitted to IEEE Int. Conf. Acoust. Speech and Signal Proc., 2008.
- Saikat Chatterjee and TV Sreenivas: “LOW COMPLEXITY WIDEBAND LSF CODING USING GMM WITH UNCORRELATED GAUSSIAN COMPONENTS AND SUBSET MIXTURE SEARCHING,” submitted to IEEE Int. Conf. Acoust. Speech and Signal Proc., 2008.
- Suresh K and TV Sreenivas: “DCT-II DOMAIN LINEAR FILTERINGWITH LOWER COMPLEXITY,”submitted to IEEE Int. Conf. Acoust. Speech and Signal Proc., 2008.
- Basavaraja SV and TV Sreenivas: “MULTILINGUAL ACOUSTIC SUB-WORD UNITS FOR SPOKEN LANGUAGE IDENTIFICATION USING LZW BASED LANGUAGE MODELING,” submitted to IEEE Int. Conf. Acoust. Speech and Signal Proc., 2008.
- Saikat Chatterjee and TV Sreenivas: “Conditional PDF based Split Vector Quantization of LSFs for Telephone-band Speech Coding,” not accepted Eurospeech 2007.
- S Chandra Sekhar and TV Sreenivas: “Blocking artifacts revisited: Time-Frequency median filtering techniques,” not accepted Eurospeech 2007.
- Sriram, G and TV Sreenivas: “Iterative eigenvoice adaptation of acoustic sub-word models for unseen vocabulary,” not accepted Eurospeech 2007.
- Krusheel, M and TV Sreenivas: “Segment Skipping Algorithm For Robust Speech Recognition,” not accepted Eurospeech 2007.
- P Srinivas, V Ramasubramanian and TV Sreenivas: “Stochastic pronunciation modeling based on pruned ergodic-HMM,” not accepted Eurospeech 2007.
- A Sreenivasa Murthy and TV Sreenivas: “Performance evaluation of the ‘Intersection of Confidence Intervals Algorithm”, submitted to ICASSP 2007. (not accepted)
- Resmi Rajendran and TV Sreenivas: “Vocabulary independent and language independent keyword spotting using acoustic subword units,” submitted to ICASSP 2007. (not accepted)
- Saikat Chatterjee and TV Sreenivas: “Optimum switched transform domain split vector quantization,” submitted to ICASSP 2007. (not accepted)
- A Sreenivasa Murthy, S Chandra Sekhar and TV Sreenivas: “Adaptive window local regression (AWLR) for general time-varying signal denoising,” submitted to European Signal Proc Conf. (EUSIPCO), Italy, Sep 2006. (not accepted)
- Saikat Chatterjee and TV Sreenivas: “Joint Inter-Frame and Intra-frame Predictive Quantization of LSF:Telephone-band to Wide-band Speech,” submitted to IEEE Int. Conf. Acoust. Speech. Signal Proc. (ICASSP), Toulouse, France, May 2006. (not accepted)
- Prasanta K. Ghosh and TV Sreenivs: “Automatic speech segmentation using extrema-based signal track length (ESTL) measure,” submitted to Eurospeech 2005. (not accepted)
- S Chandra Sekhar, A Sreenivasa Murthy and TV Sreenivas: “Optimum Signal Reconstruction from Noisy Non-uniformly Sampled Data,” submitted to IEEE Int. Symp. Information Theory (ISIT), 2005. (not accepted)
- Krishna AG: “A novel method of classification using GMMs: Applications to music instrument recognition,” submitted to IEEE Int. Conf. Acoust. Speech. Signal Proc. (ICASSP), Philadelphia, Apr 2005. (not accepted)
- Krishna Kumar, S. and TV Sreenivas: “Benefits of watermark-to-host correlation for blind detection of random phase watermarks in audio signals,” submitted to IEEE Int. Conf. Acoust. Speech. Signal Proc. (ICASSP), Philadelphia, Apr 2005. (not accepted)
- C Narayana Setty and TV Sreenivas: “Time domain estimation of polynomial phase signal parameters,” submitted to IEEE Int. Conf. Acoust. Speech. Signal Proc. (ICASSP), Montreal, Apr 2004. (not accepted)
- B Ravikumar and TV Sreenivas: “Impulse noise removal from speech and audio signals,” submitted to European Signal Processing Conference (EUSIPCO), Toulouse, France, Sep 2002.
- TV Sreenivas and A Anand, “Binaural speech enhancement for hearing aids,” submitted to Int. Conf. Hearing Aids, CA, USA, Aug 2000.