Bhuvana Ramabhadran

Gakuto Kurata, Abhinav Sethy, Bhuvana Ramabhadran, Ariya Rastrow, Nobuyasu Itoh, Masafumi Nishimura: Acoustically discriminative language model training with pseudo-hypothesis. Speech Communication 54(2): 219-228 (2012)

Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura, Abhinav Sethy, Bhuvana Ramabhadran: Leveraging word confusion networks for named entity modeling and detection from conversational telephone speech. Speech Communication 54(3): 491-502 (2012)

Junlan Feng, Bhuvana Ramabhadran, John H. L. Hansen, Jason D. Williams: Trends in Speech and Language Processing [In the Spotlight]. IEEE Signal Process. Mag. 29(1): 177-179 (2012)

Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo, Dimitri Kanevsky, Dirk Van Compernolle, Kris Demuynck, Jort F. Gemmeke, Jerome R. Bellegarda, Shiva Sundaram: Exemplar-Based Processing for Speech Recognition: An Overview. IEEE Signal Process. Mag. 29(6): 98-113 (2012)

Nobuyasu Itoh, Tara N. Sainath, Dan-Ning Jiang, Jie Zhou, Bhuvana Ramabhadran: N-best entropy based data selection for acoustic modeling. ICASSP 2012: 4133-4136

Takashi Fukuda, Ryuki Tachibana, Upendra V. Chaudhari, Bhuvana Ramabhadran, Puming Zhan: Constructing ensembles of dissimilar acoustic models using hidden attributes of training data. ICASSP 2012: 4141-4144

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran: Auto-encoder bottleneck features using deep belief networks. ICASSP 2012: 4153-4156

Christian Plahl, Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo: Improved pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines. ICASSP 2012: 4165-4168

Raul Fernandez, Steve Minnis, Bhuvana Ramabhadran: Prediction of F0 contours from symbolic and numerical variables using continuous conditional random fields. ICASSP 2012: 4621-4624

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan: Creating ensemble of diverse maximum entropy models. ICASSP 2012: 4845-4848

Andrew Rosenberg, Raul Fernandez, Bhuvana Ramabhadran: Phrase Boundary Assignment from Text in Multiple Domains. INTERSPEECH 2012

Tara N. Sainath, David Nahamoo, Dimitri Kanevsky, Bhuvana Ramabhadran: Enhancing Exemplar-Based Posteriors for Speech Recognition Tasks. INTERSPEECH 2012

Michael Picheny, David Nahamoo, Vaibhava Goel, Brian Kingsbury, Bhuvana Ramabhadran, Steven J. Rennie, George Saon: Trends and advances in speech recognition. IBM Journal of Research and Development 55(5): 2 (2011)

Ryuki Tachibana, Takashi Fukuda, Upendra V. Chaudhari, Bhuvana Ramabhadran, Puming Zhan: Frame-level AnyBoost for LVCSR with the MMI Criterion. ASRU 2011: 12-17

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, Petr Fousek, Petr Novák, Abdel-rahman Mohamed: Making Deep Belief Networks effective for large vocabulary continuous speech recognition. ASRU 2011: 30-35

Tara N. Sainath, David Nahamoo, Dimitri Kanevsky, Bhuvana Ramabhadran, Parikshit M. Shah: A convex hull approach to sparse representations for exemplar-based speech recognition. ASRU 2011: 59-64

Stanley F. Chen, Abhinav Sethy, Bhuvana Ramabhadran: Pruning exponential language models. ASRU 2011: 237-242

Alexander Sorin, Hagai Aronowitz, Jonathan Mamou, Orith Toledo-Ronen, Ron Hoory, Michael Kuritzky, Yael Erez, Bhuvana Ramabhadran, Abhinav Sethy: Speech processing and retrieval in a personal memory aid system for the elderly. ICASSP 2011: 1749-1752

Raul Fernandez, Bhuvana Ramabhadran: Exploiting active-learning strategies for annotating prosodic events with limited labeled data. ICASSP 2011: 2208-2211

Tara N. Sainath, David Nahamoo, Bhuvana Ramabhadran, Dimitri Kanevsky, Vaibhava Goel, Parikshit M. Shah: Exemplar-based Sparse Representation phone identification features. ICASSP 2011: 4492-4495

Bin Zhang, Abhinav Sethy, Tara N. Sainath, Bhuvana Ramabhadran: Application specific loss minimization using gradient boosting. ICASSP 2011: 4880-4883

Ariya Rastrow, Markus Dreyer, Abhinav Sethy, Sanjeev Khudanpur, Bhuvana Ramabhadran, Mark Dredze: Hill climbing on speech lattices: A new rescoring framework. ICASSP 2011: 5032-5035

Abdel-rahman Mohamed, Tara N. Sainath, George E. Dahl, Bhuvana Ramabhadran, Geoffrey E. Hinton, Michael A. Picheny: Deep Belief Networks using discriminative features for phone recognition. ICASSP 2011: 5060-5063

Dimitri Kanevsky, David Nahamoo, Tara N. Sainath, Bhuvana Ramabhadran, Peder A. Olsen: A-Functions: A generalization of Extended Baum-Welch transformations to convex optimization. ICASSP 2011: 5164-5167

Abhinav Sethy, Stanley F. Chen, Bhuvana Ramabhadran: Distributed training of large scale exponential language models. ICASSP 2011: 5520-5523

Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura, Abhinav Sethy, Bhuvana Ramabhadran: Named entity recognition from Conversational Telephone Speech leveraging Word Confusion Networks for training and recognition. ICASSP 2011: 5572-5575

Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabhadran: Deep belief nets for natural language call-routing. ICASSP 2011: 5680-5683

Ebru Arisoy, Bhuvana Ramabhadran, Hong-Kwang Jeff Kuo: Feature Combination Approaches for Discriminative Language Models. INTERSPEECH 2011: 617-620

Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo, Dimitri Kanevsky: Reducing Computational Complexities of Exemplar-Based Sparse Representations with Applications to Large Vocabulary Speech Recognition. INTERSPEECH 2011: 785-788

Dimitri Kanevsky, David Nahamoo, Tara N. Sainath, Bhuvana Ramabhadran: Convergence of Line Search A-Function Methods. INTERSPEECH 2011: 997-1000

Ruhi Sarikaya, Stanley F. Chen, Bhuvana Ramabhadran: Shrinkage-Based Features for Natural Language Call Routing. INTERSPEECH 2011: 1309-1312

Leonid Rachevsky, Dimitri Kanevsky, Ruhi Sarikaya, Bhuvana Ramabhadran: Clustering with Modified Cosine Distance Learned from Constraints. INTERSPEECH 2011: 1313-1316

Jonathan Mamou, Abhinav Sethy, Bhuvana Ramabhadran, Ron Hoory, Paul Vozila: Improved Spoken Query Transcription Using Co-Occurrence Information. INTERSPEECH 2011: 1473-1476

Andrew Rosenberg, Raul Fernandez, Bhuvana Ramabhadran: "What is... Dengue Fever?" - Modeling and Predicting Pronunciation Errors in a Text-to-Speech System. INTERSPEECH 2011: 2189-2192

Avishy Carmi, Tara N. Sainath, Pini Gurfil, Dimitri Kanevsky, David Nahamoo, Bhuvana Ramabhadran: The Use of isometric transformations and bayesian estimation in compressive sensing for fMRI classification. ICASSP 2010: 493-496

Tara N. Sainath, Avishy Carmi, Dimitri Kanevsky, Bhuvana Ramabhadran: Bayesian compressive sensing for phonetic classification. ICASSP 2010: 4370-4373

Srikanth Vishnubhotla, Raul Fernandez, Bhuvana Ramabhadran: An autoencoder neural-network based low-dimensionality approach to excitation modeling for HMM-based text-to-speech. ICASSP 2010: 4614-4617

Ruhi Sarikaya, Ahmad Emami, Mohamed Afify, Bhuvana Ramabhadran: Continuous space language modeling techniques. ICASSP 2010: 5186-5189

Carolina Parada, Abhinav Sethy, Bhuvana Ramabhadran: Balancing false alarms and hits in Spoken Term Detection. ICASSP 2010: 5286-5289

Mark E. Epstein, Bhuvana Ramabhadran, Rajesh Balchandran: Improved language modeling for conversational applications using sentence quality. ICASSP 2010: 5378-5381

Rajesh Balchandran, Leonid Rachevsky, Bhuvana Ramabhadran, Miroslav Novak: Techniques for topic detection based processing in spoken dialog systems. INTERSPEECH 2010: 82-85

Vaibhava Goel, Tara N. Sainath, Bhuvana Ramabhadran, Peder A. Olsen, David Nahamoo, Dimitri Kanevsky: Incorporating sparse representation phone identification features in automatic speech recognition using exponential families. INTERSPEECH 2010: 1345-1348

Raul Fernandez, Bhuvana Ramabhadran: Discriminative training and unsupervised adaptation for labeling prosodic events with limited training data. INTERSPEECH 2010: 1429-1432

Ruhi Sarikaya, Stanley F. Chen, Abhinav Sethy, Bhuvana Ramabhadran: Impact of word classing on shrinkage-based language models. INTERSPEECH 2010: 1804-1807

Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo, Dimitri Kanevsky, Abhinav Sethy: Sparse representation features for speech recognition. INTERSPEECH 2010: 2254-2257

Abhinav Sethy, Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky: Data selection for language modeling using sparse representations. INTERSPEECH 2010: 2258-2261

Tara N. Sainath, Sameer Maskey, Dimitri Kanevsky, Bhuvana Ramabhadran, David Nahamoo, Julia Hirschberg: Sparse representations for text categorization. INTERSPEECH 2010: 2266-2269

Dimitri Kanevsky, Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo: An analysis of sparseness and regularization in exemplar-based methods for speech classification. INTERSPEECH 2010: 2842-2845

Ariya Rastrow, Frederick Jelinek, Abhinav Sethy, Bhuvana Ramabhadran: Unsupervised Model Adaptation using Information-Theoretic Criterion. HLT-NAACL 2010: 190-197

Abhinav Sethy, Panayiotis G. Georgiou, Bhuvana Ramabhadran, Shrikanth S. Narayanan: An Iterative Relative Entropy Minimization-Based Data Selection Approach for n-Gram Model Adaptation. IEEE Transactions on Audio, Speech & Language Processing 17(1): 13-23 (2009)

Stanley F. Chen, Lidia Mangu, Bhuvana Ramabhadran, Ruhi Sarikaya, Abhinav Sethy: Scaling shrinkage-based language models. ASRU 2009: 299-304

Ariya Rastrow, Abhinav Sethy, Bhuvana Ramabhadran: Constrained discriminative training of N-gram language models. ASRU 2009: 311-316

Tara N. Sainath, Bhuvana Ramabhadran, Michael Picheny: An exploration of large vocabulary tools for small vocabulary phonetic recognition. ASRU 2009: 359-364

Carolina Parada, Abhinav Sethy, Bhuvana Ramabhadran: Query-by-example Spoken Term Detection For OOV terms. ASRU 2009: 404-409

Narges Bani Asadi, Irina Rish, Katya Scheinberg, Dimitri Kanevsky, Bhuvana Ramabhadran: Map approach to learning sparse Gaussian Markov networks. ICASSP 2009: 1721-1724

Dimitri Kanevsky, Tara N. Sainath, Bhuvana Ramabhadran: A generalized family of parameter estimation techniques. ICASSP 2009: 1725-1728

Ariya Rastrow, Abhinav Sethy, Bhuvana Ramabhadran: A new method for OOV detection using hybrid word/fragment system. ICASSP 2009: 3953-3956

Dogan Can, Erica Cooper, Abhinav Sethy, Christopher M. White, Bhuvana Ramabhadran, Murat Saraclar: Effect of pronounciations on OOV queries in spoken term detection. ICASSP 2009: 3957-3960

Christopher M. White, Abhinav Sethy, Bhuvana Ramabhadran, Patrick J. Wolfe, Erica Cooper, Murat Saraclar, James K. Baker: Unsupervised pronunciation validation. ICASSP 2009: 4301-4304

Ruhi Sarikaya, Sameer Maskey, R. Zhang, Ea-Ee Jan, D. Wang, Bhuvana Ramabhadran, Salim Roukos: Iterative sentence-pair extraction from quasi-parallel corpora for machine translation. INTERSPEECH 2009: 432-435

Ariya Rastrow, Abhinav Sethy, Bhuvana Ramabhadran, Frederick Jelinek: Towards using hybrid word and fragment units for vocabulary independent LVCSR systems. INTERSPEECH 2009: 1931-1934

Vit Libal, Bhuvana Ramabhadran, Nadia Mana, Fabio Pianesi, Paul Chippendale, Oswald Lanz, Gerasimos Potamianos: Multimodal Classification of Activities of Daily Living Inside Smart Homes. IWANN (2) 2009: 687-694

Bhuvana Ramabhadran, Abhinav Sethy, Jonathan Mamou, Brian Kingsbury, Upendra V. Chaudhari: Fast decoding for open vocabulary spoken term detection. HLT-NAACL (Short Papers) 2009: 277-280

Dogan Can, Erica Cooper, Arnab Ghoshal, Martin Jansche, Sanjeev Khudanpur, Bhuvana Ramabhadran, Michael Riley, Murat Saraclar, Abhinav Sethy, Morgan Ulinski, Christopher M. White: Web derived pronunciations for spoken term detection. SIGIR 2009: 83-90

Daniel Povey, Dimitri Kanevsky, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Karthik Visweswariah: Boosted MMI for model and feature-space discriminative training. ICASSP 2008: 4057-4060

Tara N. Sainath, Dimitri Kanevsky, Bhuvana Ramabhadran: Gradient steepness metrics using extended Baum-Welch transformations for universal pattern recognition tasks. ICASSP 2008: 4533-4536

Dimitri Kanevsky, Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo: Generalization of extended baum-welch parameter estimation for discriminative training and decoding. INTERSPEECH 2008: 277-280

Abhinav Sethy, Bhuvana Ramabhadran: Bag-of-word normalized n-gram models. INTERSPEECH 2008: 1594-1597

Sangyun Hahn, Abhinav Sethy, Hong-Kwang Jeff Kuo, Bhuvana Ramabhadran: A study of unsupervised clustering techniques for language modeling. INTERSPEECH 2008: 1598-1601

Jonathan Mamou, Bhuvana Ramabhadran: Phonetic query expansion for spoken document retrieval. INTERSPEECH 2008: 2106-2109

Tara N. Sainath, Dimitri Kanevsky, Bhuvana Ramabhadran: Broad phonetic class recognition in a Hidden Markov model framework using extended Baum-Welch transformations. ASRU 2007: 306-311

Bhuvana Ramabhadran, Olivier Siohan, Abhinav Sethy: The IBM 2007 speech transcription system for European parliamentary speeches. ASRU 2007: 472-477

Brett Matthews, Upendra V. Chaudhari, Bhuvana Ramabhadran: Fast audio search using vector space modelling. ASRU 2007: 641-646

Jonathan Mamou, Bhuvana Ramabhadran, Olivier Siohan: Vocabulary independent spoken term detection. SIGIR 2007: 615-622

Bhuvana Ramabhadran, Olivier Siohan, Lidia Mangu, Geoffrey Zweig, Martin Westphal, Henrik Schulz, Alvaro Soneiro: The IBM 2006 speech transcription system for european parliamentary speeches. INTERSPEECH 2006

Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury: Automated Quality Monitoring for Call Centers using Speech and NLP Technologies. HLT-NAACL 2006

George Saon, Bhuvana Ramabhadran, Geoffrey Zweig: On the Effect Ofword Error Rate on Automated Quality Monitoring. SLT 2006: 106-109

Bhuvana Ramabhadran: Exploiting large quantities of spontaneous speech for unsupervised training of acoustic models. INTERSPEECH 2005: 1617-1620

William Byrne, David S. Doermann, Martin Franz, Samuel Gustman, Jan Hajic, Douglas W. Oard, Michael Picheny, Josef Psutka, Bhuvana Ramabhadran, Dagobert Soergel, Todd Ward, Wei-Jing Zhu: Automatic recognition of spontaneous speech for access to multilingual oral history archives. IEEE Transactions on Speech and Audio Processing 12(4): 420-435 (2004)

Bhuvana Ramabhadran, Olivier Siohan, Geoffrey Zweig: Use of metadata to improve recognition of spontaneous speech and named entities. INTERSPEECH 2004

Abhinav Sethy, Shrikanth Narayanan, Bhuvana Ramabhadran: Measuring convergence in language model estimation using relative entropy. INTERSPEECH 2004

Olivier Siohan, Bhuvana Ramabhadran, Geoffrey Zweig: Speech recognition error analysis on the English MALACH corpus. INTERSPEECH 2004

Douglas W. Oard, Dagobert Soergel, David S. Doermann, Xiaoli Huang, G. Craig Murray, Jianqiang Wang, Bhuvana Ramabhadran, Martin Franz, Samuel Gustman, James Mayfield, Liliya Kharevych, Stephanie Strassel: Building an information retrieval test collection for spontaneous conversational speech. SIGIR 2004: 41-48

Martin Franz, Bhuvana Ramabhadran, Todd Ward, Michael Picheny: Automated transcription and topic segmentation of large spoken archives. INTERSPEECH 2003

Bhuvana Ramabhadran, Jing Huang, Upendra V. Chaudhari, Giridharan Iyengar, Harriet J. Nock: Impact of audio segmentation and segment clustering on automated transcription accuracy of large spoken archives. INTERSPEECH 2003

Samuel Gustman, Dagobert Soergel, Douglas W. Oard, William J. Byrne, Michael Picheny, Bhuvana Ramabhadran, Douglas Greenberg: Supporting access to large digital oral history archives. JCDL 2002: 18-27

Douglas W. Oard, Dina Demner-Fushman, Jan Hajic, Bhuvana Ramabhadran, Samuel Gustman, William J. Byrne, Dagobert Soergel, Bonnie J. Dorr, Philip Resnik, Michael Picheny: Cross-Language Access to Recorded Speech in the MALACH Project. TSD 2002: 57-64

Josef Psutka, Pavel Ircing, Josef V. Psutka, Vlasta Radová, William J. Byrne, Jan Hajic, Samuel Gustman, Bhuvana Ramabhadran: Automatic Transcription of Czech Language Oral History in the MALACH Project: Resources and Initial Experiments. TSD 2002: 253-260

Bhuvana Ramabhadran, Yuqing Gao: Decision tree based rate of speech modeling for speech recognition. INTERSPEECH 2000: 600-603

Bhuvana Ramabhadran, Yuqing Gao, Michael Picheny: Dynamic selection of feature spaces for robust speech recognition. INTERSPEECH 2000: 913-916

Bhuvana Ramabhadran, Sabine Deligne, Abraham Ittycheriah: Acoustics-based baseform generation with pronunciation and/or phonotactic models. EUROSPEECH 1999

Peter V. de Souza, Bhuvana Ramabhadran, Yuqing Gao, Michael Picheny: Enhanced likelihood computation using regression. EUROSPEECH 1999

Ramesh A. Gopinath, Bhuvana Ramabhadran, Satya Dharanipragada: Factor analysis invariant to linear transformations of data. ICSLP 1998

Mukund Padmanabhan, Bhuvana Ramabhadran, Sankar Basu: Speech recognition performance on a new voicemail transcription task. ICSLP 1998

Bhuvana Ramabhadran, Abraham Ittycheriah: Phonological rules for enhancing acoustic enrollment of unknown words. ICSLP 1998