| 2002 | ICASSP | Robust speech recognition in Noisy Environments: The 2001 IBM spine evaluation system. | Brian Kingsbury, George Saon, Lidia Mangu, Mukund Padmanabhan, Ruhi Sarikaya |
| 2001 | ACL | Information Extraction from Voicemail. | Jing Huang, Geoffrey Zweig, Mukund Padmanabhan |
| 2001 | ICASSP | Error corrective mechanisms for speech recognition. | Lidia Mangu, Mukund Padmanabhan |
| 2001 | ICASSP | Linear feature space projections for speaker adaptation. | George Saon, Geoffrey Zweig, Mukund Padmanabhan |
| 2001 | Interspeech | Maximum likelihood non-linear transformation for environment adaptation in speech recognition. | Mukund Padmanabhan, Satya Dharanipragada |
| 2001 | Interspeech | Extracting caller information from voicemail. | Geoffrey Zweig, Jing Huang, Mukund Padmanabhan |
| 2001 | SIGIR | Extracting Caller Information from Voicemail. | Jing Huang, Geoffrey Zweig, Mukund Padmanabhan |
| 2000 | ICASSP | Maximum likelihood discriminant feature spaces. | George Saon, Mukund Padmanabhan, Ramesh A. Gopinath, Scott Saobing Chen |
| 2000 | ICASSP | Boosting Gaussian mixtures in an LVCSR system. | Geoffrey Zweig, Mukund Padmanabhan |
| 2000 | Interspeech | A nonlinear unsupervised adaptation technique for speech recognition. | Satya Dharanipragada, Mukund Padmanabhan |
| 2000 | Interspeech | Recent improvements in speech recognition performance on large vocabulary conversational speech (voicemail and switchboard). | Jing Huang, Brian Kingsbury, Lidia Mangu, Mukund Padmanabhan, George Saon, Geoffrey Zweig |
| 2000 | Interspeech | Filterbank-based feature extraction for speech recognition and its application to voice mail transcription. | Jun Huang, Mukund Padmanabhan |
| 2000 | Interspeech | Spectral peak tracking and its use in speech recognition. | Mukund Padmanabhan |
| 2000 | Interspeech | Minimum Bayes error feature selection. | George Saon, Mukund Padmanabhan |
| 2000 | Interspeech | Exact alpha-beta computation in logarithmic space with application to MAP word graph construction. | Geoffrey Zweig, Mukund Padmanabhan |
| 1999 | ICASSP | HMM training based on quality measurement. | Yuqing Gao, Ea-Ee Jan, Mukund Padmanabhan, Michael Picheny |
| 1999 | Interspeech | The IBM conversational telephony system for financial applications. | K. Davies, Robert E. Donovan, Mark Epstein, Martin Franz, Abraham Ittycheriah, Ea-Ee Jan, Jean-Michel LeRoux, David M. Lubensky, Chalapathy Neti, Mukund Padmanabhan, Kishore Papineni, Salim Roukos, Andrej Sakrajda, Jeffrey S. Sorensen, Borivoj Tydlitt, Todd Ward |
| 1999 | Interspeech | A study of adaptation techniques on a voicemail transcription task. | Jing Huang, Mukund Padmanabhan |
| 1999 | Interspeech | Recent improvements in voicemail transcription. | Mukund Padmanabhan, George Saon, Sankar Basu, Jing Huang, Geoffrey Zweig |
| 1999 | Interspeech | Dependency modeling with bayesian networks in a voicemail transcription system. | Geoffrey Zweig, Mukund Padmanabhan |
| 1998 | ICASSP | A discriminant measure for model complexity adaptation. | Lalit R. Bahl, Mukund Padmanabhan |
| 1998 | ICASSP | Speech recognition performance on a voicemail transcription task. | Mukund Padmanabhan, Ellen Eide, Bhuvana Ramabhadran, Ganesh N. Ramaswamy, Lalit R. Bahl |
| 1998 | ICASSP | Acoustics-only based automatic phonetic baseform generation. | Bhuvana Ramabhadran, Lalit R. Bahl, Peter DeSouza, Mukund Padmanabhan |
| 1998 | Interspeech | Speech recognition performance on a new voicemail transcription task. | Mukund Padmanabhan, Bhuvana Ramabhadran, Sankar Basu |
| 1997 | Interspeech | Speaker adaptation based on pre-clustering training speakers. | Yuqing Gao, Mukund Padmanabhan, Michael Picheny |
| 1997 | Interspeech | Decision-tree based quantization of the feature space of a speech recognizer. | Mukund Padmanabhan, Lalit R. Bahl, David Nahamoo, Pieter de Souza |
| 1996 | ICASSP | Discriminative training of Gaussian mixture models for large vocabulary speech recognition systems. | Lalit R. Bahl, Mukund Padmanabhan, David Nahamoo, P. S. Gopalakrishnan |
| 1996 | ICASSP | Speaker clustering and transformation for speaker adaptation in large-vocabulary speech recognition systems. | Mukund Padmanabhan, Lalit R. Bahl, David Nahamoo, Michael A. Picheny |
| 1995 | ICASSP | Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task. | Lalit R. Bahl, S. Balakrishnan-Aiyer, Jerome R. Bellegarda, Martin Franz, P. S. Gopalakrishnan, David Nahamoo, Miroslav Novak, Mukund Padmanabhan, Michael A. Picheny, Salim Roukos |
| 1995 | ICASSP | Experiments using data augmentation for speaker adaptation. | Jerome R. Bellegarda, Peter V. de Souza, David Nahamoo, Mukund Padmanabhan, Michael A. Picheny, Lalit R. Bahl |
| 1995 | ISCAS | A Hyperstable Adaptive Line Enhancer for Frequency Estimation. | Mukund Padmanabhan |
| 1994 | ICASSP | A channel-bank-based phone detection strategy. | Ponani S. Gopalakrishnan, David Nahamoo, Mukund Padmanabhan, Michael A. Picheny |
| 1993 | ISCAS | A second order hyperstable adaptive filter with no post-error filtering. | Mukund Padmanabhan, Kenneth W. Martin |
| 1992 | ICASSP | Resonator-in-a-loop filter banks-based on a Lerner grouping of outputs. | Ken Martin, Mukund Padmanabhan |
| 1992 | ICASSP | Some further results on modulated/extended lapped transforms. | Mukund Padmanabhan, Ken Martin |
| 1991 | ICASSP | The spectral analysis of short data-segments using an IIR adaptive filter. | Kenneth W. Martin, Mukund Padmanabhan |
| 1991 | ICASSP | Digital filter-banks for transform computations and other applications. | Mukund Padmanabhan, Ken Martin |