Contact Information

Salim Roukos
Senior Manager, Multilingual NLP Technologies & CTO Translation Technologies
Thomas J. Watson Research Center, Yorktown Heights, NY USA


Tab navigation

2010

Improving mention detection robustness to noisy input

R Florian, J F Pitrelli, S Roukos, I Zitouni
Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 335--345

2008

System combination for machine translation of spoken and written language

Evgeny Matusov, Gregor Leusch, Rafael E Banchs, Nicola Bertoldi, Daniel Dechelotte, Marcello Federico, Muntsin Kolss, Young-Suk Lee, Jose B Marino, Matthias Paulik, others
Audio, Speech, and Language Processing, IEEE Transactions on 16(7), 1222--1237, IEEE, 2008

2007

Extracting social networks and biographical facts from conversational speech transcripts

H Jing, N Kambhatla, S Roukos
ANNUAL MEETING-ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, pp. 1040, 2007

Direct translation model 2

A Ittycheriah, S Roukos
Proc, pp. 57--64, 2007

2006

The IBM Arabic-English word alignment corpus

A Ittycheriah, Y Al-Onaizan, S Roukos
Rapport interne RC24024, IBM, 2006

IBM spoken language translation system

Young-Suk Lee, Yaser Al-Onaizan, Kishore Papineni, Salim Roukos
TC-STAR Workshop on Speech-to-Speech Translation, pp. 13--18, 2006

2005

Infrastructure and systems for adaptive speech and text analytics

S Caskey, U Chaudhari, E Epstein, R Florian, JS Mc-Carley, M Omar, G Ramaswamy, S Roukos, T Ward
First International Conference on Intelligence Analysis Methods and Tools, MITRE, McLean, VA, 2005

A maximum entropy word aligner for arabic-english machine translation

A Ittycheriah, S Roukos
Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 89--96, 2005

2003

Language model based Arabic word segmentation

Young-Suk Lee, Kishore Papineni, Salim Roukos, Ossama Emam, Hany Hassan
Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, pp. 399--406, 2003

Automatic derivation of surface text patterns for a maximum entropy based question answering system

D Ravichandran, A Ittycheriah, S Roukos
Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers-Volume 2, pp. 85--87

2002

A multistage algorithm for spotting new words in speech

S Dharanipragada, S Roukos
Speech and Audio Processing, IEEE Transactions on 10(8), 542--550, IEEE, 2002

DARPA communicator evaluation: Progress from 2000 to 2001

M A Walker, A I Rudnicky, J Aberdeen, E O Bratt, J S Garofolo, H Hastie, A N Le, B Pellom, A Potamianos, R Passonneau, others
Seventh International Conference on Spoken Language Processing, 2002

Active learning for statistical natural language parsing

M Tang, X Luo, S Roukos
Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 120--127, 2002

BLEU: a method for automatic evaluation of machine translation

K Papineni, S Roukos, T Ward, W J Zhu
Proceedings of the 40th annual meeting on association for computational linguistics, pp. 311--318, 2002

2001

IBM's Statistical Question Answering System-TREC-10

A I Martin, M Franz, S Roukos
In Proceedings of the Tenth Text REtrieval Conference (TREC, 2001

1999

Story segmentation and topic detection in the broadcast news domain

S Dharanipragada, M Franz, J S McCarley, S Roukos, T Ward
Proceedings of the DARPA Broadcast News Workshop, pp. 65--68, 1999

Free-flow dialog management using forms

KA Papineni, S Roukos, T Ward
Sixth European Conference on Speech Communication and Technology, 1999

1998

Maximum likelihood and discriminative training of direct translation models

K A Papineni, S Roukos, R T Ward
Acoustics, Speech and Signal Processing, 1998, pp. 189--192

Towards speech understanding across multiple languages

T Ward, S Roukos, C Neti, J Gros, M Epstein, S Dharanipragada
Fifth International Conference on Spoken Language Processing, 1998

Fast document translation for cross-language information retrieval

J McCarley, S Roukos
Machine Translation and the Information Soup, 150--157, Springer, 1998

Trec-6 ad-hoc retrieval

M Franz, S Roukos
NIST SPECIAL PUBLICATION SP, 511--516, NATIONAL INSTIUTE OF STANDARDS \& TECHNOLOGY, 1998

Audio indexing for broadcast news

S Dharanipragada, M Franz, S Roukos
Seventh Text REtrieval Conference (TREC-7), pp. 500--242, 1998

1997

Transcription of new speaking styles-Voicemail

M Padmanabhan, B Ramabhadran, E Eide, G Ramaswamy, LR Bahl, PS Gopalakrishnan, S Roukos
Proc, 1997

MDI adaptation of language models across corpora

P S Rao, S Dharanipragada, S Roukos
Fifth European Conference on Speech Communication and Technology, 1997

Experimental results in audio indexing

S Dharanipragada, S Roukos
Proc, 1997

Phone-context specific gender-dependent acoustic-models for continuous speech recognition

C Neti, S Roukos
Automatic Speech Recognition and Understanding, 1997, pp. 192--198

Fertility models for statistical natural language understanding

S D Pietra, M Epstein, S Roukos, T Ward
Proceedings of the eighth conference on European chapter of the Association for Computational Linguistics, pp. 168--173, 1997

Towards a universal speech recognizer for multiple languages

P Cohen, S Dharanipragada, J Gros, M Monkowski, C Neti, S Roukos, T Ward
Automatic Speech Recognition and Understanding, 1997, pp. 591--598

Word-based confidence measures as a guide for stack search in speech recognition

C V Neti, S Roukos, E Eide
Acoustics, Speech, and Signal Processing, 1997, pp. 883--886

Feature-based language understanding

K A Papineni, S Roukos, T R Ward
Fifth European Conference on Speech Communication and Technology, 1997

1996

An iterative algorithm to build Chinese language models

X Luo, S Roukos
Proceedings of the 34th annual meeting on Association for Computational Linguistics, pp. 139--143, 1996

Statistical natural language understanding using hidden clumpings

M Epstein, K Papineni, S Roukos, T Ward, S Della Pietra
Acoustics, Speech, and Signal Processing, 1996, pp. 176--179, Google Patents
US Patent 5,987,404

1995

Language model adaptation via minimum discrimination information

P S Rao, M D Monkowski, S Roukos
Acoustics, Speech, and Signal Processing, 1995, pp. 161--164

1994

Decision tree parsing using a hidden derivation model

F Jelinek, J Lafferty, D Magerman, R Mercer, A Ratnaparkhi, S Roukos
Proceedings of the workshop on Human Language Technology, pp. 272--277, 1994

A maximum entropy model for parsing

A Ratnaparkhi, S Roukos, R T Ward
Third International Conference on Spoken Language Processing, pp. 250--255, 1994

1993

Adaptive language modeling using the maximum entropy principle

R Lau, R Rosenfeld, S Roukos
Proceedings of the workshop on Human Language Technology, pp. 108--113, 1993

Trigger-based language models: A maximum entropy approach

R Lau, R Rosenfeld, S Roukos
Acoustics, Speech, and Signal Processing, 1993, pp. 45--48

1992

Decision tree models applied to the labeling of text with parts-of-speech

E Black, F Jelinek, J Lafferty, R Mercer, S Roukos
Proceedings of the workshop on Speech and Natural Language, pp. 117--121, 1992

Towards history-based grammars: Using richer models for probabilistic parsing

E Black, F Jelinek, J Lafferty, D M Magerman, R Mercer, S Roukos
Proceedings of the workshop on Speech and Natural Language, pp. 134--139, 1992

Development and evaluation of a broad-coverage probabilistic grammar of English-language computer manuals

E Black, J Lafferty, S Roukos
Proceedings of the 30th annual meeting on Association for Computational Linguistics, pp. 185--192, 1992

1991

Procedure for quantitatively comparing the syntactic coverage of English grammars

S Abney, S Flickenger, C Gdaniec, C Grishman, P Harrison, D Hindle, R Ingria, F Jelinek, J Klavans, M Liberman, others
Proceedings of the workshop on Speech and Natural Language, pp. 306--311, 1991

A dynamic language model for speech recognition

F Jelinek, B Merialdo, S Roukos, M Strauss
Proceedings of the DARPA Workshop on Speech and Natural Language, pp. 293--295, 1991

1990

Classifying words for improved statistical language models

F Jelinek, R Mercer, S Roukos
Acoustics, Speech, and Signal Processing, 1990, pp. 621--624

1989

Integration of speech and natural language: final report

S Boisen, Y Chow, A Haas, R Ingria, S Roucos, R Scha, D Stallard, M Vilain
BBN Systems and Technologies, 1989

1988

Statistical language modeling using a small corpus from an application domain

J R Rohlicek, Y L Chow, S Roucos
Acoustics, Speech, and Signal Processing, 1988, pp. 267--270

Stochastic segment modelling using the estimate-maximize algorithm [speech recognition]

S Roucos, M Ostendorf, H Gish, A Derr
Acoustics, Speech, and Signal Processing, 1988, pp. 127--130

Continuous speech recognition results of the BYBLOS system on the DARPA 1000-word resource management database

F Kubala, Y Chow, A Derr, M Feng, O Kimball, J Makhoul, P Price, J Rohlicek, S Roucos, R Schwartz, others
Acoustics, Speech, and Signal Processing, 1988, pp. 291--294

1987

A segment vocoder algorithm for real-time implementation

S Roucos, A Wilgus, W Russell
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'87, pp. 1949--1952, 1987

A stochastic segment model for phoneme-based continuous speech recognition

S Roucos, M Dunham
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'87, pp. 73--76, 1987

Measuring perplexity of language models used in speech recognizers

S Roucos
BBN Laboratories, Cambridge, MA2238, 1987

BYBLOS: The BBN continuous speech recognition system

Y Chow, M Dunham, O Kimball, M Krasner, G Kubala, J Makhoul, P Price, S Roucos, R Schwartz
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'87, pp. 89--92, 1987

1986

Evaluation of multisensor speech input for speech recognition in high ambient noise

V Viswanathan, C Henry, R Schwartz, S Roucos
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'86, pp. 85--88, 1986

Noise-Immune Multisensor Transduction of Speech

S Roucos, V R Viswanathan, C M Henry, A G Derr, R M Schwartz
1986 - BBN LABS INC CAMBRIDGE MA, BBN LABS INC CAMBRIDGE MA

Word recognition using multisensor speech input in high ambient noise

S Roucos, V Viswanathan, C Henry, R Schwartz
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'86, pp. 737--740, 1986

The role of word-dependent coarticulatory effects in a phoneme-based speech recognition system

Y L Chow, R Schwartz, S Roucos, O Kimball, P Price, F Kubala, M Dunham, M Krasner, J Makhoul
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'86, pp. 1593--1596, 1986

1985

The waveform segment vocoder: A new approach for very-low-rate speech coding

S Roucos, A Wilgus
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'85, pp. 236--239, 1985

Investigation of text-independent speaker indentification over telephone channels

H Gish, K Karnofsky, M Krasner, S Roucos, R Schwartz, J Wolf
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'85, pp. 379--382, 1985

Context-dependent modeling for acoustic-phonetic recognition of continuous speech

R Schwartz, YL Chow, O Kimball, S Roucos, M Krasner, J Makhoul
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'85, pp. 1205--1208, 1985

Vector quantization in speech coding

J Makhoul, S Roucos, H Gish
Proceedings of the IEEE 73(11), 1551--1588, IEEE, 1985

High quality time-scale modification for speech

S Roucos, A Wilgus
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'85, pp. 493--496, 1985

1984

Improved hidden Markov modeling of phonemes for continuous speech recognition

R Schwartz, Y Chow, S Roucos, M Krasner, J Makhoul
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'84, pp. 21--24, 1984

1983

A comparison of methods for 300-400 b/s vocoders

R Schwartz, S Roucos
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'83, pp. 69--72, 1983

A segment vocoder at 150 b/s

S Roucos, R Schwartz, J Makhoul
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'83, pp. 61--64, 1983

Brain potentials related to stages of sentence verification

I Fischler, P A Bloom, D G Childers, S E Roucos, N W Perry Jr
Psychophysiology 20(4), 400--409, Wiley Online Library, 1983

1982

Classification of cortical responses using features from single EEG records

D G Childers, P A Bloom, A A Arroyo, S E Roucos, I S Fischler, T Achariyapaopan, N W Perry
Biomedical Engineering, IEEE Transactions on pp. 6, 423--438, IEEE, 1982

Segment quantization for very-low-rate speech coding

S Roucos, R Schwartz, J Makhoul
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'82, pp. 1565--1568, 1982

The application of probability density estimation to text-independent speaker identification

R Schwartz, S Roucos, M Berouti
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'82, pp. 1649--1652, 1982

1981

Small Sample Performance of Pattern Recognition Machines

S E Roucos
Dissertation Abstracts International Part B: Science and Engineering[DISS. ABST. INT. PT. B- SCI. \& ENG.], 41(9), 1981

1980

A two-dimensional maximum entropy spectral estimator

S Roucos, D Childers
Information Theory, IEEE Transactions on 26(5), 554--560, IEEE, 1980

1977

Maximum entropy spectrum for arrays

S E Roucos
Ph.D. Thesis, 1977

Year Unknown

LM95 Summer Workshop Project Report of the Phrase Structure Language Models Team."

S Roucos, others
1995 Language Modeling Summer Research Workshop Technical Reports, 0

W.(1983)

L Fischler, PA Bloom, DG Childers, SE Roucos, N Perry
Brain potentials related to stages of sentence verification. Psychophysiology20, 400--409