Conference Papers

  • B. Yusuf, L. Ondel, L. Burget, J. Cernocky, M. Saraclar.
    A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery. In Proceedings of ICASSP, Toronto, Canada, 2021.

  • B Gundogdu, B Yusuf, M Yesilbursa, M Saraclar.
    Vector quantized temporally-aware correspondence sparse autoencoders for zero-resource acoustic unit discovery.
    In Proceedings of Interspeech, Shanghai, China, 2020.

  • K Polat, M Saraclar.
    Unsupervised Discovery of Sign Terms by K-Nearest Neighbours Approach. In Proceedings of ECCV, SLRTP Workshop, 2020.

  • NC Tamer, M Saraclar.
    Improving Keyword Search Performance in Sign Language with Hand Shape Features. In Proceedings of ECCV, SLRTP Workshop, 2020.

  • K Polat, M Saraclar.
    Unsupervised term discovery for continuous sign language.
    In Proc. LREC2020 9th Workshop on the Representation and Processing of Sign Languages, 2020.

  • NC Tamer, M Saraclar.
    Cross-lingual keyword search for sign language.
    In Proc. LREC2020 9th Workshop on the Representation and Processing of Sign Languages, 2020.

  • OD Kose, M Saraclar.
    Recurrent Neural Audiovisual Word Embeddings for Synchronized Speech and Real-Time MRI. In Proceedings of ICASSP, Barcelona, Spain, 2020.

  • NC Tamer, M Saraclar.
    Keyword Search for Sign Language.
    In Proceedings of ICASSP, Barcelona, Spain, 2020.

  • RD Siyli, B Gundogdu, M Saraclar, L Akarun.
    Unsupervised Key Hand Shape Discovery of Sign Language Videos with Correspondence Sparse Autoencoders.
    In Proceedings of ICASSP, Barcelona, Spain, 2020.

  • B Yusuf, M Saraclar.
    An Empirical Evaluation of DTW Subsampling Methods for Keyword Search.
    In Proceedings of Interspeech, Graz, Austria, 2019.

  • B Yusuf, A Gok, B Gundogdu, OD Kose, M Saraclar.
    Temporally-Aware Acoustic Unit Discovery for Zerospeech 2019 Challenge.
    In Proceedings of Interspeech, Graz, Austria, 2019.

  • N Dereli, M Saraclar
    Convolutional Neural Networks for Financial Text Regression
    In Proceedings of ACL: SRW, Florence, Italy, 2019.

  • M Unlu, E Arisoy, M Saraclar.
    Question answering for spoken lecture processing.
    In Proceedings of ICASSP, Brighton, UK, 2019.

  • B Gundogdu, M Saraclar
    Similarity Learning Based Query Modeling for Keyword Search.
    In Proceedings of Interspeech, Stockholm, Sweden, 2017.

  • D Ayata, M Saraclar, A Ozgur
    BUSEM at SemEval-2017 Task 4A Sentiment Analysis with Word Embedding and Long Short Term Memory RNN Approaches
    In Proceedings of SemEval, Vancouver, Canada, 2017.

  • B Gundogdu, M Saraclar
    Distance Metric Learning for Posteriorgram Based Keyword Search
    In Proceedings of ICASSP, New Orleans, LA, USA, 2017.

  • G. Cetinkaya, B. Gundogdu, and M. Saraclar.
    Pre-filtered dynamic time warping for posteriorgram based keyword search.
    In Proceedings of SLT, San Diego, CA, USA, 2016.

  • E. Arisoy and M. Saraclar.
    Compositional Neural Network Language Models for Agglutinative Languages.
    In Proceedings of Interspeech, San Fransisco, CA, USA, 2016.

  • E. Dikici and M. Saraclar.
    MT-based artificial hypothesis generation for unsupervised discriminative language modeling.
    In Proceedings of EUSIPCO, Nice, France, 2015.

  • M. Saraclar, E. Dikici, and E. Arisoy.
    A Decade of Discriminative Language Modeling for Automatic Speech Recognition.
    In Speech and Computer, Athens, Greece, 2015.

  • L. Sari, B. Gundogdu, and M. Saraclar.
    Fusion of LVCSR and Posteriorgram Based Keyword Search.
    In Proceedings of Interspeech, Dresden, Germany, 2015.

  • E. Arisoy and M. Saraclar.
    Multi-Stream Long Short-Term Memory Neural Network Language Model.
    In Proceedings of Interspeech, Dresden, Germany, 2015.

  • E. Dikici and M. Saraclar.
    Unsupervised Training Methods for Discriminative Language Modeling.
    In Proceedings of Interspeech, Singapore, 2014.

  • M. Saraclar, A. Sethy, B. Ramabhadran, L. Mangu, J. Cui, X. Cui, B. Kingsbury, and J. Mamou.
    An empirical study of confusion modeling in keyword search for low resource languages.
    In Proceedings of ASRU, Olomouc, Czech Republic, 2013.

  • E. Dikici, E. Prud’hommeaux, B. Roark, and M. Saraclar.
    Investigation of MT-based ASR Confusion Models for Semi-Supervised Discriminative Language Modeling.
    In Proceedings of Interspeech, Lyon, France, 2013.

  • A. Celebi and M. Saraclar.
    Semi-Supervised Discriminative Language Modeling with Out-of-Domain Text Data.
    In Proceedings of NAACL-HLT, Atlanta, GA, USA, 2013.

  • C. Demir, A.T. Cemgil, and M. Saraclar.
    Effect of speech priors in single-channel speech-music separation for ASR.
    In Proceedings of Interspeech, Portland, OR, USA, 2012.

  • E. Dikici, A. Celebi, and M. Saraclar.
    Performance Comparison of Training Algorithms for Semi-Supervised Discriminative Language Modeling.
    In Proceedings of Interspeech, Portland, OR, USA, 2012.

  • J. Fayolle, M. Saraclar, F. Moreau, C. Raymond, and G. Gravier.
    Lexical-phonetic automata for spoken utterance indexing and retrieval.
    In Proceedings of Interspeech, Portland, OR, USA, 2012.

  • D. Karakos, B. Roark, I. Shafran, K. Sagae, M. Lehr, E. Prud’hommeaux, P. Xu, N. Glenn, S. Khudanpur, M. Saraclar, D. Bikel, M. Dredze, C. Callison-Burch, Y. Cao, K. Hall, E. Hasler, P. Koehn, A. Lopez, M. Post, D. Riley.
    Deriving conversation-based features from unlabeled speech for discriminative language modeling.
    In Proceedings of Interspeech, Portland, OR, USA, 2012.

  • C. Demir, A.T. Cemgil, and M. Saraclar.
    Catalog-Based Single-Channel Speech-Music Separation with the Itakura-Saito Divergence.
    In Proceedings of EUSIPCO, Bucharest, Romania, 2012.

  • A. Celebi, H. Sak, E. Dikici, M. Saraclar, M. Lehr, E. Prud’hommeaux, P. Xu, N. Glenn, D. Karakos, S. Khudanpur, B. Roark, K. Sagae, I. Shafran, D. Bikel, C. Callison-Burch, Y. Cao, K. Hall, E. Hasler, P. Koehn, A. Lopez, M. Post, D. Riley.
    Semi-supervised Discriminative Language Modeling for Turkish ASR.
    In Proceedings of ICASSP, Kyoto, Japan, 2012.

  • K. Sagae, M. Lehr, E. Prud’hommeaux, P. Xu, N. Glenn, D. Karakos, S. Khudanpur, B. Roark, M. Saraclar, I. Shafran, D. Bikel, C. Callison-Burch, Y. Cao, K. Hall, E. Hasler, P. Koehn, A. Lopez, M. Post, D. Riley.
    Hallucinated N-best Lists for Discriminative Language Modeling.
    In Proceedings of ICASSP, Kyoto, Japan, 2012.

  • P. Xu, S. Khudanpur, M. Lehr, E. Prud’hommeaux, N. Glenn, D. Karakos, B. Roark, K. Sagae, M. Saraclar, I. Shafran, D. Bikel, C. Callison-Burch, Y. Cao, K. Hall, E. Hasler, P. Koehn, A. Lopez, M. Post, D. Riley.
    Continuous Space Discriminative Language Modeling.
    In Proceedings of ICASSP, Kyoto, Japan, 2012.

  • C. Demir, A.T. Cemgil, and M. Saraclar.
    Gain Estimation Approaches in Catalog-Based Single-Channel Speech-Music Separation.
    In Proceedings of ASRU, Hawaii, USA, 2011.

  • H. Sak, M. Saraclar, and T. Gungor.
    Discriminative Reranking of ASR Hypotheses with Morpholexical and N-Best-List Features.
    In Proceedings of ASRU, Hawaii, USA, 2011.

  • C. Demir, A.T. Cemgil, and M. Saraclar.
    Catalog-based single-channel speech-music separation for automatic speech recognition.
    In Proceedings of EUSIPCO, Barcelona, Spain, 2011.

  • C. Demir, M. Saraclar, and A.T. Cemgil.
    Semi-supervised Single-Channel Speech-Music Separation for Automatic Speech Recognition.
    In Proceedings of Interspeech, Florence, Italy, 2011.

  • E. Dikici, M. Semerci, M. Saraclar, and E. Alpaydin.
    Data Sampling and Dimensionality Reduction Approaches for Reranking ASR Outputs Using Dis- criminative Language Models.
    In Proceedings of Interspeech, Florence, Italy, 2011.

  • C. Mermer and M. Saraclar.
    Bayesian Word Alignment for Statistical Machine Translation.
    In Proceedings of ACL-HLT, Portland, OR, USA, 2011.

  • U. Firat, S.N. Engin, M. Saraclar, and A.B. Ertuzun.
    Wind Speed Forecasting Based On Second Order Blind Identification and Autoregressive Model.
    In Proceedings of ICMLA, Washington DC, USA, 2010.

  • C. Demir, A.T. Cemgil, and M. Saraclar.
    Catalog-Based Single-Channel Speech-Music Separation.
    In Proceedings of Interspeech, Makuhari, Japan, 2010.

  • H. Sak, M. Saraclar, and T. Gungor.
    On-the-fly Lattice Rescoring for Real-time Automatic Speech Recognition.
    In Proceedings of Interspeech, Makuhari, Japan, 2010.

  • I. Sen, M. Saraclar, and Y.P. Kahya.
    Acoustic Mapping of the Lung Based on Source Localization of Adventitious Respiratory Sound Components.
    In Proceedings of EMBC, Buenos Aires, Argentina, 2010.

  • E. Arisoy, M. Saraclar, B. Roark and I. Shafran.
    Syntactic and Sub-lexical Features for Turkish Discriminative Language Models.
    In Proceedings of IEEE ICASSP, Dallas, TX, USA, 2010.

  • H. Sak, M. Saraclar, and T. Gungor.
    Morphology-based and Sub-word Language Modeling for Turkish Speech Recognition.
    In Proceedings of IEEE ICASSP, Dallas, TX, USA, 2010.

  • H. Sak, M. Saraclar, and T. Gungor.
    Integrating Morphology into Automatic Speech Recognition.
    In Proceedings of IEEE ASRU, Merano, Italy, 2009.

  • T. Som, D. Can, and M. Saraclar.
    HMM-based Sliding Video Text Recognition for Turkish Broadcast News.
    In Proceedings of ISCIS, N. Cyprus, 2009.

  • E. Dikici and M. Saraclar.
    Investigating the Effect of Training Data Partitioning for GMM Supervector Based Speaker Verification.
    In Proceedings of ISCIS, N. Cyprus, 2009.

  • H. Sak, T. Gungor and M. Saraclar.
    A Stochastic Finite-State Morphological Parser for Turkish.
    In Proceedings of ACL-IJCNLP, Singapore, 2009.

  • S. Parlak and M. Saraclar.
    Spoken Information Retrieval for Turkish Broadcast News.
    In Proceedings of ACM-SIGIR, Boston, MA, USA, 2009.

  • D. Can, E. Cooper, A. Ghoshal, M. Jansche, S. Khudanpur, B. Ramabhadran, M. Riley, M. Saraclar, A. Sethy, M. Ulinski, C. White.
    Web derived Pronunciations for Spoken Term Detection.
    In Proceedings of ACM-SIGIR, Boston, MA, USA, 2009.

  • E. Arisoy, T. Pellegrini, M. Saraclar, L. Lamel.
    Enhanced Morfessor Algorithm with Phonetic Features: application to Turkish.
    In Proceedings of SPECOM, St.Petersburg, Russia, 2009.

  • P. Santemiz, O. Aran, M. Saraclar, L. Akarun.
    Extraction of Isolated Signs from Sign Language Videos via Multiple Sequence Alignment.
    In Proceedings of SPECOM, St.Petersburg, Russia, 2009.

  • D. Can and M. Saraclar.
    Score Distribution Based Term Specific Thresholding for Spoken Term Detection.
    In Proceedings of NAACL-HLT, Boulder, CO, USA, 2009.

  • D. Can, E. Cooper, A. Sethy, C. White, B. Ramabhadran, M. Saraclar.
    Effect of Pronunciations on OOV Queries in Spoken Term Detection.
    In Proceedings of IEEE ICASSP, Taiwan, 2009.

  • C.M. White, A. Sethy, B. Ramabhadran, P. Wolfe, E. Cooper, M. Saraclar, J. Baker.
    Unsupervised Pronunciation Validation.
    In Proceedings of IEEE ICASSP, Taiwan, 2009.

  • E. Arisoy, B. Roark, I. Shafran, M. Saraclar.
    Discriminative N-gram Language Modeling for Turkish.
    In Proceedings of Interspeech, Brisbane, Australia, 2008.

  • H. Sak, T. Gungor and M. Saraclar.
    Turkish Language Resources: Morphological Parser, Morphological Disambiguator and Web Corpus.
    In Proceedings of the 6th International Conference on Natural Language Processing, GoTAL, 2008.

  • S. Parlak and M. Saraclar.
    Spoken Term Detection for Turkish Broadcast News.
    In Proceedings of IEEE ICASSP, Las Vegas, USA, 2008.

  • E. Arisoy, H. Sak and M. Saraclar.
    Language Modeling for Automatic Turkish Broadcast News Transcription.
    In Proceedings of Interspeech, Antwerp, Belgium, 2007.

  • Z. Liu and M. Saraclar.
    Speaker Segmentation and Adaptation for Speech Recognition on Multiple-Speaker Audio Conference Data.
    In Proceedings of ICME, Beijing, China, 2007.

  • M. Creutz, T. Hirsimaki, M. Kurimo, A. Puurula, J. Pylkkonen, V. Siivola, M. Varjokallio, E. Arisoy, M. Saraclar, and A. Stolcke.
    Analysis of Morph-Based Speech Recognition and the Modeling of Out-of-Vocabulary Words Across Languages.
    In Proceedings of HLT-NAACL, Rochester, NY, USA, 2007.

  • H. Sak, T. Gungor and M. Saraclar.
    Morphological Disambiguation of Turkish Text with Perceptron Algorithm.
    In Proceedings of the 8th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), Mexico City, Mexico, 2007.

  • E. Arisoy and M. Saraclar.
    Lattice extension and rescoring based approaches for LVCSR of Turkish.
    In Proceedings of Interspeech, Pittsburgh, PA, USA, 2006.

  • M. Kurimo, M. Creutz, M. Varjokallio, E. Arisoy, and M. Saraclar.
    Unsupervised segmentation of words into morphemes – Morpho Challenge 2005: Applications to automatic speech recognition.
    In Proceedings of Interspeech, Pittsburgh, PA, USA, 2006.

  • M. Kurimo, A. Puurula, E. Arisoy, V. Siivola, T. Hirsimaki, J. Pylkkonen, T. Alumae, and M. Saraclar.
    Unlimited vocabulary speech recognition for agglutinative languages.
    In Proceedings of HLT-NAACL, New York, USA, 2006.

  • J. Feng, S. Reddy, and M. Saraclar.
    WebTalk: Mining Websites for Interactively Answering Questions.
    In Proceedings of Interspeech, Lisbon, Portugal, 2005.

  • M. Collins, B. Roark, and M. Saraclar.
    Discriminative Syntactic Language Modeling for Speech Recognition.
    In Proceedings of ACL, Ann Arbor, Michigan, USA, 2005.

  • M. Saraclar and B. Roark.
    Joint discriminative language modeling and utterance classification.
    In Proceedings of IEEE ICASSP, Philadelphia, USA, 2005.

  • V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tu ̈r, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar.
    The AT&T WATSON Speech Recognizer.
    In Proceedings of IEEE ICASSP, Philadelphia, USA, 2005.

  • E. Bocchieri, M. Riley, and M. Saraclar.
    Methods for task adaptation of acoustic models with limited transcribed in-domain data.
    In Proceedings of Interspeech, Jeju Island, South Korea, 2004.

  • A. Ljolje, V. Goffin, and M. Saraclar.
    Low Latency Real-Time Vocal Tract Length Normalization.
    In Proceedings of the 7th International Conference on Text, Speech and Dialogue (TSD), Brno, Czech Republic, 2004.

  • B. Roark, M. Saraclar, M. Collins, and M. Johnson.
    Discriminative language modeling with conditional random fields and the perceptron algorithm.
    In Proceedings of ACL, Barcelona, Spain, 2004.

  • B. Roark, M. Saraclar, and M. Collins.
    Corrective language modeling for large vocabulary ASR with the perceptron algorithm.
    In Proceedings of IEEE ICASSP, Montreal, Canada, 2004.

  • A. Yazgan and M. Saraclar.
    Hybrid language models for out of vocabulary word detection in large vocabulary conversational speech recognition.
    In Proceedings of IEEE ICASSP, Montreal, Canada, 2004.

  • M. Saraclar and R. Sproat.
    Lattice-based search for spoken utterance retrieval.
    In Proceedings of HLT-NAACL, Boston, USA, 2004.

  • M. Bacchiani, B. Roark, and M. Saraclar.
    Language model adaptation with MAP estimation and the perceptron algorithm.
    In Proceedings of HLT-NAACL, Boston, USA, 2004.

  • C. Allauzen, M. Mohri, and M. Saraclar.
    General indexation of weighted automata – application to spoken utterance retrieval.
    In Proceedings of the HLT-NAACL Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval, Boston, 2004.

  • L. Begeja, D. Gibbon, Z. Liu, B. Renger, M. Saraclar, and B. Shahraray.
    A system for searching and browsing spoken communications.
    In Proceedings of the HLT-NAACL Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval, Boston, 2004.

  • M. Saraclar, M. Riley, E. Bocchieri, and V. Goffin.
    Towards automatic closed captioning: Low latency real time broadcast news transcription.
    In Proceedings of Interspeech, Denver, Colorado, 2002.

  • M. Saraclar and S. Khudanpur.
    Pronunciation ambiguity vs pronunciation variability in speech recognition.
    In Proceedings of IEEE ICASSP, Istanbul, Turkey, 2000.

  • M. Saraclar, H. Nock, and S. Khudanpur.
    Pronunciation modeling by sharing gaussian densities across phonetic models.
    In Proceedings of Eurospeech, Budapest, Hungary, 1999.

  • W. Byrne, M. Finke, S. Khudanpur, J. McDonough, H. Nock, M. Riley, M. Saraclar, C. Wooters, and G. Zavaliagkos.
    Pronunciation modelling using a hand-labelled corpus for conversational speech recognition.
    In Proceedings of IEEE ICASSP, Seattle, WA, 1998.

  • M. Riley, W. Byrne, M. Finke, S. Khudanpur, A. Ljolje, J. McDonough, H. Nock, M. Saraclar, C. Wooters, and G. Zavaliagkos.
    Stochastic pronunciation modeling from hand-labeled phonetic corpora.
    In Proceedings of the Workshop on Modeling Pronunciation Variation for Automatic Speech Recog- nition, Rolduc, The Netherlands, 1998.

  • W. Byrne, M. Finke, S. Khudanpur, J. McDonough, H. Nock, M. Riley, M. Saraclar, C. Wooters, and G. Zavaliagkos.
    Pronunciation modelling for conversational speech recognition: A status report from WS97.
    In Proceedings of IEEE ASRU, Santa Barbara, CA, 1997.

  • E. Fosler, M. Weintraub, S. Wegmann, Y.H. Kao, S. Khudanpur, C. Galles, and M. Saraclar.
    Automatic learning of word pronunciation from data.
    In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Philadel- phia, PA, 1996.