Publications

2023

• Roi Benita, Michael Elad, Joseph Keshet, DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation, preprint, 2023.
• Kasia Hitczenko, Yael Segal, Joseph Keshet, Matthew Goldrick & Vijay A. Mittal, Speech Characteristics Yield Important Clues about Motor Function: Speech Variability in Individuals at Clinical High-Risk for Psychosis, Nature Schizophrenia volume 9, Article number: 60 (2023)
• Aviv Navon, Aviv Shamsian, Neta Glazer, Gill Hetz, Joseph Keshet, Open Vocabulary Keyword-Spotting with Adaptive Instance Normalization, preprint, 2023.
• Daniel Eitan, Menachem Pirchi, Neta Glazer, Shai Meital, Gil Ayach, Aviv Shamsian, Aviv Navon, Gill Hetz, Joseph Keshet, Combining language models for specialized domains: a colorful approach, preprint, 2023.

2022

• Gabi Shalev, Gal-Lev Shalev, Joseph Keshet, A Baseline for Detecting Out-of-Distribution Examples in Image Captioning, accepted to ACM Multimedia 2022, Lisbon, Portugal
• Bronya Roni Chernyak, Talia Ben Simon, Yael Segal, Jeremy Steffman, Eleanor Chodroff, Jennifer Cole, Joseph Keshet, DeepFry: Identifying Vocal Fry Using Deep Neural Networks, The 23rd Annual Conference of the International Speech Communication Association (Interspeech), Incheon, Korea, 2022.
• Yael Segal, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts, Joseph Keshet, DDKtor: Automatic Diadochokinetic Speech Analysis, The 23rd Annual Conference of the International Speech Communication Association (Interspeech), Incheon, Korea, 2022.
• Yosi Shrem, Felix Kreuk, Joseph Keshet, Formant Estimation and Tracking using Probabilistic Heat-Maps, The 23rd Annual Conference of the International Speech Communication Association (Interspeech), Incheon, Korea, 2022.
• Yehoshua Dissen, Felix Kreuk, Joseph Keshet, Self-supervised Speaker Diarization, The 23rd Annual Conference of the International Speech Communication Association (Interspeech), Incheon, Korea, 2022.
• Talia ben Simon, Felix Kreuk, Faten Awwad, Jacob T. Cohen, Joseph Keshet, Correcting Misproducted Speech using Spectrogram Inpainting, The 23rd Annual Conference of the International Speech Communication Association (Interspeech), Incheon, Korea, 2022.
• Tzeviya Sylvia Fuchs, Yedid Hoshen, Joseph Keshet, Unsupervised Word Segmentation using K Nearest Neighbors, The 23rd Annual Conference of the International Speech Communication Association (Interspeech), Incheon, Korea, 2022.
• Eyal Cohen, Felix Kreuk, Joseph Keshet, Speech Time-Scale Modification with GANs, IEEE Signal Processing Letters, Vol. 29, pp. 1067-1071, April 2022. DOI: 10.1109/LSP.2022.3164361. 
• Tzeviya Sylvia Fuchs, Joseph Keshet, THOR: Threshold-Based Ranking Loss for Ordinal Regression, working paper on arXiv, 2022.

2021

• Gal-Lev Shalev, Gabi Shalev, Joseph Keshet, On Randomized Classification Layers and Their Implications in Natural Language Generation, Proceedings of the Third Workshop on Multimodal Artificial Intelligence, NAACL 2021
• Yael Segal, May Arama-Chayoth, Joseph Keshet, Pitch Estimation by Multiple Octave Decoders, IEEE Signal Processing Letters, Vol. 28, pp. 1610-1614, July 2021.
• Bronya Roni Chernyak, Bhiksha Raj, Tamir Hazan, Joseph Keshet, Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy, RobustML Workshop, Ninth International Conference on Learning Representations (ICLR), 2021. Code.
• Shahar Segal, Yossi Adi, Benny Pinkas, Carsten Baum, Chaya Ganesh, and Joseph Keshet, Fairness in the Eyes of the Data: Certifying Machine-Learning Models, AAAI/ACM conference on AI, Ethics, and Society (AIES), 2021.
• Tzeviya Sylvia Fuchs, Yael Segal, and Joseph Keshet, CNN-based Spoken Term Detection and Localization without Dynamic Programming, the 46rd IEEE International Conference in Acoustic, Speech and Signal Processing (ICASSP), 2021.
• Adar Paz, Eshkol Rafaeli, Eran Bar-Kalifa, Eva Gilboa-Schectman, Sharon Gannot, Bracha Laufer-Goldshtein, Shrikanth Narayanan, Joseph Keshet, Dana Atzil-Slonim, Intrapersonal and Interpersonal Vocal Affect Dynamics During Psychotherapy, Journal of Consulting and Clinical Psychology, Vol. 89, Issue 3, pp. 227, ASA, March 2021.

2020

• Felix Kreuk, Joseph Keshet and Yossi Adi, Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation, The 21th Annual Conference of the International Speech Communication Association (Interspeech), Shanghai, China, 2020.
• Felix Kreuk, Yossi Adi, Bhiksha Raj, Rita Singh and Joseph Keshet, Hide and Speak: Towards Deep Neural Networks for Speech Steganography, The 21th Annual Conference of the International Speech Communication Association (Interspeech), Shanghai, China, 2020. Speech examples can be found here.
• Matthew Goldrick, Yosi Shrem, Oriana Kilbourn-Ceron, Cristina Baus, and Joseph Keshet, Using automated acoustic analysis to explore the link between planning and articulation in second-language speech production, Language, Cognition and Neuroscience, Volume 36, Issue 7, pp. 824-839, 2020.
• Ben Goldberger, Guy Katz, Yossi Adi and Joseph Keshet, Minimal Modifications of Deep Neural Networks using Verification, 23rd International Conference on Logic for Programming, Artificial Intelligence and Reasoning (LPAR23), 2020.
• Felix Kreuk, Yanov Sheena, Joseph Keshet, Yossi Adi, Phoneme Boundary Detection using Learnable Segmental Features, 45th International Conference in Acoustic, Speech and Signal Processing (ICASSP), 2020.
• Ariel Rosenfeld, Moshe Cohen, Sarit Kraus, and Joseph Keshet, Online Prediction of Time Series with Assumed Behavior, Engineering Applications of Artificial Intelligence, Volume 88, 103358, February 2020.

2019

• Yosi Shrem, Matthew Goldrick, and Joseph Keshet, Dr.VOT : Measuring Positive and Negative Voice Onset Time in the Wild , The 20th Annual Conference of the International Speech Communication Association (Interspeech), Graz, 2019.
• Yael Segal*, Tzeviya Sylvia Fuchs*, Joseph Keshet, SpeechYOLO: Detection and Localization of Speech Objects, The 20th Annual Conference of the International Speech Communication Association (Interspeech), Graz, 2019.
• Jacob T. Cohen, Alma Cohen, Limor Benyamini, Yossi Adi, Joseph Keshet, Predicting glottal closure insufficiency using fundamental frequency contour analysis, Head & Neck, Journal of the Sciences and Specialities of the Head and Neck, Volume 41, Issue 7, pp. 2324-2331, July 2019.
• Yehoshua Dissen, Jacob Goldberger, and Joseph Keshet, Formant Estimation and Tracking: A Deep Learning Approach, Journal of the Acoustical Society of America, 145 (2), February 2019.

2018

• Joseph Keshet, Automatic speech recognition: A primer for speech-language pathology researchers, International Journal of Speech-Language Pathology, Vol. 20 No. 6, pp. 599-609, 2018.
• Esteban Buz, Adam Buchwald, Tzeviya Fuchs, and Joseph Keshet, Assessing Automatic VOT Annotation using Unimpaired and Impaired Speech, International Journal of Speech-Language Pathology, Vol. 20, No, 6, pp. 624-634, 2018.
• Gabi Shalev, Yossi Adi, and Joseph Keshet, Out-of-Distribution Detection using Multiple Semantic Label Representations, Neural Information and Processing Systems (NIPS), 2018.
• Matthew Goldrick, Rhonda McClain, Emily Cibelli, Yossi Adi , Erin Gustafson, Cornelia Moers, and Joseph Keshet, The influence of lexical selection disruptions on articulation, Journal of Experimental Psychology: Learning, Memory, and Cognition, July 2018.
• Yossi Adi, Carsten Baum, Moustapha Cisse, Benny Pinkas, Joseph Keshet, Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring, Usenix, 2018.
• Felix Kreuk, Assi Barak, Shir Aviv-Reuven, Moran Baruch, Benny Pinkas, Joseph Keshet, Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples, working paper on arXiv, 2018.
• Felix Kreuk, Yossi Adi, Moustapha Cisse, Joseph Keshet, Fooling End-to-end Speaker Verification by Adversarial Examples, the 43rd IEEE International Conference in Acoustic, Speech and Signal Processing (ICASSP), Calgari, Canada, 2018.

2017

• Tzeviya Fuchs, Joseph Keshet, Spoken Term Detection Automatically Adjusted for a Given Threshold, IEEE Journal of Selected Topics in Signal Processing, Dec 2017, Volume 11, Issue 8, pp. 1-8.
• Moustapha Cisse, Yossi Adi, Natalia Neverova, Joseph Keshet, Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples, Neural Information and Processing Systems (NIPS), 2017.
• Yaniv Sheena, Míša Hejná, Yossi Adi, Joseph Keshet, Automatic Measurement of Pre-aspiration, The 18th Annual Conference of the International Speech Communication Association (Interspeech), Stockholm, 2017.
• Einat Naaman, Yossi Adi, Joseph Keshet, Learning Similarity Functions for Pronunciation Variations, The 18th Annual Conference of the International Speech Communication Association (Interspeech), Stockholm, 2017.
• Yossi Adi, Joseph Keshet, Emily Cibelli, Matthew Goldrick, Sequence Segmentation Using Joint RNN and Structured Prediction Models, the 42st IEEE International Conference in Acoustic, Speech and Signal Processing (ICASSP), New Orleans, 2017.

2016

• Yossi Adi, Joseph Keshet, Emily Cibelli, Erin Gustafson, Cynthia Clopper, and Matthew Goldrick, Automatic Measurement of Vowel Duration via Structured Prediction, Journal of the Acoustical Society of America, Volume 140, Issue 6, 2016.
• Yehoshua Dissen, Joseph Keshet, Jacob Goldberger, Cynthia Clopper, Domain Adaptation For Formant Estimation Using Deep Learning, working paper on arXiv, 2016.
• Yehoshua Dissen and Joseph Keshet, Formant Estimation and Tracking using Deep Learning, The 17th Annual Conference of the International Speech Communication Association (Interspeech), San Francisco, CA, 2016.
• Yossi Adi, Joseph Keshet, Olga Dmitrieva, and Matt Goldrick, Automatic Measurement of Voice Onset Time and Prevoicing using Recurrent Neural Networks, The 17th Annual Conference of the International Speech Communication Association (Interspeech), San Francisco, CA, 2016.
• Joseph Keshet, Subhransu Maji, Tamir Hazan, and Tommi Jaakkola, Perturbation Models and PAC-Bayesian Generalization Bounds, in Perturbations, Optimization, and Statistics, Tamir Hazan, George Papandreou, and Daniel Tarlow, Eds., The MIT Press, 2016.
• Nisan Ozana, Stav Buchsbaum, Yael Bishitz, Yevgeny Beiderman, Zeev Schmilovitch, Ariel Schwarz, Amir Shemer, Joseph Keshet, and Zeev Zalevsky, An optical remote sensor for peanut kernel abortion classification, Applied Optics, Vol. 55, Issue 15, pp. 4005-4010, 2016.
• Rita Singh, Joseph Keshet, Eduard Hovy, Profiling hoax callers, IEEE Symposium on Technologies for Homeland Security (HST), 1-6, 2016
• Yossi Adi and Joseph Keshet, StructED : Risk Minimization in Structured Prediction, Journal of Machine Learning Research 17(64):1-5, 2016.
  Source code is available here.
• Matthew Goldrick, Joseph Keshet, Erin Gustafson, Jordana Heller, and Jeremy Needle, Automatic Analysis of Slips of the Tongue: Insights into the Cognitive Architecture of Speech Production, Cognition, 149, 31-39, 2016.
  Reproduction code is available on github.
• Rita Singh, Joseph Keshet, Deniz Gencaga, Bhiksha Raj, The Relationship of Voice Onset Time and Voice Offset Time to Physical Age, the 41st IEEE International Conference in Acoustic, Speech and Signal Processing (ICASSP), Shanghai, China, 2016.

2015

• Yossi Adi, Joseph Keshet, and Matt Goldrick, Vowel Duration Measurement using Deep Neural Networks, IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Boston, USA, 2015.
• Joseph Keshet, Adam Kariv, Arnon Dagan, Dvir Volk, and Joey Simhon, Context-Based Prediction of App Usage, working paper on arXiv, 2015.
• Danny Karmon, and Joseph Keshet, Risk Minimization in Structured Prediction using Orbit Loss, working paper on arXiv, 2015.
• Jacob T Cohen, Limor Benyamini, Yossi Adi and Joseph Keshet, Predicting Glottal Insufficiency using Pitch Analysis, The Annual Meeting of Otolaryngology Head and Neck Surgery, Eilat, 2015.

2014

• Joseph Keshet, Optimizing the Measure of Performance in Structured Prediction, in Advanced Structured Prediction, Sebastian Nowozin, Peter V. Gehler, Jeremy Jancsary, and Christoph H. Lampert, Eds., The MIT Press, 2014.
• Adiel Ben-Shalom, Joseph Keshet, Roni Yeger-Granot, Automatic analysis of music: Performance of cantillation signs in Yemenite Jewish traditional cantillation, Proceedings of the 9th Conference on Interdisciplinary Musicology (CIM14), Berlin, Germany, 2014.
• Adiel Ben-Shalom, Joseph Keshet, Doron Modan, and Asher Laufer, Automatic Tools for Analyzing Spoken Hebrew, Afeka Conferece for Speech Processing, 2014.

2013

• Tamir Hazan, Subhransu Maji, Joseph Keshet, Tommi Jaakkola, On Sampling from the Gibbs distribution with Random Maximum A-Posteriori Perturbations, Neural Information and Processing Systems (NIPS), 2013.
• Joseph Keshet, Discriminative Pronunciation Modeling, Afeka Conferece for Speech Processing, 2013.
• Joseph Keshet, Discriminative Keyword Spotting with Limited Data, Afeka Conferece for Speech Processing, 2013.
• Noam Peled, Moshe Bitan, Joseph Keshet, Sarit Kraus, Predicting Human Strategic Decisions Using Facial Expressions, International Joint Conference on Artificial Intelligence (IJCAI), Beijing, China, 2013.
• Rohit Prabhavalkar, Karen Livescu, Eric Fosler-Lussier, Joseph Keshet, Discriminative Articulatory Models for Spoken Term Detection in Low-Resource Conversational Settings, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada, 2013.

2012

• Rohit Prabhavalkar, Joseph Keshet, Karen Livescu and Eric Fosler-Lussier, Discriminative Spoken Term Detection with Limited Data, 2nd Symposium on Machine Learning in Speech and Language Processing, Portland, Oregon, 2012.
  A description of the utterances used in our experiments can be downloaded from here.
• Morgan Sonderegger and Joseph Keshet, Automatic Measurement of Voice Onset Time using Discriminative Structured Prediction, Journal of the Acoustical Society of America, Vol. 132, Issue 6, pp. 3965−3979, 2012. http://link.aip.org/link/?JAS/132/3965.
  Source code is available on github.
• Katharine Henry, Morgan Sonderegger and Joseph Keshet, Automatic Measurement of Positive and Negative Voice Onset Time, The 13th Annual Conference of the International Speech Communication Association (Interspeech), Portland, Oregon, 2012.
• Hao Tang, Joseph Keshet, and Karen Livescu, Discriminative Pronunciation Modeling: A Large-Margin, Feature-Rich Approach, The 50th Annual Meeting of the Association of Computational Linguistics (ACL), 2012.

2011

• David McAllester and Joseph Keshet, Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss, The 25th Annual Conference on Neural Information Processing Systems (NIPS), 2011 (full oral presentation).
• Andrew Cotter, Joseph Keshet, and Nathan Srebro, Explicit Approximations of the Gaussian Kernel, working paper on arXiv, 2011.
• Joseph Keshet, Chih-Chieh Cheng, Mark Stoehr, and David McAllester, Direct Error Rate Minimization of Hidden Markov Models, The 12th Annual Conference of the International Speech Communication Association (Interspeech), Florence, Italy, 2011.
• Andrew Cotter, Nathan Srebro, and Joseph Keshet, A GPU-Tailored Approach for Training Kernelized SVMs, The 17th ACM Conference on Knowledge Discovery and Data Mining (KDD), San Diego, CA, 2011.Source code, C and MATLAB interfaces and benchmarks can be found here.

2010

• Joseph Keshet, David McAllester, and Tamir Hazan, PAC-Bayesian Approach for Minimization of Phoneme Error Rate, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Prague, Czech Republic, 2011.
• David McAllester, Tamir Hazan and Joseph Keshet, Direct Loss Minimization for Structured Prediction, The 24th Annual Conference on Neural Information Processing Systems (NIPS), 2010.
• Morgan Sonderegger and Joseph Keshet, Automatic Discriminative Measurement of Voice Onset Time, The 12th Annual Conference of the International Speech Communication Association (INTERSPEECH), Chiba, Japan, 2010.

2009

• Francesco Orabona, Joseph Keshet, and Barbara Caputo, Bounded Kernel-Based Online Learning, Journal of Machine Learning Research, 10 (Nov):2643−2666, 2009.
• Martin Wöllmer, Florian Eyben, Joseph Keshet, Alex Graves, Björn Schuller, and Gerhard Rigoll, Robust Discriminative Keyword Spotting for Emotionally Colored Spontaneous Speech using Bidirectional LSTM Networks, IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Taipei, Taiwan, 2009.
• Joseph Keshet, David Grangier and Samy Bengio, Discriminative Keyword Spotting, Speech Communication, Volume 51, Issue 4, pp. 317-329, April 2009.
• Joseph Keshet and Samy Bengio, Eds., Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods, John Wiley & Sons, March 2009.

2008

• Yves Grandvalet, Alain Rakotomamonjy, Joseph Keshet, Stéphane Canu, Support Vector Machines with a Reject Option, The 22nd Annual Conference on Neural Information Processing Systems (NIPS), 2008.
• Francesco Orabona, Joseph Keshet and Barbara Caputo, The Projectron: a Bounded Kernel-Based Perceptron, The 25th International Conference on Machine Learning (ICML), Helsinki, Finland, 2008.
• Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer and Dan Chazan, A Large Margin Algorithm for Forced Alignment in Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods, Joseph Keshet and Samy Bengio, Eds., John Wiley & Sons, August 2008.
• Joseph Keshet and Dan Chazan, A Kernel Wrapper for Phoneme Sequence Recognition in Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods,Joseph Keshet and Samy Bengio, Eds., John Wiley & Sons, August 2008.
• Joseph Keshet, A Proposal for a Kernel-based Algorithm for Large Vocabulary Continuous Speech Recognition in Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods, Joseph Keshet and Samy Bengio, Eds., John Wiley & Sons, August 2008.
• David Grangier, Joseph Keshet and Samy Bengio, Discriminative Keyword Spotting, in Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods,Joseph Keshet and Samy Bengio, Eds., John Wiley & Sons, August 2008.

2007 and earlier

• Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer and Dan Chazan, Large Margin Algorithm for Speech-to-Phoneme and Music-to-Score Alignment, IEEE Trans. on Audio, Speech and Language Processing, 15(8), pp. 2373--2382, Nov. 2007.
• Joseph Keshet, Large Margin Algorithms for Discriminative Continuous Speech Recognition, Ph.D. dissertation, August 2007.
• Joseph Keshet, David Grangier and Samy Bengio, Discriminative Keyword Spotting, The 3rd Non-Linear Speech Processing Workshop (NOLISP), Paris, 2007.
• Joseph Keshet, Shai Shalev-Shwartz, Samy Bengio, Yoram Singer and Dan Chazan, Discriminative Kernel-Based Phoneme Sequence Recognition, The 9th International Conference on Spoken Language Processing (INTERSPEECH), Pittsburgh, PA, 2006.
• Koby Crammer, Ofer Dekel, Joseph Keshet, Shai Shalev-Shwartz and Yoram Singer, Online Passive-Aggressive Algorithms, Journal of Machine Learning Research, 7(Mar):551−585, 2006.
• Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer and Dan Chazan, Phoneme Alignment Based on Discriminative Learning, The 9th European Conference on Speech Communication and Technology (INTERSPEECH), Lisbon, 2005.
• Shai Shalev-Shwartz, Joseph Keshet and Yoram Singer, Learning to Align Polyphonic Music, The 5th International Conference on Music Information Retrieval (ISMIR), Barcelona, Spain, 2004. The Long version includes the proof of the theorem. Here you can find the dataset.
• Ofer Dekel, Joseph Keshet and Yoram Singer, An Online Algorithm for Hierarchical Phoneme Classification, Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI), Martigny, Switzerland, 2004, LNCS, Vol. 3361/2005, p.146, Springer-Verlag.
• Ofer Dekel, Joseph Keshet and Yoram Singer, Large Margin Hierarchical Classification, The 21st International Conference on Machine Learning (ICML), Banff, Canada, 2004
• Koby Crammer, Joseph Keshet and Yoram Singer, Kernel Design using Boosting, The 15th Annual Conference on Neural Information Processing Systems (NIPS), 2002.
• Joseph Keshet, Dan Chazan and Ben-Zion Bobrovsky, Plosive Spotting with Margin Classifiers, The 7th European Conference on Speech Communication and Technology (EUROSPEECH), Aalborg, Denmark, 2001.