Joseph Keshet - RankMe

119 papers A* 9A 25B 1C 2Misc 10Journal 59Unranked 12

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models. CoRR Roi Benita, Michael Elad, Joseph Keshet
2026	A*	`conf`	Beyond Transcription: Mechanistic Interpretability in ASR. AAAI Neta Glazer, Yael Segal-Feldman, Hilit Segev, Aviv Shamsian, Asaf Buchnick, Gill Hetz, Ethan Fetaya, Joseph Keshet, Aviv Navon
2026	J	`jnl`	Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits. CoRR Gilad Nurko, Roi Benita, Yehoshua Dissen, Tomohiro Nakatani, Marc Delcroix, Shoko Araki, Joseph Keshet
2026	J	`jnl`	Open-vocabulary keyword spotting with hyper-matched filters for small footprint devices. Comput. Speech Lang. Yael Segal-Feldman, Ann R. Bradlow, Matthew Goldrick, Joseph Keshet
2025	J	`jnl`	Beyond Transcription: Mechanistic Interpretability in ASR. CoRR Neta Glazer, Yael Segal-Feldman, Hilit Segev, Aviv Shamsian, Asaf Buchnick, Gill Hetz, Ethan Fetaya, Joseph Keshet, Aviv Navon
2025	J	`jnl`	CarelessWhisper: Turning Whisper into a Causal Streaming Model. CoRR Tomer Krichli, Bhiksha Raj, Joseph Keshet
2025	J	`jnl`	Designing Scheduling for Diffusion Models via Spectral Analysis. CoRR Roi Benita, Michael Elad, Joseph Keshet
2025	J	`jnl`	Drax: Speech Recognition with Discrete Flow Matching. CoRR Aviv Navon, Aviv Shamsian, Neta Glazer, Yael Segal-Feldman, Gill Hetz, Joseph Keshet, Ethan Fetaya
2025	J	`jnl`	Enhancing analysis of diadochokinetic speech using deep neural networks. Comput. Speech Lang. Yael Segal-Feldman, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts, Joseph Keshet
2025	A	`conf`	FlowTSE: Target Speaker Extraction with Flow Matching. INTERSPEECH Aviv Navon, Aviv Shamsian, Yael Segal-Feldman, Neta Glazer, Gil Hetz, Joseph Keshet
2025	J	`jnl`	FlowTSE: Target Speaker Extraction with Flow Matching. CoRR Aviv Navon, Aviv Shamsian, Yael Segal-Feldman, Neta Glazer, Gill Hetz, Joseph Keshet
2025	J	`jnl`	How Does a Deep Neural Network Look at Lexical Stress? CoRR Itai Allouche, Itay Asael, Rotem Rousso, Vered Dassa, Ann R. Bradlow, Seung-Eun Kim, Matthew Goldrick, Joseph Keshet
2025	J	`jnl`	Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices. CoRR Yael Segal-Feldman, Ann R. Bradlow, Matthew Goldrick, Joseph Keshet
2025	J	`jnl`	UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching. CoRR Neta Glazer, Aviv Navon, Yael Segal, Aviv Shamsian, Hilit Segev, Asaf Buchnick, Menachem Pirchi, Gill Hetz, Joseph Keshet
2025	Misc	`conf`	Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR. ICASSP Yael Segal-Feldman, Aviv Shamsian, Aviv Navon, Gill Hetz, Joseph Keshet
2025	C	`conf`	WhisperNER: Unified Open Named Entity and Speech Recognition. ASRU Gil Ayache, Menachem Pirchi, Aviv Navon, Aviv Shamsian, Gill Hetz, Joseph Keshet
2024	A*	`conf`	DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation. ICLR Roi Benita, Michael Elad, Joseph Keshet
2024	A	`conf`	Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network. INTERSPEECH Yehoshua Dissen, Shiry Yonash, Israel Cohen, Joseph Keshet
2024	J	`jnl`	Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network. CoRR Yehoshua Dissen, Shiry Yonash, Israel Cohen, Joseph Keshet
2024	A	`conf`	HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing. INTERSPEECH Arnon Turetzky, Or Tal, Yael Segal, Yehoshua Dissen, Ella Zeldes, Amit Roth, Eyal Cohen, Yosi Shrem, Bronya Roni Chernyak, Olga Seleznova, Joseph Keshet, Yossi Adi
2024	J	`jnl`	HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing. CoRR Arnon Turetzky, Or Tal, Yael Segal-Feldman, Yehoshua Dissen, Ella Zeldes, Amit Roth, Eyal Cohen, Yosi Shrem, Bronya Roni Chernyak, Olga Seleznova, Joseph Keshet, Yossi Adi
2024	A	`conf`	Keyword-Guided Adaptation of Automatic Speech Recognition. INTERSPEECH Aviv Shamsian, Aviv Navon, Neta Glazer, Gill Hetz, Joseph Keshet
2024	J	`jnl`	Keyword-Guided Adaptation of Automatic Speech Recognition. CoRR Aviv Shamsian, Aviv Navon, Neta Glazer, Gill Hetz, Joseph Keshet
2024	Misc	`conf`	Open-Vocabulary Keyword-Spotting with Adaptive Instance Normalization. ICASSP Aviv Navon, Aviv Shamsian, Neta Glazer, Gill Hetz, Joseph Keshet
2024	A	`conf`	Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment. INTERSPEECH Rotem Rousso, Eyal Cohen, Joseph Keshet, Eleanor Chodroff
2024	J	`jnl`	Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR. CoRR Yael Segal-Feldman, Aviv Shamsian, Aviv Navon, Gill Hetz, Joseph Keshet
2024	J	`jnl`	WhisperNER: Unified Open Named Entity and Speech Recognition. CoRR Gil Ayache, Menachem Pirchi, Aviv Navon, Aviv Shamsian, Gill Hetz, Joseph Keshet
2023	J	`jnl`	Combining Language Models For Specialized Domains: A Colorful Approach. CoRR Daniel Eitan, Menachem Pirchi, Neta Glazer, Shai Meital, Gil Ayache, Gidon Krendel, Aviv Shamsian, Aviv Navon, Gill Hetz, Joseph Keshet
2023	J	`jnl`	DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation. CoRR Roi Benita, Michael Elad, Joseph Keshet
2023	J	`jnl`	Open-vocabulary Keyword-spotting with Adaptive Instance Normalization. CoRR Aviv Navon, Aviv Shamsian, Neta Glazer, Gill Hetz, Joseph Keshet
2022	A*	`conf`	A Baseline for Detecting Out-of-Distribution Examples in Image Captioning. ACM Multimedia Gal-Lev Shalev, Gabi Shalev, Joseph Keshet
2022	J	`jnl`	A Baseline for Detecting Out-of-Distribution Examples in Image Captioning. CoRR Gabi Shalev, Gal-Lev Shalev, Joseph Keshet
2022	J	`jnl`	Correcting Misproducted Speech using Spectrogram Inpainting. CoRR Talia Ben Simon, Felix Kreuk, Faten Awwad, Jacob T. Cohen, Joseph Keshet
2022	A	`conf`	Correcting Mispronunciations in Speech using Spectrogram Inpainting. INTERSPEECH Talia Ben Simon, Felix Kreuk, Faten Awwad, Jacob T. Cohen, Joseph Keshet
2022	A	`conf`	DDKtor: Automatic Diadochokinetic Speech Analysis. INTERSPEECH Yael Segal, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts, Joseph Keshet
2022	J	`jnl`	DDKtor: Automatic Diadochokinetic Speech Analysis. CoRR Yael Segal, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts, Joseph Keshet
2022	A	`conf`	DeepFry: Identifying Vocal Fry Using Deep Neural Networks. INTERSPEECH Bronya Roni Chernyak, Talia Ben Simon, Yael Segal, Jeremy Steffman, Eleanor Chodroff, Jennifer Cole, Joseph Keshet
2022	J	`jnl`	DeepFry: Identifying Vocal Fry Using Deep Neural Networks. CoRR Bronya Roni Chernyak, Talia Ben Simon, Yael Segal, Jeremy Steffman, Eleanor Chodroff, Jennifer S. Cole, Joseph Keshet
2022	A	`conf`	Formant Estimation and Tracking using Probabilistic Heat-Maps. INTERSPEECH Yosi Shrem, Felix Kreuk, Joseph Keshet
2022	J	`jnl`	Formant Estimation and Tracking using Probabilistic Heat-Maps. CoRR Yosi Shrem, Felix Kreuk, Joseph Keshet
2022	A	`conf`	Self-supervised Speaker Diarization. INTERSPEECH Yehoshua Dissen, Felix Kreuk, Joseph Keshet
2022	J	`jnl`	Self-supervised Speaker Diarization. CoRR Yehoshua Dissen, Felix Kreuk, Joseph Keshet
2022	J	`jnl`	Speech Time-Scale Modification With GANs. IEEE Signal Process. Lett. Eyal Cohen, Felix Kreuk, Joseph Keshet
2022	J	`jnl`	THOR: Threshold-Based Ranking Loss for Ordinal Regression. CoRR Tzeviya Sylvia Fuchs, Joseph Keshet
2022	J	`jnl`	Unsupervised Word Segmentation using K Nearest Neighbors. CoRR Tzeviya Sylvia Fuchs, Yedid Hoshen, Joseph Keshet
2021	—	`conf`	Adversarial Robustness for Face Recognition: How to Introduce Ensemble Diversity among Feature Extractors? SafeAI@AAAI Takuma Amada, Kazuya Kakizaki, Seng Pei Liew, Toshinori Araki, Joseph Keshet, Jun Furukawa
2021	Misc	`conf`	CNN-Based Spoken Term Detection and Localization without Dynamic Programming. ICASSP Tzeviya Sylvia Fuchs, Yael Segal, Joseph Keshet
2021	J	`jnl`	CNN-based Spoken Term Detection and Localization without Dynamic Programming. CoRR Tzeviya Sylvia Fuchs, Yael Segal, Joseph Keshet
2021	J	`jnl`	Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy. CoRR Bronya Roni Chernyak, Bhiksha Raj, Tamir Hazan, Joseph Keshet
2021	C	`conf`	Fairness in the Eyes of the Data: Certifying Machine-Learning Models. AIES Shahar Segal, Yossi Adi, Benny Pinkas, Carsten Baum, Chaya Ganesh, Joseph Keshet
2021	J	`jnl`	Pitch Estimation by Multiple Octave Decoders. IEEE Signal Process. Lett. Yael Segal, May Arama-Chayoth, Joseph Keshet
2020	J	`jnl`	Fairness in the Eyes of the Data: Certifying Machine-Learning Models. CoRR Shahar Segal, Yossi Adi, Benny Pinkas, Carsten Baum, Chaya Ganesh, Joseph Keshet
2020	A	`conf`	Hide and Speak: Towards Deep Neural Networks for Speech Steganography. INTERSPEECH Felix Kreuk, Yossi Adi, Bhiksha Raj, Rita Singh, Joseph Keshet
2020	B	`conf`	Minimal Modifications of Deep Neural Networks using Verification. LPAR Ben Goldberger, Guy Katz, Yossi Adi, Joseph Keshet
2020	J	`jnl`	Online prediction of time series with assumed behavior. Eng. Appl. Artif. Intell. Ariel Rosenfeld, Moshe Cohen, Sarit Kraus, Joseph Keshet
2020	Misc	`conf`	Phoneme Boundary Detection Using Learnable Segmental Features. ICASSP Felix Kreuk, Yaniv Sheena, Joseph Keshet, Yossi Adi
2020	J	`jnl`	Phoneme Boundary Detection using Learnable Segmental Features. CoRR Felix Kreuk, Yaniv Sheena, Joseph Keshet, Yossi Adi
2020	J	`jnl`	Redesigning the classification layer by randomizing the class representation vectors. CoRR Gabi Shalev, Gal-Lev Shalev, Joseph Keshet
2020	A	`conf`	Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation. INTERSPEECH Felix Kreuk, Joseph Keshet, Yossi Adi
2020	J	`jnl`	Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation. CoRR Felix Kreuk, Joseph Keshet, Yossi Adi
2019	J	`jnl`	Dr.VOT : Measuring Positive and Negative Voice Onset Time in the Wild. CoRR Yosi Shrem, Matthew Goldrick, Joseph Keshet
2019	A	`conf`	Dr.VOT: Measuring Positive and Negative Voice Onset Time in the Wild. INTERSPEECH Yosi Shrem, Matthew Goldrick, Joseph Keshet
2019	J	`jnl`	Hide and Speak: Deep Neural Networks for Speech Steganography. CoRR Felix Kreuk, Yossi Adi, Bhiksha Raj, Rita Singh, Joseph Keshet
2019	A	`conf`	SpeechYOLO: Detection and Localization of Speech Objects. INTERSPEECH Yael Segal, Tzeviya Sylvia Fuchs, Joseph Keshet
2019	J	`jnl`	SpeechYOLO: Detection and Localization of Speech Objects. CoRR Yael Segal, Tzeviya Sylvia Fuchs, Joseph Keshet
2018	J	`jnl`	Adversarial Examples on Discrete Sequences for Beating Whole-Binary Malware Detection. CoRR Felix Kreuk, Assi Barak, Shir Aviv-Reuven, Moran Baruch, Benny Pinkas, Joseph Keshet
2018	Misc	`conf`	Fooling End-To-End Speaker Verification With Adversarial Examples. ICASSP Felix Kreuk, Yossi Adi, Moustapha Cissé, Joseph Keshet
2018	J	`jnl`	Fooling End-to-end Speaker Verification by Adversarial Examples. CoRR Felix Kreuk, Yossi Adi, Moustapha Cissé, Joseph Keshet
2018	A*	`conf`	Out-of-Distribution Detection using Multiple Semantic Label Representations. NeurIPS Gabi Shalev, Yossi Adi, Joseph Keshet
2018	J	`jnl`	Out-of-Distribution Detection using Multiple Semantic Label Representations. CoRR Gabi Shalev, Yossi Adi, Joseph Keshet
2018	A*	`conf`	Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring. USENIX Security Symposium Yossi Adi, Carsten Baum, Moustapha Cissé, Benny Pinkas, Joseph Keshet
2018	J	`jnl`	Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring. CoRR Yossi Adi, Carsten Baum, Moustapha Cissé, Benny Pinkas, Joseph Keshet
2017	A	`conf`	Automatic Measurement of Pre-Aspiration. INTERSPEECH Yaniv Sheena, Mísa Hejná, Yossi Adi, Joseph Keshet
2017	J	`jnl`	Automatic Measurement of Pre-aspiration. CoRR Yaniv Sheena, Mísa Hejná, Yossi Adi, Joseph Keshet
2017	J	`jnl`	Houdini: Fooling Deep Structured Prediction Models. CoRR Moustapha Cissé, Yossi Adi, Natalia Neverova, Joseph Keshet
2017	—	`conf`	Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples. NIPS Moustapha Cissé, Yossi Adi, Natalia Neverova, Joseph Keshet
2017	J	`jnl`	Learning Similarity Function for Pronunciation Variations. CoRR Einat Naaman, Yossi Adi, Joseph Keshet
2017	A	`conf`	Learning Similarity Functions for Pronunciation Variations. INTERSPEECH Einat Naaman, Yossi Adi, Joseph Keshet
2017	Misc	`conf`	Sequence segmentation using joint RNN and structured prediction models. ICASSP Yossi Adi, Joseph Keshet, Emily Cibelli, Matthew Goldrick
2017	J	`jnl`	Spoken Term Detection Automatically Adjusted for a Given Threshold. IEEE J. Sel. Top. Signal Process. Tzeviya Fuchs, Joseph Keshet
2016	A	`conf`	Automatic Measurement of Voice Onset Time and Prevoicing Using Recurrent Neural Networks. INTERSPEECH Yossi Adi, Joseph Keshet, Olga Dmitrieva, Matthew Goldrick
2016	J	`jnl`	Automatic measurement of vowel duration via structured prediction. CoRR Yossi Adi, Joseph Keshet, Emily Cibelli, Erin Gustafson, Cynthia G. Clopper, Matthew Goldrick
2016	J	`jnl`	Domain Adaptation For Formant Estimation Using Deep Learning. CoRR Yehoshua Dissen, Joseph Keshet, Jacob Goldberger, Cynthia G. Clopper
2016	A	`conf`	Formant Estimation and Tracking Using Deep Learning. INTERSPEECH Yehoshua Dissen, Joseph Keshet
2016	A	`conf`	Online Prediction of Exponential Decay Time Series with Human-Agent Application. ECAI Ariel Rosenfeld, Joseph Keshet, Claudia V. Goldman, Sarit Kraus
2016	J	`jnl`	Sequence Segmentation Using Joint RNN and Structured Prediction Models. CoRR Yossi Adi, Joseph Keshet, Emily Cibelli, Matthew Goldrick
2016	J	`jnl`	StructED: Risk Minimization in Structured Prediction. J. Mach. Learn. Res. Yossi Adi, Joseph Keshet
2016	Misc	`conf`	The relationship of voice onset time and Voice Offset Time to physical age. ICASSP Rita Singh, Joseph Keshet, Deniz Gençaga, Bhiksha Raj
2015	J	`jnl`	Context-Based Prediction of App Usage. CoRR Joseph Keshet, Adam Kariv, Dvir Volk, Joey Simhon
2015	J	`jnl`	Risk Minimization in Structured Prediction using Orbit Loss. CoRR Danny Karmon, Joseph Keshet
2015	—	`conf`	Vowel duration measurement using deep neural networks. MLSP Yossi Adi, Joseph Keshet, Matthew Goldrick
2013	Misc	`conf`	Discriminative articulatory models for spoken term detection in low-resource conversational settings. ICASSP Rohit Prabhavalkar, Karen Livescu, Eric Fosler-Lussier, Joseph Keshet
2013	—	`conf`	Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions. NIPS Tamir Hazan, Subhransu Maji, Joseph Keshet, Tommi S. Jaakkola
2013	A*	`conf`	Predicting Human Strategic Decisions Using Facial Expressions. IJCAI Noam Peled, Moshe Bitan, Joseph Keshet, Sarit Kraus
2012	A	`conf`	Automatic Measurement of Positive and Negative Voice Onset Time. INTERSPEECH Katharine Henry, Morgan Sonderegger, Joseph Keshet
2012	—	`conf`	Discriminative Pronunciation Modeling: A Large-Margin, Feature-Rich Approach. ACL (1) Hao Tang, Joseph Keshet, Karen Livescu
2012	—	`conf`	Discriminative spoken term detection with limited data. MLSLP Rohit Prabhavalkar, Joseph Keshet, Karen Livescu, Eric Fosler-Lussier
2011	A*	`conf`	A GPU-tailored approach for training kernelized SVMs. KDD Andrew Cotter, Nathan Srebro, Joseph Keshet
2011	A	`conf`	Direct Error Rate Minimization of Hidden Markov Models. INTERSPEECH Joseph Keshet, Chih-Chieh Cheng, Mark Stoehr, David A. McAllester
2011	J	`jnl`	Explicit Approximations of the Gaussian Kernel CoRR Andrew Cotter, Joseph Keshet, Nathan Srebro
2011	—	`conf`	Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss. NIPS David A. McAllester, Joseph Keshet
2011	Misc	`conf`	PAC-Bayesian approach for minimization of phoneme error rate. ICASSP Joseph Keshet, David A. McAllester, Tamir Hazan
2010	A	`conf`	Automatic discriminative measurement of voice onset time. INTERSPEECH Morgan Sonderegger, Joseph Keshet
2010	—	`conf`	Direct Loss Minimization for Structured Prediction. NIPS David A. McAllester, Tamir Hazan, Joseph Keshet
2009	J	`jnl`	Bounded Kernel-Based Online Learning. J. Mach. Learn. Res. Francesco Orabona, Joseph Keshet, Barbara Caputo
2009	J	`jnl`	Discriminative keyword spotting. Speech Commun. Joseph Keshet, David Grangier, Samy Bengio
2009	Misc	`conf`	Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional LSTM networks. ICASSP Martin Wöllmer, Florian Eyben, Joseph Keshet, Alex Graves, Björn W. Schuller, Gerhard Rigoll
2008	—	`conf`	Support Vector Machines with a Reject Option. NIPS Yves Grandvalet, Alain Rakotomamonjy, Joseph Keshet, Stéphane Canu
2008	A*	`conf`	The projectron: a bounded kernel-based Perceptron. ICML Francesco Orabona, Joseph Keshet, Barbara Caputo
2007	J	`jnl`	A Large Margin Algorithm for Speech-to-Phoneme and Music-to-Score Alignment. IEEE Trans. Speech Audio Process. Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer, Dan Chazan
2007	—	`—`	Large margin algorithms for discriminative continuous speech recognition (זיהוי דיבור רציף באמצעות אלגוריתמי שוליים רחבים.). Joseph Keshet
2006	A	`conf`	Discriminative kernel-based phoneme sequence recognition. INTERSPEECH Joseph Keshet, Shai Shalev-Shwartz, Samy Bengio, Yoram Singer, Dan Chazan
2006	J	`jnl`	Online Passive-Aggressive Algorithms. J. Mach. Learn. Res. Koby Crammer, Ofer Dekel, Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer
2005	A	`conf`	Phoneme alignment based on discriminative learning. INTERSPEECH Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer, Dan Chazan
2004	—	`conf`	An Online Algorithm for Hierarchical Phoneme Classification. MLMI Ofer Dekel, Joseph Keshet, Yoram Singer
2004	A*	`conf`	Large margin hierarchical classification. ICML Ofer Dekel, Joseph Keshet, Yoram Singer
2004	—	`conf`	Learning to Align Polyphonic Music. ISMIR Shai Shalev-Shwartz, Joseph Keshet, Yoram Singer
2002	—	`conf`	Kernel Design Using Boosting. NIPS Koby Crammer, Joseph Keshet, Yoram Singer
2001	A	`conf`	Plosive spotting with margin classifiers. INTERSPEECH Joseph Keshet, Dan Chazan, Ben-Zion Bobrovsky