Saliency map

In computer vision, a saliency map is an image that highlights either the region on which people's eyes focus first or the most relevant regions for machine learning models. The goal of a saliency map is to reflect the degree of importance of a pixel to the human visual system or an otherwise opaque ML model. For example, in this image, a person first looks at the fort and light clouds, so they should be highlighted on the saliency map. == Application == === Overview === Saliency maps have applications in a variety of different problems. Some general applications: ==== Human eye ==== Image and video compression: The human eye focuses only on a small region of interest in the frame. Therefore, it is not necessary to compress the entire frame with uniform quality. According to the authors, using a salience map reduces the final size of the video with the same visual perception. Image and video quality assessment: The main task for an image or video quality metric is a high correlation with user opinions. Differences in salient regions are given more importance and thus contribute more to the quality score. Image retargeting: It aims at resizing an image by expanding or shrinking the noninformative regions. Therefore, retargeting algorithms rely on the availability of saliency maps that accurately estimate all the salient image details. Object detection and recognition: Instead of applying a computationally complex algorithm to the whole image, we can use it to the most salient regions of an image most likely to contain an object. the primary visual cortex (V1) appears to be responsible for the saliency map, according to the V1 Saliency Hypothesis. ==== Explainable artificial intelligence ==== Saliency maps are a prominent tool in explainable artificial intelligence, providing visual explanations of the decision-making process of machine learning models, particularly deep neural networks. These maps highlight the regions in input data that are most influential on the model's output, effectively indicating where the model is "looking" when making a prediction. In image classification tasks, for example, saliency maps can identify pixels or regions that contribute most to a specific class decision. Developed for convolutional neural networks, saliency mapping techniques range from simply taking the gradient of the class score with respect to the input data to more complex algorithms, such as integrated gradients and class activation mapping. In transformer architecture, attention mechanisms led to analogous saliency maps, such as attention maps, attention rollouts, and class-discriminative attention maps. === Saliency as a segmentation problem === Saliency estimation may be viewed as an instance of image segmentation. In computer vision, image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as superpixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics. == Algorithms == === Overview === There are three forms of classic saliency estimation algorithms implemented in OpenCV: Static saliency: Relies on image features and statistics to localize the regions of interest of an image. Motion saliency: Relies on motion in a video, detected by optical flow. Objects that move are considered salient. Objectness: Objectness reflects how likely an image window covers an object. These algorithms generate a set of bounding boxes of where an object may lie in an image. In addition to classic approaches, neural-network-based are also popular. There are examples of neural networks for motion saliency estimation: TASED-Net: It consists of two building blocks. First, the encoder network extracts low-resolution spatiotemporal features, and then the following prediction network decodes the spatially encoded features while aggregating all the temporal information. STRA-Net: It emphasizes two essential issues. First, spatiotemporal features integrated via appearance and optical flow coupling, and then multi-scale saliency learned via attention mechanism. STAViS: It combines spatiotemporal visual and auditory information. This approach employs a single network that learns to localize sound sources and to fuse the two saliencies to obtain a final saliency map. There's a new static saliency in the literature with name visual distortion sensitivity. It is based on the idea that the true edges, i.e. object contours, are more salient than the other complex textured regions. It detects edges in a different way from the classic edge detection algorithms. It uses a fairly small threshold for the gradient magnitudes to consider the mere presence of the gradients. So, it obtains 4 binary maps for vertical, horizontal and two diagonal directions. The morphological closing and opening are applied to the binary images to close the small gaps. To clear the blob-like shapes, it utilizes the distance transform. After all, the connected pixel groups are individual edges (or contours). A threshold of size of connected pixel set is used to determine whether an image block contains a perceivable edge (salient region) or not. === Example implementation === First, we should calculate the distance of each pixel to the rest of pixels in the same frame: S A L S ( I k ) = ∑ i = 1 N | I k − I i | {\displaystyle \mathrm {SALS} (I_{k})=\sum _{i=1}^{N}|I_{k}-I_{i}|} I i {\displaystyle I_{i}} is the value of pixel i {\displaystyle i} , in the range of [0,255]. The following equation is the expanded form of this equation. SALS(Ik) = |Ik - I1| + |Ik - I2| + ... + |Ik - IN| Where N is the total number of pixels in the current frame. Then we can further restructure our formula. We put the value that has same I together. SALS(Ik) = Σ Fn × |Ik - In| Where Fn is the frequency of In. And the value of n belongs to [0,255]. The frequencies is expressed in the form of histogram, and the computational time of histogram is ⁠ O ( N ) {\displaystyle O(N)} ⁠ time complexity. ==== Time complexity ==== This saliency map algorithm has ⁠ O ( N ) {\displaystyle O(N)} ⁠ time complexity. Since the computational time of histogram is ⁠ O ( N ) {\displaystyle O(N)} ⁠ time complexity which N is the number of pixel's number of a frame. Besides, the minus part and multiply part of this equation need 256 times operation. Consequently, the time complexity of this algorithm is ⁠ O ( N + 256 ) {\displaystyle O(N+256)} ⁠ which equals to ⁠ O ( N ) {\displaystyle O(N)} ⁠. ==== Pseudocode ==== All of the following code is pseudo MATLAB code. First, read data from video sequences. After we read data, we do superpixel process to each frame. Spnum1 and Spnum2 represent the pixel number of current frame and previous pixel. Then we calculate the color distance of each pixel, this process we call it contract function. After this two process, we will get a saliency map, and then store all of these maps into a new FileFolder. ==== Difference in algorithms ==== The major difference between function one and two is the difference of contract function. If spnum1 and spnum2 both represent the current frame's pixel number, then this contract function is for the first saliency function. If spnum1 is the current frame's pixel number and spnum2 represent the previous frame's pixel number, then this contract function is for second saliency function. If we use the second contract function which using the pixel of the same frame to get center distance to get a saliency map, then we apply this saliency function to each frame and use current frame's saliency map minus previous frame's saliency map to get a new image which is the new saliency result of the third saliency function. == Datasets == The saliency dataset usually contains human eye movements on some image sequences. It is valuable for new saliency algorithm creation or benchmarking the existing one. The most valuable dataset parameters are spatial resolution, size, and eye-tracking equipment. Here is part of the large datasets table from MIT/Tübingen Saliency Benchmark datasets, for example. To collect a saliency dataset, image or video sequences and eye-tracking equipment must be prepared, and observers must be invited. Observers must have normal or corrected to normal vision and must be at the same distance from the screen. At the beginning of each recording session, the eye-tracker recalibrates. To do this, the observer fixates their gaze on the screen center. The session is then started, and saliency data are collected by showing sequences and recording eye gazes. The eye-tracking device is a high-speed camera, capable of recording eye movements at least 250 fr

Wispr

Wispr AI is a software company founded in 2021 by Tanay Kothari and Sahaj Garg that develops voice-based interfaces for computers and other devices. The company’s main product, Wispr Flow, is an AI-powered speech-to-text application available on macOS, Windows and iOS. == History == Wispr was founded in 2021 with the goal of building a non-invasive wearable device that would allow users to control smartphones without touch input. The device was intended to translate neurological signals into actions and to enable silent text entry by mouthing words, drawing on techniques similar to brain–computer interfaces. Early funding was directed toward this hardware-focused effort. After around three years of development, Wispr concluded that contemporary AI systems were not sufficient for the requirements of the wearable device. The company shifted its focus to Flow voice dictation software, the software layer originally built for the wearable, and in 2024 released a macOS application based on this platform. == Wispr Flow == Wispr Flow (often referred to as Flow) is a speech-to-text application for macOS, Windows and iOS. It provides real-time dictation and transcription in more than 100 languages and can operate across applications, including email clients, messaging platforms and chatbots. In June 2025 Wispr released an iOS version that functions as a third-party keyboard, allowing voice input in any app. == Technology == Wispr Flow is based on automatic speech recognition (ASR) and other AI models. The system adapts to individual users over time, learning their vocabulary and preferred style with the aim of reducing manual editing. Flow operates through configurable “Flow Sessions”, defined as time windows during which the app has access to the microphone; users can set session timeouts or disable automatic time limits. == Users and Adoption == Wispr initially targeted users such as venture capitalists, entrepreneurs and executives who process large volumes of text and often work in private or flexible environments. The user base later expanded via platforms such as Product Hunt to students, software developers, writers, lawyers and consultants. Flow has also been adopted by users with conditions such as ADHD, dyslexia, paralysis and carpal tunnel syndrome. About 40% of users are in the United States, 30% in Europe and the remaining 30% in other regions. More than 30% of users come from non-technical backgrounds. Flow supports 104 languages, with approximately 40% of dictations in English and 60% in other languages, including Spanish, French, German, Dutch, Hindi and Mandarin. Wispr has reported monthly user growth above 50%, a six-month active-user retention rate of about 80%, a payment rate around 19%, and revenue of approximately US$3.8 million between July 2024 and July 2025. == Development == Wispr has announced plans for an Android application and maintains waiting lists for Android, Linux and web versions of Flow. The company is developing shared-context features for teams so that the software can recognize common terminology within organizations and has stated that it aims to evolve Flow into a broader AI assistant for tasks such as messaging, note-taking and reminders. Wispr has also reported working with unnamed AI hardware partners on interaction layers for future devices. == Funding == In 2025 Wispr raised US$30 million in a Series A funding round led by Menlo Ventures, with participation from NEA, 8VC and several individual investors, including Evan Sharp and Henry Ward. Earlier investors include Neo, MVP Ventures and AIX Ventures. In November of that same year, the company raised a US$25 million Series A extension led by Notable Capital, with participation from Flight Fund, bringing its total funding to US$81 million. Wispr competes with other AI-based dictation and voice-input tools, including Aqua, Talktastic, Superwhisper and Betterdication.

Eric Xing

Eric Poe Xing (Chinese: 邢波) is an American computer scientist who has been serving as president of Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) since January 2021. He is also a professor in the Carnegie Mellon University School of Computer Science where he founded the SAILING Lab in 2004, and is the co-founder of the AI companies Petuum and GenBio AI. Xing's research focuses on statistical machine learning, probabilistic graphical models, and systems for distributed machine learning. He was elected a Fellow of the Institute of Electrical and Electronics Engineers in 2019 for "contributions to machine learning algorithms and systems" and a Fellow of the Association for Computing Machinery in 2022 for "contributions to algorithms, architectures, and applications in machine learning." == Education == Xing earned a B.Sc. in physics from Tsinghua University in 1993, and an M.Sc. in computer science from Rutgers University in 1998. He earned a Ph.D. in molecular biology and biochemistry from Rutgers in 1999, supervised by molecular cancer researcher Chung S. Yang. His dissertation examined the inactivation of the Rb and p53 pathways in human esophageal squamous cell carcinoma. He earned a second Ph.D. in computer science from the University of California, Berkeley in 2004, supervised by Richard Karp, Michael I. Jordan, and Stuart J. Russell. His thesis applied probabilistic graphical models to motif identification and haplotype inference in genomic data. == Career == Xing joined Carnegie Mellon University (CMU) as a faculty member in 2004, where he created the Statistical Artificial Intelligence and Integrative Genomics (SAILING) Lab. He held visiting appointments from 2010 to 2011, serving as a visiting research professor at Facebook Inc. and as a visiting associate professor in the Department of Statistics at Stanford University. He served as co-Program Chair of the International Conference on Machine Learning (ICML) in 2014 and General Chair in 2019. Xing served as the founding director of CMU’s Center for Machine Learning and Health, established in 2015 as part of the Pittsburgh Health Data Alliance, a collaboration between CMU, the University of Pittsburgh, and the University of Pittsburgh Medical Center. In 2016, Xing co-founded Petuum Inc., a US-based startup. In 2017, Petuum raised $93 million in a round of venture funding from SoftBank. In 2018 Petuum was named a World Economic Forum Technology Pioneer. In 2019, Xing received the Carnegie Science Award for Startup Entrepreneurs in recognition of his leadership of Petuum. On 29 November 2020, Xing was appointed president of the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), with the appointment taking effect in January 2021. In 2024, Xing co-founded GenBio AI where he is chief scientist. The US-based startup, which he co-founded with David Baker, Ziv Bar-Joseph, Emma Lundberg, Le Song and Fred Hu, aims to create AI-driven digital organisms (AIDO) for the purposes of modeling medical treatments. Xing has overseen the launch of the MBZUAI Institute of Foundation Models (IFM), which focuses on research and development of large-scale foundation models. In 2025–2026, IFM released the open-source reasoning model K2 Think, which was covered internationally as part of the UAE’s push to develop domestically controlled (“sovereign”) AI capabilities. IFM presented PAN as a “world model” research project and demonstrated related systems publicly. MBZUAI also collaborated with G42 and Cerebras Systems on the Jais language model, an open-source Arabic–English large language model released in 2023, according to Reuters. == Awards and honors == Xing is a recipient of the National Science Foundation (NSF) Career Award and the Alfred P. Sloan Research Fellowship. Xing is an elected Fellow of the following institutes and associations: Association for the Advancement of Artificial Intelligence (AAAI) 2016 Institute of Electrical and Electronics Engineers (IEEE) 2019 for "contributions to machine learning algorithms and systems" American Statistical Association (ASA) 2022 Association for Computing Machinery (ACM) 2022 for "contributions to algorithms, architectures, and applications in machine learning" Institute of Mathematical Statistics (IMS) 2023 International Society for Computational Biology (ISCB) 2026 == Selected publications == Eric P. Xing; Michael I. Jordan; Stuart J. Russell; Andrew Y. Ng (2003). "Distance Metric Learning with Application to Clustering with Side-Information" (PDF). Advances in Neural Information Processing Systems 15. Advances in Neural Information Processing Systems. Wikidata Q77691192. Edoardo M. Airoldi; David M. Blei; Stephen E Fienberg; Eric P Xing (1 September 2008). "Mixed Membership Stochastic Blockmodels". Journal of Machine Learning Research. 9: 1981–2014. ISSN 1533-7928. PMC 3119541. PMID 21701698. Wikidata Q35058357. Eric P. Xing; Michael I. Jordan; Richard M. Karp (28 June 2001), Feature selection for high-dimensional genomic microarray data, vol. 18, pp. 601–608, Wikidata Q138678867 Xing EP; Karp RM (1 January 2001). "CLIFF: clustering of high-dimensional microarray data via iterative feature filtering using normalized cuts". Bioinformatics. 17 Suppl 1: S306-15. doi:10.1093/BIOINFORMATICS/17.SUPPL_1.S306. ISSN 1367-4803. PMID 11473022. Wikidata Q30657299.

Imitation learning

Imitation learning is a paradigm in reinforcement learning, where an agent learns to perform a task by supervised learning from expert demonstrations . It is also called learning from demonstration and apprenticeship learning. It has been applied to underactuated robotics, self-driving cars, quadcopter navigation, helicopter aerobatics, and locomotion. == Approaches == Expert demonstrations are recordings of an expert performing the desired task, often collected as state-action pairs ( o t ∗ , a t ∗ ) {\displaystyle (o_{t}^{},a_{t}^{})} . === Behavior Cloning === Behavior Cloning (BC) is the most basic form of imitation learning. Essentially, it uses supervised learning to train a policy π θ {\displaystyle \pi _{\theta }} such that, given an observation o t {\displaystyle o_{t}} , it would output an action distribution π θ ( ⋅ | o t ) {\displaystyle \pi _{\theta }(\cdot |o_{t})} that is approximately the same as the action distribution of the experts. BC is susceptible to distribution shift. Specifically, if the trained policy differs from the expert policy, it might find itself straying from expert trajectory into observations that would have never occurred in expert trajectories. This was already noted by ALVINN, where they trained a neural network to drive a van using human demonstrations. They noticed that because a human driver never strays far from the path, the network would never be trained on what action to take if it ever finds itself straying far from the path. === DAgger === DAgger (Dataset Aggregation) improves on behavior cloning by iteratively training on a dataset of expert demonstrations. In each iteration, the algorithm first collects data by rolling out the learned policy π θ {\displaystyle \pi _{\theta }} . Then, it queries the expert for the optimal action a t ∗ {\displaystyle a_{t}^{}} on each observation o t {\displaystyle o_{t}} encountered during the rollout. Finally, it aggregates the new data into the dataset D ← D ∪ { ( o 1 , a 1 ∗ ) , ( o 2 , a 2 ∗ ) , . . . , ( o T , a T ∗ ) } {\displaystyle D\leftarrow D\cup \{(o_{1},a_{1}^{}),(o_{2},a_{2}^{}),...,(o_{T},a_{T}^{})\}} and trains a new policy on the aggregated dataset. === Decision transformer === The Decision Transformer approach models reinforcement learning as a sequence modelling problem. Similar to Behavior Cloning, it trains a sequence model, such as a Transformer, that models rollout sequences ( R 1 , o 1 , a 1 ) , ( R 2 , o 2 , a 2 ) , … , ( R t , o t , a t ) , {\displaystyle (R_{1},o_{1},a_{1}),(R_{2},o_{2},a_{2}),\dots ,(R_{t},o_{t},a_{t}),} where R t = r t + r t + 1 + ⋯ + r T {\displaystyle R_{t}=r_{t}+r_{t+1}+\dots +r_{T}} is the sum of future reward in the rollout. During training time, the sequence model is trained to predict each action a t {\displaystyle a_{t}} , given the previous rollout as context: ( R 1 , o 1 , a 1 ) , ( R 2 , o 2 , a 2 ) , … , ( R t , o t ) {\displaystyle (R_{1},o_{1},a_{1}),(R_{2},o_{2},a_{2}),\dots ,(R_{t},o_{t})} During inference time, to use the sequence model as an effective controller, it is simply given a very high reward prediction R {\displaystyle R} , and it would generalize by predicting an action that would result in the high reward. This was shown to scale predictably to a Transformer with 1 billion parameters that is superhuman on 41 Atari games. === Other approaches === See for more examples. == Related approaches == Inverse Reinforcement Learning (IRL) learns a reward function that explains the expert's behavior and then uses reinforcement learning to find a policy that maximizes this reward. Recent works have also explored multi-agent extensions of IRL in networked systems. Generative Adversarial Imitation Learning (GAIL) uses generative adversarial networks (GANs) to match the distribution of agent behavior to the distribution of expert demonstrations. It extends a previous approach using game theory.

How to Choose an AI Video Editor

In search of the best AI video editor? An AI video editor is software that uses machine learning to help you get more done — it turns a rough idea into a polished result in seconds. When choosing one, weigh output quality, pricing, export formats, and how well it fits the tools you already use. Whether you are a beginner or a pro, the right AI video editor slots into your workflow and pays for itself fast. We tested the leading options and ranked them by quality, value, and ease of use.

Rejoyn

Rejoyn is a prescription-only digital therapeutic smartphone app approved by the US FDA for the treatment of major depressive disorder (MDD) in adults ages 22 and up. It is prescribed in conjunction with standard antidepressant medication and professional guidance and support. Rejoyn was developed by Click Therapeutics and Otsuka America Pharmaceutical Inc., and gained FDA clearance as a "medical device" on March 30th, 2024. The smartphone app helps patients with depression using exercises based on cognitive behavioral therapy (CBT) along with timed notifications to keep the patient engaged and in treatment. Randomized controlled trials showed that the Rejoyn app was more effective at relieving depression symptoms compared to a "sham app", a placebo app that required similar effort but was not intended to be helpful. Dr. John Torous, MD, MBI,[a] a psychiatrist at the Beth Israel Deaconess Medical Center in Boston, said that the app seems to pose minimal risks, and is an important step forward in unlocking the power of smartphones in treating psychiatric disorders. Some experts have signaled that the claims should be taken with caution, since the app was "tested only in a narrow subset of patients." and its benefits are "not statistically significant," according to the study’s primary outcome."

Joseph Keshet

Joseph (Yossi) Keshet (Hebrew: יוסף (יוסי) קשת; born: 28 February 1973) is an Israeli professor in the Electrical and Computer Engineering Faculty of the Technion, where he is the director of the Speech, Language, and Deep Learning Lab. His research focuses on human speech processing and machine learning. == Early life and education == Keshet was born in Tel-Aviv. He graduated from the Amal School and began his academic studies at the Department of Electrical Engineering-Systems at Tel-Aviv University in 1991 and received his B.Sc. (Cum Laude) in 1994. Keshet served in the IDF Unit 8200 from 1995 to 2002 as the head of the speech processing research section in the R&D Center. During his service, he received a national award from the Administration for the Development of Weapons and Technological Infrastructure (Maf’at). Keshet was award his M.Sc. from the same department after he completed his Israel Defense Force service in 2002. His Dissertation was titled: Stop consonant spotting in continuous speech and was supervised by Dan Chazan from IBM Research Labs, Haifa. He continued his Ph.D. studies at the Hebrew University of Jerusalem until 2008. Prof. Yoram Singer supervised his thesis on Large Margin Algorithms for Discriminative Continuous Speech. == Career == Keshet was a Research Associate (postdoc) at IDIAP Research Institute, Martigny, Switzerland in 2007, and joined the TTI-Chicago and Department of Computer Science, University of Chicago, Chicago, IL in 2009 as Research Assistant Professor. In 2013, he returned to Israel and joined the Computer Science department at Bar-Ilan University as a senior lecturer and head of the Speech, Language, and Deep Learning Lab. In 2020, Keshet became a Founding Venture Partner at the Disruptive AI Venture Capital. In the same year, he also joined Amazon in Tel-Aviv as an Amazon Scholar. In 2022, Keshet joined the Faculty of Electrical and Computer Engineering at the Technion. == Research == Keshet's research work focuses on both machine learning and computational study of human speech and language. His work on speech and language concentrates on speech processing, speech recognition, acoustic phonetics, and pathological speech. In machine learning, Keshet is focused on deep learning and structured tasks. According to Google Scholar (September 2020), Keshet is one of the 15 most cited researchers in the field of spoken language processing. The algorithms that were developed in the Speech, Language, and Deep Learning Lab can analyze different pathological conditions in the throat and vocal cords based on the subject's voice. Other algorithms showed that the voice can be used to estimate physical and emotional state of the speaker. Another research led by Keshet suggested that it is possible to fool structured AI systems (like Google Voice). == Membership in professional societies == Keshet is the founder and chair of the Machine Learning for Speech and Language Processing Special Interest Group (SIGML) of the International Speech Communication Association (ISCA), from 2011. He is a senior member of the IEEE Signal Processing Society since 2018 and a member of ISCA since 2002. == Publications == Prof. Keshet has authored more than 70 scientific publications and edited one book. === Book === Joseph Keshet and Samy Bengio, Eds., Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods, John Wiley & Sons, March 2009. === Selected articles === 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. 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. Yossi Adi, Carsten Baum, Moustapha Cisse, Benny Pinkas, Joseph Keshet, Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring, Usenix, 2018. 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. 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. 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. Joseph Keshet, Optimizing the Measure of Performance in Structured Prediction, in Advanced Structured Prediction, Sebastian Nowozin, Peter V. Gehler, Jeremy January, and Christoph H. Lampert, Eds., The MIT Press, 2014. 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. David McAllester, Tamir Hazan and Joseph Keshet, Direct Loss Minimization for Structured Prediction, The 24th Annual Conference on Neural Information Processing Systems (NIPS), 2010. Joseph Keshet, David Grangier and Samy Bengio, Discriminative Keyword Spotting, Speech Communication, Volume 51, Issue 4, pp. 317–329, April 2009. == Personal life == Keshet is married to Lital. They have three children.