Below are links to recordings of seminars hosted by the Center for Language and Speech Processing at Johns Hopkins University. We endeavor to record most of our events for the benefit of those unable to attend, as well as those who wish to review the information presented. Recordings not listed here are available for internal CLSP viewing on request.

For recordings of the most recent seminars, visit CLSP’s YouTube channel. 

• 2021 Speakers

  • Carolina Parada (Google AI) “State of Robotics at Google”
  • Wilker Aziz (University of Amsterdam) “The Inadequacy of the Mode in Neural Machine Translation“
  • Jiri Mekyska (Brno University of Technology) “Data Science in Small Medical Data Sets: From Logistic Regression Towards Logistic Regression“
  • Shannon Heald (University of Chicago) “Speech Recognition in the Context of Variability: Lessons from Human Listeners“
  • Alicia Lozano-Díez (Universidad Autonoma de Madrid) “Text-Dependent Speaker Verification: BUT system for the SdSV Challenge 2020“
  • Tuo Zhao (Georgia Tech) “Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach”
  • David Bamman (University of California, Berkeley) “Modeling the Spread of Information within Novels“
  • Eunsol Choi (University of Texas at Austin) “Learning to Understand Language in Context”

• 2020 Speakers

  • Kira Radinsky (Diagnostic Robotics / Technion) “Learning to Predict the Future”
  • Boqing Gong (Google) “Towards Visual Recognition in the Wild: Long Tailed Sources and Open Compound Targets”
  • Dirk Hovy (Bocconi University) “Five Sources of Biases and Ethical Issues in NLP and What to Do about Them“
  • Iryna Gurevych (Technische Universitat Darmstadt) “Let’s Argue: Understanding and Generating Natural Language Arguments”
  • Mirella Lapata (University of Edinburgh) “What’s This Movie About? Automatic Content Analysis and Summarization”
  • Tuomas Virtanen (Tampere University) “Computational Analysis of Sound Scenes“
  • Preslav Nakov (Qatar Computing Research Institute) “Detecting Fake News“
  • Judy Hoffman (Georgia Tech) “Understanding and Mitigating Model and Dataset Bias”
  • Zhizheng Wu (Facebook) “Audio Deep Fake Detection“
  • Annie Louis (Google) “Understanding Indirect Answers to Polar Questions”
  • Piotr Szymanski (Wroclaw University of Science and Technology) “Bayesian Approaches to Model Comparison in ML/NLP and Quantifying the ASR-NLP Gap”
  • Herman Kamper (Stellenbosch University) “Learning acoustic units and words from unlabelled speech (with a bit of vision)“
  • Frank Hutter (University of Freiburg) “Neural Architecture Search Coming of Age“
  • Violet Peng (UCLA) “From Language Understanding to Creative Generation“
  • Chris Re (Stanford University) “Guidable Self Supervision for Named Entity Disambiguation“
  • Abdelrahman Mohamed (Facebook) “Better Use of Un-paired Data and Pre-trained Modules for Speech Recognition”
  • Matt Gardner (Allen Institute for Artificial Intelligence) “NLP Evaluations that We Believe In“
  • Mei-Yuh Hwang (Mobvoi AI Lab) “Codemix Speech Recognition at Mobvoi: Current and Future”
  • Zachary Lipton (Carnegie Mellon University) “Deep (Inter-)Active Learning: Cure-all or Catastrophe?“
  • Bhuvana Ramabhadran (Google) “Transliteration Based Approaches for Multilingual, Code-Switched Languages“
  • Vivian Chen (National Taiwan University) “Scalable and Robust Conversational System“
  • Rada Mihalcea (University of Michigan) “Words and People”

• 2019 Speakers

  • Noah Smith (University of Washington) “Rational Recurrences for Empirical Natural Language Processing“
  • Marcello Federico (Amazon AI) “Five Short Pieces on Neural Machine Translation of Text and Speech“
  • Allyson Ettinger (University of Chicago) “NLP Representations from a Perspective of Human Cognition“
  • David Mimno (Cornell University) “Data Science and Data Scholarship”
  • Ming Sun (Amazon) “Acoustic Event Detection at Amazon Alexa”
  • Rick Rose (Google) “Multimodal audio-visual speech processing at Google”
  • Paris Smaragdis (University of Illinois) “New Twists for New Tricks, Making Audio Deep Learning Practical”
  • Gopala Anumanchipalli (University of California, San Francisco) “Decoding Speech and Language Representations from the Brain”
  • Jerry Zhu (University of Wisconsin-Madison), “Adversarial Machine Learning: Beyond Manipulating Pixels and Words“
  • Niranjan Balasubramanian (Stony Brook University), “Multi-hop QA, Modeling Events, and a Bit of Translation: Forays into Reuse, Decomposition and Control in Neural Models“
  • Dan Ellis (Google), “Recognizing Sound Events“
  • Mohammad Sadegh Rasooli (Facebook), “Cross-Lingual Transfer of Natural Language Processing Systems”
  • Ferhan Ture (Comcast Applied AI Research Group) “A Family of Neural Models for Voice Query Understanding on an Entertainment Platform“
  • Hyejin Youn (Northwestern University) “Lost and Found in Translation: On Universal Structure of Human Lexical Semantics”

  • Kenneth Heafield (University of Edinburgh) “Faster Neural Machine Translation”

  • Le Song (Georgia Institute of Technology) “Can Graph Neural Networks Help Logic Inference?”
  • DeLiang Wang (Ohio State University) “Towards Solving the Cocktail Party Problem”
  • Alex Cristia (CNRS) “Diarization in the Wild: Challenges and Opportunities”

  • Nazli Goharian (Georgetown University)”Social Media and Mental Health”

  • Heng Ji (RPI) Universal Information Extraction

  • Lea Frermann (University of Melbourne) “Learning Representations of Long Narratives for Summarization and Inference”
  • Nobuaki Minematsu (University of Tokyo) “How Can Speech Technologies Support Learners to Improve Their Skills of Speaking, Listening, Conversation and More?”
  • Jessica Ouyang (Columbia University) “Adapting Automatic Summarization to New Sources of Information”
  • Rediet Abebe (Cornell University) “Using Search Queries to Understand Health Information Needs in Africa”

  • Kenton Murray (University of Notre Dame) “Learning Neural Network Hyperparameters for Machine Translation”

  • Thomas Schatz (UMD) “Quantitative Models of Adult Phonetic Category Perception and Infant Phonetic Learning”

  • Brendan O’Connor (UMass Amherst) “Demographic Bias in Social Media Language Analysis: A Case Study of African-American English”

• 2018 Speakers

  • James Foulds (UMBC) “Differential Fairness for Machine Learning and Artificial Intelligence Systems: Unbiased Decisions with Biased Data”

  • David Harrison (Swarthmore College and National Geographic Society) “Endangered Languages”

  • Chin-Hui Lee (Georgia Tech) “A Regression Approach to Spectral Mapping for Speech Enhancement”

  • Carolyn Rose (CMU) “Who is the Bridge Between the What and the How”

  • Tamara Broderick (MIT) “Automated Scalable Bayesian Inference via Data Summarization”

  • Jennifer Chu-Carroll (Elemental Cognition)”Dialoguing to a Better Understanding”

  • Jon Barker (University of Sheffield) “Distant Microphone Conversational Speech Recognition in Domestic Environments: Some Initital Outcomes of the 5th CHiME Challenge”

  • Gautham Mysore (Adobe Research) “Simplifying the Creation of Voice-based Content”

  • Panos Georgiou (USC) “Speech Processing & Machine Learning for Behavior Analysis”

  • William Cohen (Google AI) “Logic and Reasoning in the Age of Deep Learning”

  • Omri Abend (Hebrew University) “UCCA: A Computational Approach to Cross-Linguistic Semantic Representation”

  • Yulia Tsvetkov(CMU): Towards Flexible but Controllable Language Generation

  • Kyunghyun Cho (New York University): Three recent directions in neural machine translation

  • Brian Roark (Google AI): Romanization, non-standard orthography and text entry

  • René Vidal (Johns Hopkins University): Mathematics of Deep Learning

  • Debra Mathews (Johns Hopkins University): Ethics of AI in Healthcare and Beyond

  • Mari Ostendorf (University of Washington) “Multi-Factor Context-Aware Language Modeling”

  • Been Kim (Google) “Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

  • James Pustejovsky (Brandeis University) “Modeling Common Ground for Multimodal Communication”

  • Mike Hopcroft (Microsoft) “How Bing Uses Bloom Filters for Search”

  • Richard Sproat (Google Research) “Neural Models of Text Normalization for Speech Applications”

  • Kate Saenko (Boston University) “Connecting Vision and Language End-to-End”

  • Amir Zeldes (Georgetown University) “Feature Rich Models for Discourse Signaling”

  • Joao Graca (University of Lisbon) “Unbabel: How to Combine AI with the Crowd to Scale Professional-Quality Translation”

  • David Smith (Northeastern University) “Modeling Text Dependencies: Information Cascades, Translations and Multi-Input Attention”

  • Tara Sainath (Google Research) “End-to-End Modeling for Speech Recognition”

  • Ken Grant (Walter Reed National Military Medical Center) “Speech Perception with Minimal Acoustics Cues Informs Novel Approaches to Automatic Speech Recognition”

• 2017 Speakers

  • Andrew Gordon (USC) “Automated Behavior Interpretation Using Etcetera Abduction”

  • Luke Zettlemoyer (University of Washington) “End-to-End Deep Learning for Broad Coverage Semantics: SRL, Conference and Beyond”

  • Jinyu Li (Microsoft) “Deep Learning Acoustic Model in Microsoft Cortana Voice Assistant”

  • Jeffrey Siskind (Purdue University) “Decoding the Brain to Help Build Machines”

  • Kate Knill (University of Cambridge) “Are All Languages Created Equal for Speech Recognition?”

  • Katharina Kann (LMU Munich) “Low-resource Morphological Generation with Neural Sequence-to-Sequence Models”

  • Sharon Gannot (Bar-Ilan University, Israel) “Speech Enhancement Using a Deep Mixture of Experts”

  • Amanda Stent (Bloomberg) “Text Analytics in Finance: A Case Study and Some Considerations”

  • Laura Dietz (University of New Hampshire) “Retrieving Complex Answers through Knowledge Graph and Text”

  • Malcolm Slaney (Google) “Auditory Attention: From Saliency to Models to Applications”

  • Michael Auli (Facebook) “Sequence to Sequence Learning: Fast Training and Inference with Gated Convolutions”

  • Satinder Singh (University of Michigan) “Deep Reinforcement Learning for Sequential Decision Making Tasks with Natural Language Interaction”

  • Lambert Mathias (Amazon) “Natural Language Understanding with Heterogenous Schema”

  • Tal Linzen (JHU) “Structure-Sensitive Dependency Learning in Recurrent Neural Networks”

  • Soumith Chintala (Facebook, New York) “An Overview of Deep Learning Frameworks and an Introduction to PyTorch”

  • Xuedong Huang (Microsoft) “Cognitive Toolkit and Language Processing”

  • Nathan Schneider (Georgetown University) – “The Ins and Outs of Preposition Semantics: Challenges of Coverage and Cross-Linguistic Adequacy”
  • Mohit Bansal (UNC Chapel Hill) – “Multi-Task and Reinforcement Learning for Entailment-Based Natural Language Generation”
  • Sanjeev Satheesh (Baidu, Inc.) – “Bias Reduction in Production Speech Systems”
  • Suzanne Stevenson (University of Toronto) – “How Languages Carve Up the World: Modeling Developmental and Linguistic Relativity Effects”
  • Kevin Jamieson (UC Berkeley) – “Bayesian Optimization and Other Potentially Bad Ideas for Hyperparameter Optimization”
  • Ciprian Chelba (Google Research) – “Sparse Non-negative Matrix Language Modeling”
  • Jianfeng Gao (Microsoft) – “Neural Approaches to Machine Reading Comprehension and Dialogue”
  • Jordan Boyd-Graber (University of Colorado) – “Thinking on your Feet: Reinforcement Learning for Incremental Language Tasks”
  • Dilek Hakkani-Tur (Google Research) – “Deep Learning for Goal Oriented Conversational Understanding”
  • Sharon Gannot (Bar-Ilan University, Israel) – “A Hybrid Approach for Speech Enhancement Using MoG Model and Neural Network Phoneme Classifier”
  • Claire Bonial (U.S. Army Research Laboratory) – “Sensible Semantic Distinctions for NLP Annotation Resources”
  • Haitao Mi (Ant Financial) – “Advances in Neural Machine Translation”
  • Nathan Schneider (Georgetown University) – “The Ins and Outs of Preposition Semantics: Challenges of Coverage and Cross-Linguistic Adequacy”
  • Margaret Mitchell (Google Research) – “Algorithmic Bias in Artificial Intelligence: The Seen and Unseen Factors Influencing Machine Perception of Images and Language”
  • Charles Yang (University of Pennsylvania) – “Generalizations and Exceptions”
  • Shinji Watanabe (MERL) – “Distant-Talk Speech Processing Toward Natural Conversation Understanding”

• 2016 Speakers

  • Nima Mesgarani (Columbia University) – “Reverse Engineering the Neural Mechanisms Involved in Robust Speech Processing”
  • Jonathan May (Information Sciences Institute – USC) – “How I Learned to Stop Worrying and Love Evaluations (and Keep Worrying)”
  • Rebecca Steorts (Duke University) – “Flexible Models for Microclustering with Application to Entity Resolution”
  • Vikramjit Mitra (SRI International) – “Toward Robust Speech Processing Systems: Speech Perception, Gestural Phonology and Machine Learning”
  • Louis-Philippe Morency (Carnegie Mellon University) – “Modeling Human Communication Dynamics”
  • Lu Wang (Northeastern University) “Understanding Opinions and Arguments in Text”
  • Florian Metze (Carnegie Mellon University) – “Visual Features for Context-Aware Speech Recognition”
  • Hendrik Kayser (University of Oldenburg) – “Probabilistic Spatial Filter Estimation for Multi-Channel Signal Enhancement in Hearing Aids and Automatic Speech Recognition”
  • Yejin Choi (University of Washington) – “Procedural Language and Knowledge”
  • Mona Diab (George Washington University) – “Processing Arabic Social Media: Challenges and Opportunities”
  • Nancy Chen (Institute of Infocomm Research) – “Low-Resource Spoken Keyword Search”
  • Christo Kirov (Johns Hopkins University) – “Rich Morphological Modeling for Multi-lingual HLT Applications”
  • Pedro Moreno (Google Research) – “Contextual Speech Recognition in Google Voice Search”
  • Colin Cherry (National Research Council Canada) – “Sampling to Efficiently Train Bilingual Neural Network Language Models”
  • David Peterson (The Art of Language Invention) – “Conlanging”
  • Alexander “Sasha” Rush (Harvard) – “Deep Learning and Linguistic Structure”
  • Bowen Zhou (IBM, T.J. Watson Research Center) – “Recent Advances of Deep Learning for Question Answering”
  • Diane Litman (University of Pittsburgh) – “Argument Mining from Text for Teaching and Assessing Writing”
  • John Hershey (MERL) – “Speech Separation by Deep Clustering: Towards Intelligent Audio Analysis and Understanding”
  • KyungHyun Cho (New York University) – “Future (?) of Machine Translation”
  • Richard Socher (MetaMind) – “Multimodal Question Answering for Language and Vision”
  • Alona Fyshe (University of Victoria) – “Corpora, Cognition and Composition”
  • Niko Brummer (AGNITIO) – “Binary and Multiclass Calibration in Speaker and Language Recognition”
  • Sameer Singh (University of Washington) – “Interactive Training of Relation Embeddings Using High-Level Supervision

• 2015 Speakers

  • Yoav Artzi (Cornell Tech) – Broad-Coverage CCG Semantic Parsing with AMR
  • Dean Foster (Amazon.com) – Linear Methods for Linguistics
  • Leonardo Badino (Italian Institute of Technology) – Speech Production Features for Deep Neural Network Acoustic Modeling
  • Ryan Adams (Harvard) – Better Science Through Better Bayesian Computation
  • Emma Brunskill (Carnegie Mellon University) – Challenges in Interactive Machine Learning for Social Benefit
  • Anima Anandkumar (UC Irvine) – Beating the Perils of Non-convexity: Guaranteed Training of Neural Networks Using Tensor Methods
  • Graham Neubig (Nara Institute of Science and Technology) — Simultaneous Speech Translation
  • Tomas Mikolov (Facebook) – Deep Learning in NLP and Beyond
  • Guido Zarrella (MITRE Corporation) – Neuromorphic Language Understanding
  • Yan Liu (University of Southern California) – Learning and Mining in Large-Scale Time Series Data
  • Timothy J. Hazen (Microsoft) – Detecting Events, Trends and Anomalies in Document Collections
  • Hoifung Poon (Microsoft Research) – Machine Reading for Cancer Panomics
  • Najim Dehak (MIT – CSAIL) – I-Vector Representation Based on GMM and DNN for Audio Classification
  • Dirk Hovy (University of Copenhagen) – Texts Come from People – how Demographic Factors Influence NLP
  • Regina Barzilay (MIT Computer Science & Artificial Intelligence Lab) – Semantics of Language Grounding
  • Kevin Gimpel (Toyota Technological Institute at Chicago) – Neural Paraphrase Models
  • Will Lewis (Microsoft Research) – Speech Translation for Everyone – Breaking Down the Language Barriers
  • Abeer Alwan (UCLA) – The Role of Subglottal Resonances in Machine-Based Speech Processing Applications
  • Yariv Ephraim (George Mason University) – Recursive Estimation of Multivariate Markov Processes
  • Paul Cohen (Information Innovation Office, DARPA and the University of Arizona) – Acquiring Big Mechanisms by Reading Primary Literature
  • Aron Culotta (Illinois Institute of Technology) – Towards Web-Scale Observational Studies of Health
  • Wei Xu (University of Pennsylvania) – Modeling Lexically Divergent Paraphrases in Twitter and Beyond
  • Seza Dogruoz (Tilburg University) – Embracing Multilingualism in Face to Face and Online Social Interactions
  • Salim Roukos (IBM T.J Watson Research Center) – Cognitive Computing – An NLP Renaissance!

ARCHIVE

• CLSP 2014 Fall Seminar Series
• Vimeo Archive (through 2014, plus ws16 Opening Day presentations)