| 2025 | ISM | From 2D to 3D: How Discrete Dependencies Enable Cross-Dimensional Inference in Neural Networks in Defiance of Euclidean Geometry. | Gerald Friedland, Robert Mertens |
| 2024 | ICASSP | Enhancing GAN-based Vocoders with Contrastive Learning Under Data-Limited Condition. | Haoming Guo, Seth Z. Zhao, Jiachen Lian, Gopala Anumanchipalli, Gerald Friedland |
| 2023 | ISM | Deep Layers Beware: Unraveling the Surprising Benefits of JPEG Compression for Image Classification Pre-processing. | Guruprasad Nayak, Gerald Friedland |
| 2020 | MMM | DIME: An Online Tool for the Visual Comparison of Cross-modal Retrieval Models. | Tony Zhao, Jaeyoung Choi, Gerald Friedland |
| 2018 | MMM | Rethinking Summarization and Storytelling for Modern Social Multimedia. | Stevan Rudinac, Tat-Seng Chua, Nicols E. Daz Ferreyra, Gerald Friedland, Tatjana Gornostaja, Benoit Huet, Rianne Kaptein, Krister Lindn, Marie-Francine Moens, Jaakko Peltonen, Miriam Redi, Markus Schedl, David A. Shamma, Alan F. Smeaton, Lexing Xie |
| 2016 | SIGCSE | The Teaching Privacy Curriculum. | Serge Egelman, Julia Bernd, Gerald Friedland, Dan Garcia |
| 2015 | ICASSP | An information-theoretic metric of fingerprint effectiveness. | T. J. Tsai, Gerald Friedland, Xavier Anguera |
| 2015 | SIGCSE | Teaching Privacy: What Every Student Needs to Know (Abstract Only). | Gerald Friedland, Serge Egelman, Daniel D. Garcia |
| 2014 | Interspeech | Audio-concept features and hidden Markov models for multimedia event detection. | Benjamin Elizalde, Mirco Ravanelli, Karl Ni, Damian Borth, Gerald Friedland |
| 2013 | ICASSP | Nowhere to hide: Exploring user-verification across Flickr accounts. | Howard Lei, Jaeyoung Choi, Gerald Friedland |
| 2013 | Interspeech | Audio Concept Ranking for Video Event Detection on User-Generated Content. | Benjamin Elizalde, Mirco Ravanelli, Gerald Friedland |
| 2013 | Interspeech | Exploring methods of improving speaker accuracy for speaker diarization. | Mary Tai Knox, Nikki Mirghafori, Gerald Friedland |
| 2013 | ISM | An i-Vector Representation of Acoustic Environments for Audio-Based Video Event Detection on User Generated Content. | Benjamin Elizalde, Howard Lei, Gerald Friedland |
| 2013 | WWW | Exploiting innocuous activity for correlating users across sites. | Oana Goga, Howard Lei, Sree Hari Krishnan Parthasarathi, Gerald Friedland, Robin Sommer, Renata Teixeira |
| 2012 | ICASSP | How to put it into words - using random forests to extract symbol level descriptions from audio content for concept detection. | Po-Sen Huang, Robert Mertens, Ajay Divakaran, Gerald Friedland, Mark Hasegawa-Johnson |
| 2012 | ICASSP | Multimodal city-verification on flickr videos using acoustic and textual features. | Howard Lei, Jaeyoung Choi, Gerald Friedland |
| 2012 | Interspeech | Where did I go wrong?: Identifying troublesome segments for speaker diarization systems. | Mary Tai Knox, Nikki Mirghafori, Gerald Friedland |
| 2011 | ASRU | Fast speaker diarization using a high-level scripting language. | Ekaterina Gonina, Gerald Friedland, Henry Cook, Kurt Keutzer |
| 2011 | ICASSP | User verification: Matching the uploaders of videos across accounts. | Howard Lei, Jaeyoung Choi, Adam Janin, Gerald Friedland |
| 2011 | Interspeech | Improved Overlapped Speech Handling for Speaker Diarization. | Kofi Boakye, Oriol Vinyals, Gerald Friedland |
| 2011 | ISM | On the Applicability of Speaker Diarization to Audio Concept Detection for Multimedia Retrieval. | Robert Mertens, Po-Sen Huang, Luke R. Gottlieb, Gerald Friedland, Ajay Divakaran |
| 2011 | NSPW | Sherlock holmes' evil twin: on the impact of global inference for online privacy. | Gerald Friedland, Gregor Maier, Robin Sommer, Nicholas Weaver |
| 2010 | ICASSP | An adaptive initialization method for speaker Diarization based on prosodic features. | David Imseng, Gerald Friedland |
| 2010 | ICASSP | Leveraging speaker diarization for meeting recognition from distant microphones. | Andreas Stolcke, Gerald Friedland, David Imseng |
| 2010 | Interspeech | System output combination for improved speaker diarization. | Simon Bozonnet, Nicholas W. D. Evans, Xavier Anguera, Oriol Vinyals, Gerald Friedland, Corinne Fredouille |
| 2010 | Interspeech | Multimodal speaker diarization using oriented optical flow histograms. | Mary Tai Knox, Gerald Friedland |
| 2010 | Interspeech | A hybrid approach to online speaker diarization. | Carlos Vaquero, Oriol Vinyals, Gerald Friedland |
| 2010 | Interspeech | Discriminative training for hierarchical clustering in speaker diarization. | Oriol Vinyals, Gerald Friedland, Nelson Morgan |
| 2010 | ISM | Parallelizing Speaker-Attributed Speech Recognition for Meeting Browsing. | Gerald Friedland, Jike Chong, Adam Janin |
| 2009 | ASRU | Robust Speaker Diarization for short speech recordings. | David Imseng, Gerald Friedland |
| 2009 | ICASSP | Multi-modal speaker diarization of real-world meetings using compressed-domain video features. | Gerald Friedland, Hayley Hung, Chuohao Yeo |
| 2009 | ICASSP | Fusing short term and long term features for improved speaker diarization. | Gerald Friedland, Oriol Vinyals, Yan Huang, Christian A. Mller |
| 2009 | ISM | Using Artistic Markers and Speaker Identification for Narrative-Theme Navigation of Seinfeld Episodes. | Gerald Friedland, Luke R. Gottlieb, Adam Janin |
| 2009 | IUI | Multimodal interfaces for automotive applications (MIAA). | Christian A. Mller, Gerald Friedland |
| 2008 | ICASSP | Overlapped speech detection for improved speaker diarization in multiparty meetings. | Kofi Boakye, B. Trueba-Hornero, Oriol Vinyals, Gerald Friedland |
| 2008 | ICASSP | Estimating the dominant person in multi-party conversations using speaker diarization strategies. | Hayley Hung, Yan Huang, Gerald Friedland, Daniel Gatica-Perez |
| 2008 | Interspeech | Two's a crowd: improving speaker diarization by automatically identifying and excluding overlapped speech. | Kofi Boakye, Oriol Vinyals, Gerald Friedland |
| 2008 | Interspeech | Modulation spectrogram features for improved speaker diarization. | Oriol Vinyals, Gerald Friedland |
| 2008 | ISM | A Hardware-Independent Fast Logarithm Approximation with Adjustable Accuracy. | Oriol Vinyals, Gerald Friedland |
| 2007 | ASRU | A fast-match approach for robust, faster than real-time speaker diarization. | Yan Huang, Oriol Vinyals, Gerald Friedland, Christian A. Mller, Nikki Mirghafori, Chuck Wooters |
| 2006 | ISM | A Practical Approach to Boundary Accurate Multi-Object Extraction from Still Images and Videos. | Gerald Friedland, Kristian Jantz, Tobias Lenz, Fabian Wiesel, Ral Rojas |
| 2006 | ISM | Human-Centered Webcasting of Interactive-Whiteboard Lectures. | Gerald Friedland, Ral Rojas |
| 2005 | ISM | SIOX: Simple Interactive Object Extraction in Still Images. | Gerald Friedland, Kristian Jantz, Ral Rojas |
| 2005 | KES | The Virtual Technician: An Automatic Software Enhancer for Audio Recording in Lecture Halls. | Gerald Friedland, Kristian Jantz, Lars Knipping, Ral Rojas |
| 2003 | KES | Web Based Education as a Result of AI Supported Classroom Teaching. | Gerald Friedland, Lars Knipping, Ral Rojas, Ernesto Tapia |