This article was accepted into the corpus but its outbound wikilinks were never NER-processed — typical at the deepest BFS hop or when the run's entity cap was reached. No expansion funnel to show.
| Center for Language and Speech Processing (Johns Hopkins University) | |
|---|---|
| Name | Center for Language and Speech Processing |
| Established | 1986 |
| Type | Research center |
| Parent | Johns Hopkins University |
| Location | Homewood Campus, Baltimore, Maryland |
| Director | H. Paul Haus |
| Fields | Natural language processing, speech recognition, machine learning |
Center for Language and Speech Processing (Johns Hopkins University) is an interdisciplinary research center at Johns Hopkins University focused on computational linguistics, automatic speech recognition, and machine learning applications to language. Founded to bring together scholars from Department of Computer Science, Department of Electrical and Computer Engineering, and Department of Cognitive Science at Johns Hopkins University, the center has been influential in advancing methods used by industry and academia worldwide. Its members have collaborated with institutions such as Massachusetts Institute of Technology, Stanford University, and Carnegie Mellon University on projects spanning multilingual processing, information retrieval, and human–computer interaction.
The center was founded in the late 20th century at Johns Hopkins University as part of an effort to unify research in computational approaches developed across Hopkins departments and research units. Early collaborations included partnerships with Bell Labs, MITRE Corporation, and the Defense Advanced Research Projects Agency on speech corpora and statistical methods. Throughout the 1990s and 2000s the center worked with teams from IBM Research, Microsoft Research, Google Research, and AT&T Bell Labs to transition academic results into deployed systems. Significant historical milestones involved contributions to shared tasks organized by National Institute of Standards and Technology, European Language Resources Association, and international conferences such as Association for Computational Linguistics, International Conference on Machine Learning, and NeurIPS.
The center's research spans core topics in language and speech processing, including automatic speech recognition influenced by work from Jelinek, Bahl, and Brownian motion-informed models; statistical machine translation reflecting paradigms advanced by IBM Models and later neural architectures popularized by Google Brain and OpenAI; and information retrieval strategies related to developments at Stanford University and University of Massachusetts Amherst. Other active areas include spoken language understanding connected to initiatives at DARPA, dialog systems with ties to research at SRI International, and low-resource language technology inspired by fieldwork linked to Summer Institute of Linguistics. The center also pursues research in multimodal processing that draws on methodologies used at MIT Media Lab and UC Berkeley.
Facilities include clustered compute resources comparable to systems used by Amazon Web Services research programs and GPU arrays similar to those at NVIDIA Research, enabling experiments in deep learning architectures pioneered at Google DeepMind and Facebook AI Research. The center maintains annotated corpora and speech datasets analogous to collections at Linguistic Data Consortium, repositories used by Europarl, and benchmarks aligned with evaluations by NIST. Laboratory spaces are situated near the Homewood Campus libraries and computing centers linked academically to Peabody Institute collaborations and regional partnerships with Johns Hopkins Applied Physics Laboratory.
Graduate and undergraduate instruction at the center supplements curricula in Whiting School of Engineering and offers courses modeled after syllabi from Massachusetts Institute of Technology and Carnegie Mellon University. Training includes seminars featuring visitors from Google Research, Microsoft Research, Apple Machine Learning Research, and funding-supported internships with agencies like DARPA and foundations such as the National Science Foundation. Students engage in thesis supervision by faculty with affiliations to professional societies including Association for Computational Linguistics, IEEE, and ACM SIGIR.
The center maintains long-standing collaborations with corporate and government partners including Google, Microsoft, Amazon, IBM, Apple, DARPA, and National Institutes of Health. Academic partnerships extend to University of Cambridge, University of Oxford, ETH Zurich, University of Toronto, and Princeton University. Joint projects have been funded by organizations such as the National Science Foundation, Defense Advanced Research Projects Agency, and private foundations like the Gordon and Betty Moore Foundation and Simons Foundation.
The center contributed to seminal evaluations and toolkits used across the field, paralleling efforts like the Brown Corpus and software traditions akin to Kaldi and frameworks influenced by TensorFlow and PyTorch. Contributions include advances in acoustic modeling that resonated with research at IBM Research and algorithmic improvements in machine translation that intersected with work from University of Edinburgh and Johns Hopkins Statistical Machine Translation group. The center's members have published at venues such as ACL, EMNLP, ICASSP, and Interspeech and have influenced deployments in speech-enabled products by Nuance Communications and assistive technologies used by National Institutes of Health clinical trials.
Faculty associated with the center have included scholars with links to Johns Hopkins University departments, visiting researchers from MIT, Stanford University, Carnegie Mellon University, and long-term collaborators from SRI International and Bell Labs. Key personnel have held leadership roles in professional organizations like Association for Computational Linguistics and IEEE Signal Processing Society, and have served on program committees for conferences such as NeurIPS and ICML.
Category:Johns Hopkins University Category:Computational linguistics research institutions