Martin Graciarena
Technical Manager, Speech Technology and Research Laboratory
Martin Graciarena, Ph.D., is a senior research engineer in SRI International’s Speech Technology and Research (STAR) Laboratory. His research interests include noise robust features; voice activity detection; speaker, language, and speech recognition; non-audible microphone signal processing; and bird song processing.
At SRI, he is currently the co-principal investigator and speech activity detection task leader in the Defense Advanced Research Projects Agency (DARPA) Robust Automatic Transcription of Speech (RATS) program, and a team member of the Acoustic Background Characterization program led by Sandia National Laboratories. He has worked on projects such as DARPA’s Effective, Affordable Reusable Speech-to-text (EARS) program and Global Autonomous Language Exploitation (GALE) program, and the Intelligence Advanced Research Projects Activity’s (
Prior to joining SRI, Graciarena was a researcher at the Biomedical Engineering Institute in the School of Engineering, University of Buenos Aires, Argentina.
He has more than 30 publications in peer-reviewed conferences and holds two patents. His Ph.D. in noise robust speech processing is from the University of Buenos Aires, Argentina.
Recent publications
Robust Speaker Recognition from Distant Speech under Real Reverberant Environments Using Speaker Embeddings
Mahesh Nandwana, Julien van Hout, Mitchell McLaren, Allen Stauffer, Colleen Richey, Aaron Lawson, Martin Graciarena
Conference Proceeding September 2018
Speech recognition in unseen and noisy channel conditions
Horacio Franco, Julien van Hout, Martin Graciarena, Dimitra Vergyri
Conference Proceeding March 2017
Minimizing Annotation Effort for Adaptation of Speech-Activity Detection Systems
Martin Graciarena
Conference Paper September 2016
