Technical Manager, Speech Technology and Research Laboratory (STAR)
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
-
Resilient Data Augmentation Approaches to Multimodal Verification in the News Domain
Building on multimodal embedding techniques, we show that data augmentation via two distinct approaches improves results: entity linking and cross-domain local similarity scaling.
-
Wideband Spectral Monitoring Using Deep Learning
We present a system to perform spectral monitoring of a wide band of 666.5 MHz, located within a range of 6 GHz of Radio Frequency (RF) bandwidth, using state-of-the-art deep…
-
Robust Speaker Recognition from Distant Speech under Real Reverberant Environments Using Speaker Embeddings
This article focuses on speaker recognition using speech acquired using a single distant or far-field microphone in an indoors environment.
-
Speech recognition in unseen and noisy channel conditions
This work investigates robust features, feature-space maximum likelihood linear regression (fMLLR) transform, and deep convolutional nets to address the problem of unseen channel and noise conditions in speech recognition.
-
Minimizing Annotation Effort for Adaptation of Speech-Activity Detection Systems
This paper focuses on the problem of selecting the best-possible subset of available audio data given a budgeted time for annotation.
-
The SRI System for the NIST OpenSAD 2015 Speech Activity Detection Evaluation
In this paper, we present the SRI system submission to the NIST OpenSAD 2015 speech activity detection (SAD) evaluation. We present results on three different development databases that we created…