Director of the Speech Communication Lab at University of Maryland

Engineering - Electrical
Status: yes
Patent: 9886967;10381025;9640200;8666734;6359988;6975984;7664642

About This Innovation

Espy-Wilson's research interests include: "the integration of engineering, linguistics and speech acoustics to study speech communication. She is developing an approach to speech recognition based on phonetic features, articulatory parameters and landmarks to better address variability in the speech signal. She also conducts research in the areas of speech production, speech enhancement, speaker recognition, single-channel speaker separation and language and genre detection in audio content analysis and forensics. A major focus of her research is to gain a better understanding of the relationship between articulation, acoustics and perception and to use this knowledge to develop effective speech technologies". She holds 6 patents

The Invention

Systems & methods for speech extraction; Multiple pitch extraction by strength calculation from extrema; Systems & methods for multiple pitch tracking using a multidimensional function & strength values; Process for introduce realistic pitch variation in artificial larynx speech; Electrolaryngeal speech enhancement for telephony;System & method for automatic speech recognition from phonetic features & acoustic landmark

Key Information

Category:
Engineering - Electrical

Completion Status:
yes

Patent Number:
9886967;10381025;9640200;8666734;6359988;6975984;7664642

Co-Inventor:
Srikantha Visnubhotla; Joel M. MacAuslan; Venkatesh Chari; Richard Goldhor; Amit Juneja

Patent Information

Patent Number: 9886967;10381025;9640200;8666734;6359988;6975984;7664642

Technical Specifications

Systems & methods for speech extraction; Multiple pitch extraction by strength calculation from extrema; Systems & methods for multiple pitch tracking using a multidimensional function & strength values; Process for introduce realistic pitch variation in artificial larynx speech; Electrolaryngeal speech enhancement for telephony;System & method for automatic speech recognition from phonetic features & acoustic landmark

Collaboration

Co-Inventor: Srikantha Visnubhotla; Joel M. MacAuslan; Venkatesh Chari; Richard Goldhor; Amit Juneja