About Jordan Cohen
Jordan R. Cohen
209A North 4th Avenue, Kure Beach, North Carolina 28449
Practical Applications of Technology
As independent SPELAMODE consultant
- Co-founder of Semantic Machines, exploring machine learning in the space of intelligent assistants (November, 2014 – June 2018: sold to Microsoft)
Named an expert witness in 8 cases
Created a research organization at Cisco and a support group for Audience
Solved speech recognition signal processing issues for Audience and Telenav.
Testified as expert witness for Vlingo (Nuance vs Vlingo, Boston, 2011),
Retained for Intellectual Property search and analysis by several firms
Served as CTO of Kextil and as Chief Scientist of Speech Morphing
As Principal Investigator for GALE at SRI
Applied speech and language technology to military applications ($12M annual budget with 14 sub-contractors).
Advised the SRI Commercialization Board speech technology applications to mobile devices.
As CTO of Voice Signal
Developed and managed intellectual property program, including patent production, pursuit, litigation, and strategy, which created more than 40 patents in 3 years.
Co-authored 13 granted patents, several more pending.
As a staff member at the Institute for Defense Analyses
Designed, funded, and co-chaired two summer workshops in the application of speech recognition techniques to realistic environments at CAIP/Rutgers in Summers, 1993 and 1994. (DARPA funded, 30 researchers for 6 weeks). Program continues annually at Johns Hopkins.
Developed Vocal Tract Length Normalization, now used in all major speech systems.
- While a staff member at IBM
- Developed the first successful auditory front end for a large scale speech recognition system.
Speech, Signals, and Algorithm Development in Department of Defense and related industries
- 24 years experience at NSA and IDA
- Areas of expertise: Hillclimbing, Dynamic Programming, Signal Processing, Probabilistic Analysis, Speech and Language Technology
- Two Letters of Commendation and NSA Special Achievement Award
- Four awards for development and application of novel cryptanalytic techniques at IDA
Corporate Advice and Governance
- Reviewed papers and proposals for DARPA, NSF, IEEE, Eurospeech, European Union Framework 6
- Serve on the Industrial Advisory Committee, IDIAP (Swiss Government Research Institute)
- Serve on the Industrial Advisory Board of Sensory, Santa Clara, CA
- Serve on the Technical Advisory Board, Center of Excellence in Human Language Technology, JHU
- Former consultant advisor to Yap (now part of Amazon), a speech recognition company in Charlotte, NC
- Past member of Board of Directors at the International Computer Science Institute, Berkeley, CA
- Served as advisor to CLSP (Center for Speech and Language Processing, JHU) and CAIP at RutgersEMPLOYMENT DETAILS
2009- SPELAMODE (SPEech, LAnguage, and MObile DEvices) Consulting, Kure Beach NC
Title: Founder and Technologist
- With Patti Price, created a research organization for Cisco in Speech and Language Technology.
- Created robust signal processing solutions for Audience to enhance Speech Recognition performance.
- Resolved performance problems in Telenav speech processing systems.
- Advised and managed Automatic Speech Recognition portion of a potential multi-million dollar proposal for Basis Technologies.
- Currently serving as Chief Scientist of Voice Morphing, a California start-up, and co-CTO of Kextil, engaged in voice-centric interfaces for the field service industry.
- Continuing with legal prior art and expert witness work for various customers in speech recognition and human interfaces, including successful defense against patent infringement in Nuance vs Vlingo in Boston, 2011.
2006-2009 SRI International, Menlo Park CA
Title: Senior Scientist
- Principal Investigator for GALE‚ Global Autonomous Language Exploitation, DARPA program.
- Created new business opportunities, including BALTIC, a virtual institute for language innovation which required negotiations with the staff of the House Armed Services Committee and various representatives.
- Technical Advisor to the STAR laboratory for speech and language processing.
- Advisor to the SRI Commercialization Board on embedded speech systems.
- Created new algorithms for machine translation.
2000 – 2006 Voice Signal Technology, Woburn MA
Title: Chief Technology Officer
- Recruited technical members of core technology team.
- Guided speech, language, and user interface technology and business development in cell phones and other mobile devices. Tracked emerging opportunities.
- Presented Voice Signal technology and marketing strategy at conferences and in popular articles.
1999 – 2000 Dragon Systems, Newton, MA
Title: Director of Business Relations
- Developed business opportunities in Audio Mining.
- Identified and negotiated government contracts, including $6M of research from DARPA.
1985 – 1999+ Institute for Defense Analyses CCR, Princeton NJ – continuing relationship as adjunct
Title: Member of the Technical Staff
- Developed novel signal processing and speech algorithms.
- Developed cryptanalytic techniques and applications.
- Assisted DARPA in bringing speech technology to use in government applications, including founding Summer Workshops in Speech Recognition (now JHU CLSP summer program in speech and language).
- Chair of Arpa workshop in Spoken Language Technology, Barton Creek, TX.
- Received four special awards for development and application of novel cryptanalytic techniques.
1982 – 1985 International Business Machines, Yorktown Heights NH
Title: Member of the Technical Staff
- Developed practical applications for discrete recognition.
- Wrote front end for TANGORA, the IBM Recognizer (auditory model)
1974 – 1982 National Security Agency, Fort Meade MD
Title: Research Engineer
- Developed novel statistical processes for signal analysis.
- Created new applications of mathematical search algorithms.
- Certified as Cryptanalytic Mathematician and Engineer.
1970-1974 US Air Force, Served at Chanute Air Force Base and at Fort Meade MD and at NSA (from 1971)
Final Rank: Captain
|1975 – 1982||University of Connecticut Storrs, CT||PhD, Linguistics (PhD Dissertation not-in-residence)|
|1968 – 1970||University of Illinois Urbana, IL||MSEE, Electrical Engineering|
|1964 – 1968||University of Massachusetts Amherst||BSEE, Electrical Engineering|
Member, Acoustical Society of America
Senior Life Member, IEEE
H. Hermansky, J. R. Cohen, and R. M. Stern, “Perceptual Properties of Current Speech Recognition Technology”, Proceedings of the IEEE, September, 2013, Vol 101 No 9, p. 1968.
M Gilbert, A Acero, J Cohen, H Bourlard, SF Chang, M Etoh, “Media Search in Mobile Devices”, Signal Processing Magazine, IEEE 28 (4), 2011, 12-13
B Erol, J Cohen, M Etoh, HW Hon, J Luo, J Schalkwyk, “Mobile media search”,ICASSP, 2009, 9, 4897-4900
J Wilpon, ME Gilbert, J Cohen, “ The Business of Speech Technologies”, Springer Handbook of Speech Processing, 2008, p. 681-704
M Harper, A Acero, S Bangalore, J Carbonell, J Cohen, B Cuthill, C Espy… Report on the NSF-sponsored Human Language Technology Workshop on Industrial Centers , 2007/6/22, pdf available from umd.edu
Jordan Cohen1, Terri Kamm2, and Andreas G. Andreou, “Vocal tract normalization in speech recognition: Compensating for systematic speaker variability”, J. Acoust. Soc. Am. Volume 97, Issue 5, pp. 3246-3247 (1995)
J. Cohen, J Flanagan, “A Welcome to the Special Edition on Robust Speech Recognition, A Summer workshop – 1993”, IEEE Trans on Speech and Audio Processing, 2, 4, 551-553.J. Cohen, “Application of an auditory model to speech recognition”, JASA, 85, June 1989J. Cohen, “Segmenting speech using dynamic programming”, JASA, 69, 1980J. Cohen, T. Crystal, A. House and E. Neuburg, “Weighty voices and shaky evidence”, JASA, 68, 1980
Many popular short articles and presentations More than 20 Classified Publications Co-author of more than 13 Patents granted Clearance:
8,019,324 Extendable voice commands
September 13, 2011 Roth; Daniel L., Reiner; Chris, Furnari; Mark, Cohen; Jordan
7,873,390 Provider-activated software for mobile communication devices
January 18, 2011 Cohen; Jordan, Roth; Daniel L.
7,809,574 Word recognition using choice lists
October 5, 2010 Roth; Daniel L., Cohen; Jordan R., Johnston; David F. , Porter; Edward W.
7,797,157 Automatic speech recognition channel normalization based on measured statistics from initial portions of speech utterances
September 14, 2010 Zlokarnik; Igor, Gillick; Laurence S., Cohen; Jordan
7,716,058 Speech recognition using automatic recognition turn off
May 11, 2010 Roth; Daniel L., Cohen; Jordan R., Johnston; David F.
7,634,403 Word recognition using word transformation commands
December 15, 2009 Roth; Daniel L., Cohen; Jordan R., Johnston; David F.
7,577,569 Combined speech recognition and text-to-speech generation
August 18, 2009 Roth; Daniel L., Cohen; Jordan R., Johnston; David F., Grabherr; Manfred G., Porter; Edward W.
7,562,019 Automated testing of voice recognition software
July 14, 2009 Cohen; Jordan, Barton; William, Ploumis; John, Ely; Douglas J.
7,526,431 Speech recognition using ambiguous or phone key spelling and/or filtering
April 28, 2009 Roth; Daniel L., Cohen; Jordan R., Johnston; David F.
7,505,911 Combined speech recognition and sound recording
March 17, 2009 Roth; Daniel L., Cohen; Jordan R., Johnston; David F., Porter; Edward W.
7,444,286 Speech recognition using re-utterance recognition
October 28, 2008 Roth; Daniel L., Cohen; Jordan R.
7,313,526 Speech recognition using selectable recognition modes
December 25, 2007 Roth; Daniel L., Cohen; Jordan R., Johnston; David F., Grabherr; Manfred G.
7,225,130 Methods, systems, and programming for performing speech recognition
May 29, 200 Roth; Daniel L., Cohen; Jordan R., Johnston; David F., Grabherr; Manfred G.
SELECTED INFORMAL PRESENTATIONS AND ARTICLES
“Simple Speech Morphing: A Story” presented to the Boston chapter of AVIOS and Brandeis University, October 17, 2013.
“OUCH (Outing Unfortunate Characteristics of HiddenMarkovModels) or What’s Wrong with Speech Recognition and What Can We Do About it?”, Johns Hopkins University, Sep 14, 2012 (see http://www.clsp.jhu.edu/seminars/1335/)
“Embedded speech recognition applications in mobile phones: Status, trends and challenges”, in Proceedings of the International Conference on Acoustic Speech and Signal Processing 2008, April, 2008, p. 5352 – 5355
“The GALE Project: a description and an update”, in Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, 9-13 December, 2007
“Handheld Multimodal Interfaces Technology, Markets, and Opportunities” Johns Hopkins, Baltimore, 2005
“Is Embedded Speech Recognition Disruptive Technology?” in Information Quarterly, Volume 3, Number 5, 2004, p. 14-17
“Practical Manipulation of Local Data – An Update”, At Wireless Internet Data and Enterprise Applications, UCLA, Los Angeles, CA, September 2003
“Putting Speech Technologies in your Hands”, LangTech 2003, Paris, 24-5 November 2003
“Voice Signal Overview: The Case for Embedded Speech Recognition”, VOX 2002, Kelsey Group, San Francisco, CA (July, 2002)
“Speech recognition in the real world: An Embedded Viewpoint” Center for Language and Speech Processing Workshop at Johns Hopkins, July 26, 2001
“Some musings on systematic variability and speech recognition”, J. Acoust. Soc. Am. Volume 105, Issue 2, pp. 1158-1158 (1999)
“The Challenge of Spoken Language Systems: Research Directions for the Nineties”, Co-author, IEEE Transactions on Speech and Audio Processing, Vol 3, No. 1 1-20 Jan 1995.
“The hub and spoke paradigm for CSR evaluation” (co-author), Proceedings of the 1994 Human Language Technology Workshop, Plainsboro, NJ, March, 1994
“Robust speech processing”, Jordan Cohen, Chair “The Summers of our Discontent”, a talk In Speech and Natural Language: Proceedings of a Workshop Held at Harriman, New York, February 23-26, 1992
“A Pitch measurement algorithm for speech” Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP ’82.