Software architect and speech scientist with over twenty years of experience in new product development and project management. Has expertise in financial services, linguistics, biometrics, human factors, IVR & text chatbot design and natural language processing:
Programming: Python, Java, C, C++, VB, LISP
Voice & Chatbot User Interface Design
Strategic planning, project estimation, project plan development
VXML application and grammar development
Custom recognition and TTS lexicon development
Speech & text application usability assessment
RFI & RFP response authoring, SOW authoring
IVR Design Group: New York, NY, 12/17-Current. Principal. Consulting on design and development of speech, text and multi-modal applications for clients including Apple, IBM/TD, Great Healthworks, PTP, FirstBank, Coke, Western Union and Fedex.
ImmunityHealth: New York, NY, 1/18-1/22. NLP Consultant. Use CRM, NLP and ML on medical records to automate patient matching to clinical trials.
Voxgen (Waterfield): New York, NY, 10/16-12/17. Senior Voice User Experience Consultant. Designed IVR, voice and text user experiences, clients included Allstate, Nike, XPO, Lime, Game, Home Depot, Hawaiian Telecom; Assisted with client management for user experience design projects; Assisted with Speech Science, including grammar development and performance tuning; Assisted with Chat Bot development.
Speechpro: New York, NY, 1/16-10/16. Chief Technology Officer. Voice biometrics, multi-channel recording, speech analytics, audio enhancement, ASR, TTS; Oversaw customization and localization of products for the US market.
Cyara: New York, NY, 3/15-1/16. Senior Technical Consultant. Worked with clients to understand and gather business and technical requirements; provided consultancy on test strategies, methodologies and best practices within the contact center domain; worked with project and technical personnel to implement, deploy and deliver solutions; ran training sessions, product demonstrations, workshops and webinars; provided support for client queries; developed strong customer relationships; pre-sales support.
MorganStanley: New York, NY, 5/10-3/15. Contact Center Engineering, UI Designer & Speech Scientist. Design and build new IVR and call center infrastructure for the merger of Morgan Stanley and Smith Barney. Roles: principal UI designer for IVR managing call flows, prompts, grammar development and speech science; Business analyst develop new features; day-to-day performance testing and escalations; analysis and research of new technologies such as biometrics and chatbot virtual agents. Redesigned ID&V process resulted in increased containment rate of 30%, savings more than $1M per year, improved user experience.
IVR Design Group: New York, NY, 10/09-05/10. Principal. Design and development of speech, text and multi-modal applications.
Genesys: Daly City, CA, 4/04-10/09. Principal Consultant, UI Design & Speech Science. Performed pre-sales and post-sales technical consulting and design and development of speech applications.
Bank of America (Countrywide): Calabasas, CA, 1/04-3/05. VP Application Development. Designed self-service voice applications for mortgage insurance servicing, human resources call routing, privacy preferences setting, credit card activation and pay plan enrollment.
HeyAnita: Los Angeles, CA, 3/01-1/04. Director of Design & Speech Science. Managed team of linguists, created voice portals for Sprint-PCS, Verizon Wireless and Vodaphone. Developed requirements, call flows, grammars and dictionaries, testing and system tuning.
Hughes Research Labs: Malibu, CA, 9/00-3/01. Technical Consultant, Speech Understanding. Developed voice-activated applications, including telematics for GM and air traffic control for Raytheon.
Text Analysis International: Laguna Beach, CA, 8/99-3/01. Worked on IDE for text analysis applications. Indicast (Oracle): Del Mar, CA, 9/99-1/00. Voice user interface designer. Patented interface.
Unisys: Malvern PA, 1/98-1/00. Technical Consultant. Performed technical pre- and post-sales support for Natural Language Speech Assistant.
Echobuzz: Irvine, CA, 1/98-8/99. Vice President, R&D. Developed voice activated voice mail.
Citigroup: Advanced Development Group: Los Angeles, CA 90-98. Systems Architect 96; Computer Scientist 95; Principal, Technical Staff 92; Technical Staff 90. Developed biometrics lab, patented biometrics implementation on smartcards; Built patented multilingual IVR system; Analyzed & deployed NLP and translation technologies; Implemented ASR systems for consumer and corporate financial services, including auto-attendants & phone banking; Implemented voice input & output for FX trading; Assesse and selected vendors of telecom technologies for trading floors; Designed SEI CMM SDM for R&D.
LSI: Woodland Hills, CA, 90-95, 99. Speech Consultant. Developed speech-to-speech translation system for military intelligence.
Speech Systems: Tarzana, CA 84-89. Director, Contract Research 86; Technical Staff 84. Coded acoustic phonetic features, dictionaries, grammars and tools; Wrote proposals for and managed activity on government and privately sponsored contract R&D, including programs for Citibank, DARPA, DOD, FAA, NASA, DOE, & DOT.
Language Systems: Providence, RI, 83-84. Application Developer. Worked on a grammar checker for word processing developed by Henry Kucera. Code licensed to Houghton Mifflin and delivered in Microsoft Word.
Brown University: Providence, RI, 81-83. Research Assistant Speech Lab. The lab examined the cognitive and neural bases of language.
Ph.D., Linguistics, Brown University.
B.A., International Relations & History, Brown University.
US5794218: Automated multilingual interactive system.
US5806050: Electronic transaction terminal for vocalization of transactional data.
US6529586: System for secure telephonic transmission of audio data.
US6655585: System and method of biometric smart card user authentication.
US7376622: System for automated debiting and settling of financial transactions
Selected Publications & Presentations
“The Impact of Voice Talent Persona Selection on Intelligibility for the Elderly,” SpeechTek, New York, 8/2009
“View From AVIOS: The Dilemma of AI Transparency”, Speech Technology, Feb. 7, 2020, p. 6.
“Who Are You?” in Ubiquitous Voice, Falkson, L. Ed., Independent Pubs, 2018, pp. 74-79.
“Ten Criteria for Measuring Effective Voice User Interfaces,” with J. Larson et al., Speech Technology, 12/2005 “Designing Language Models for Voice Portal Applications,” with M. Shomphe,et al., International Journal of Speech Technology, Kluwer Academic, Vol. 7, pp 93-99, 2004.
“Methods for the Identification of Evoked Response Components in the Frequency and combined Time/Frequency Domains”, with A. M. Norcia et al., Electroencephalography and Clinical Neurophysiology, 1986, 65, pp. 212-226.
“Limitations on Context-Conditioned Effects in the Perception of [b] and [w],” with S. E. Blumstein and A. Jongman, Perception and Psychophysics, 1985, 38(5), pp. 397-407.
“On the Role of the Amplitude Envelope for the Perception of [b] and [w],” with S. E. Blumstein, Journal of the Acoustical Society of America, 1984, Vol. 75, No. 4, pp. 1243-1252.
“Phonetic Disintegration in Aphasia: Acoustic Analysis of Spectral Characteristics for Place of Articulation,” with S. E. Blumstein, Brain and Language, 1983, Vol. 20, pp. 90-114.
“A Continuous Speech Recognizer Using Two-Stage Encoder Neural Nets,” with W.S. Meisel, et al., Proc Int. Joint Conference on Neural Networks, Washington DC, pp 306-306, 1/1990
“Phoneme-based, Speaker Independent, Continuous Speech Recognition,” Presentation at the American Association for Artificial Intelligence Conference, Minneapolis, 8/1988.
A Cross-language Investigation of the Stop, Affricate and Fricative Manners of Articulation, University Microfilms, Ann Arbor, MI, 1984