Montclair State University - Speech Communication
Ph.D., Speech Scientist, Vocologist
Higher Education
Peter
Popolo
Greater New York City Area
Research scientist in digital image and speech processing/analysis with over 7 years of experience in the medical device industry, and 15+ years of experience in the development of software and hardware for video and audio recording, image analysis, and acoustic analysis.
Product Manager
Managed the ENT (Ear, Nose, and Throat) Imaging product line that generated $25 million in annual sales and $3 million/year in profits. Headed new product development projects, including video imaging systems, speech analysis products, and EMR/networking software.
• Developed user requirements based on customer goals, product knowledge, and best practices in user-centered design.
• Performed customer-centered validation and usability testing of products from conceptual design to pre-production stages.
• Established Optical Testing Laboratory within Product Management for the specification and analysis of video endoscope parameters including image quality, magnification, distortion, field of view, and depth of field.
• Led seven-member multidisciplinary teams consisting of Marketing, R&D, QA, RA, Production, Operations, and Sales.
Research Scientist
• Proposed, created, and executed on projects funded by government and private agencies.
• Developed new algorithms and techniques in speech recognition and speaker identification, by extracting acoustic features of voice used in clinical diagnosis of voice disorders.
• Designed and developed an ambulatory monitoring device used by speech-language pathologists to monitor voice use, for a grant-funded study of vocal fatigue in teachers.
• Created algorithms to solve problem of detecting and processing speech signals in real time using a PDA (Personal Digital Assistant), precursor to today’s smart-phone and apps.
Consultant, Digital Health Applications
Provide expertise in speech recognition, speaker identification, laryngeal imaging, and acoustic analysis of voice for digital health applications used by speech-language pathologists and speech scientists.
• Development of applications and UI/UX solutions for mobile platforms (iPhone and Android), and API and SDK requirements for communication solutions.
• Specification and implementation of image and video analysis products and components.
• Integration of wearable, wireless biosensors with smartphones for high-fidelity (CD-quality or better) voice signal input.
• Specification of HIS (Hospital Information Systems), EMR (Electronic Medical Records), and medical imaging exchange systems and solutions.
Assistant Professor, Dept. of Communication Sciences & Disorders
Perform funded scholarly research and provide instruction in clinical instrumentation for speech-language pathology, acoustic analysis of voice, and high-speed imaging of the vocal folds. Current research interests include:
• Creation of computer vision algorithms and software for motion analysis of high-speed video of the larynx, including detection and tracking of changes in glottal area and movement of vocal folds, edge detection, color analysis and classification, FFT analysis of vocal fold vibration, and kymographic analysis to show image motion over time.
• Development of a smartphone app to collect voice data from disordered voice patients over a cloud-based network, for use by speech-language pathologists to study the efficacy of vocal therapies and track improvements in their patients.
• Design of a wearable biosensor to be used with smartphones or other mobile platforms for transduction of speech and voice signals.
B.S.
Electrical Engineering
M.S.
Electrical Engineering
Ph.D.
Speech and Hearing Science