Developed ESPN's Automatic Speech recognition System

Involved video/audio content analysis/retrieval processing

• - Successfully Developed the software tools (Grxml2Gnd) for converting the grammars with the Speech Recognition Grammar Specification (SRGS) into PlayStation Voice Response System’s grammars (GnD). Took sole responsibly for design and implementation of Grxml2Gnd include several features. (C/C++, Linux/Windows,)

multi-lingual capability and switching between languages in a grammar.

provide the Phoneme set based on the given lexicon.

Process grammars with formats of ASCII and UTF8. Reject other format files

Added semantic information in GND for the semantic interpretation post processing.

• - Design the semantic interpreter for PSVR

• - Developed website data collection tools. (C, Python, Scrapy,Django, Linux/Windows)

• - Developed speech-to-text application of using Google Speech API for the speech recognition (Python, JAVA, Linux/Windows)

Successfully developed, enhanced and optimized signal and decoding algorithms used to automatically transcribe speech into text across multiple languages. Modeled, tested, designed, and optimized algorithms for speed, accuracy, and scalability. Led the enhancement and optimization of SAIC’s PlainSpeech ASR decoder to include several new features. (C/C++)

• Designed uniform front-end features from different engines.

• Implemented linear discrimination methods, language model look-ahead method, key/hot word recognition, and test-to-speech alignment

• Enhanced the finite state automata (FSA) functionalities.

• Developed SRGS-compatible grammar-based speech recognition to support voice based 511 systems.

• Optimized ASR engine to dynamically manage lexicons, language models, and grammar.

• Improved the ability of the engine to perform real time recognition.

• Significantly reduced CPU time and memory requirements, while improving speech recognition accuracy.

• Designed and developed a high quality multi-pass speech recognition architecture.

• Led the design and implementation of the SAIC Advanced Speech Recognition System for IVR solutions with a grammar parser that fully supports the W3C Speech Recognition Grammar Specification (SRGS).

• Built a Synthetic Aperture Radar (SAR) and Ground Moving Target Indication (GMTI) simulation system. (Matlab)

• Developed and Implemented the advanced interference mitigation and high resolution imagery algorithms (Matlab)

• Developed and implemented the DFC’s moving target tracking systems; built the orbit tracking toolbox for multiple moving target tracking, with the following modules. (Matlab)

• Developed numerous advanced algorithms (for sensor collection management planning; for the generation of the combined balanced multiple classifier; and for an assignment system by using game theory). (Matlab)

• Developed and implemented a radar multi-scan processing system. (Matlab)

• Conducted a study of Subspace Tracking algorithms in applications of target detections in strong interference environment; and conducted a study of Wavelet algorithms in applications of target detections in images.

• Conducted research on image object tracking by using morphological anisotropic diffusion pyramid methods. (Matlab)

• Developed and implemented belief models with Analytic hierarchy Process (AHP), Fuzzy logic, and Dempster-Shafer evidential reasoning methods. (Matlab)

• Developed a control tool for managing data rates and data resolution in a distributed battle management using a model-reference, adaptive control-theoretic approach.

• Developed and implemented a Genetic Algorithm in path design.