SBIR-STTR Award

We propose to design and implement a system that combines multiple audio transcription and multiple translation tools with natural language processing capabilities, such that information can be automatically extracted from audio files with improved performances. In our approach, speech waveforms of a foreign language are first processed to remove background noise using our noise reduction algorithm developed based on our patented auditory transform theory. The clean speech is then feed forward to multiple speech recognizers to convert to text. A error correction algorithm is then applied to reduce word error rates based on the text and a neural language model. Following that, multiple machine translators are used to translate the text to English. An error correction algorithm with English language model is then applied to make further correction. Finally, a natural language processing unit extracts out the entities, associations, concepts, and themes. Based on recent research results, the proposed approach has the potential to reduce word error rates by 20% and improve the entire system robustness. Our solution will leverage our experience and expertise in noise reduction, speech enhancement, neural network training, robust speech recognition and language model construction.

Keywords:
Audio Processing, Nautural Language Processing, Machine Translation, Transcription, Word Error Rates, Cloud Computation, Word Gazetteers, Word Frames, Map Reduce

The purpose of this project is to advance the state of the art in audio transcription, text analytics and machine translation technologies and solutions for National Geospatial-Intelligence Agency (NGA), Navy, and Marine Corps operations. This project has four major tasks: first, audio transcription to convert Chinese audio into English text; second, maritime Chinese-English dictionaries; third, accurate machine translation to translate text documents in Chinese language into US English in near perfect accuracy; and last, text analytics to extract associative and actionable information, identify concepts, and recognize theme from Chinese text. The input documents are in Chinese while the output and queries are in English. Advance algorithms and software will be developed and delivered in this project for real applications.

Benefit:
Several software products will be developed and delivered from this project. For the military market, we will delivery four products: (1) Chinese audio to text transcription software; (2) Maritime Chinese-English dictionaries; (3) Maritime Chinese-English translation software; and (4) Text analytic software from Chinese for English users. For the commercial market, the product from this project will be a software tool for data analytics. The software can create knowledge base from documents, extract interested information, identify concept, and recognize theme for business intelligence and personal information analysis, decision, and associative searching.

Keywords:
Natural Language Processing, notice to mariners, Analytics, Audio Processing, text, translation, Automatic Speech Recognition, machine transcription