Automated briefings are an essential information source for pilots as they provide a comprehensive and up-to-date picture of meteorological and aeronautical conditions, ensuring safe and efficient flight operations. These briefings come in a variety of formats, a notable few being Automated Terminal Information Service (ATIS), Automated Surface/Weather Observation System (ASOS/AWOS). These systems provide an audio broadcast of the current weather, runway surface conditions, and other pertinent information to pilots without them having to reference the air traffic control tower or ground observers. While most aircraft are equipped with VHF radios for receiving information through audio transmissions, it poses challenges as pilots must accurately interpret the audio and manually execute necessary actions. Though digital data transmissions are the ideal solution to improve accuracy and allow automation, most airplanes lack the necessary equipment for this. As a result, general aviation (GA) will continue to rely on audio transmissions for the foreseeable future. However, recent advances in speech recognition and natural language processing can bridge this gap by converting analog audio information into digital data, thus enabling automation. These advanced technologies rely on vast amounts of data, particularly human-verified transcriptions, to be effective in aviation applications. To facilitate research in this area, we propose and publicly release an automated informational briefings voice dataset (AVIBRIEF) for Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) research purposes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    AVIBRIEF: Automated Vocal Information Briefings Dataset


    Contributors:


    Publication date :

    2023-10-01


    Size :

    4017062 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English