Skip to content

Latest commit

 

History

History
54 lines (35 loc) · 3.23 KB

README.md

File metadata and controls

54 lines (35 loc) · 3.23 KB

Logo(Black)

Whsiper-ATC

2024년 국립창원대학교 정보통신공학과 캡스톤디자인(졸업작품) - 음성인식을 이용한 항공교통관제(ATC) 보조시스템 (김동균, 손승광)

Capstone Design (Graduation Work), Department of Information and Communication Engineering, Changwon National University, 2024 - Air Traffic Control (ATC) Assistance System using Voice Recognition (Dongkyun Kim, Seungkwang Son)

소개

Whisper-ATC은 OPENAI사가 개발한 Whisper 모델에 항공교통관제(ATC)의 교신내용을 추가로 Fine-Tuning(미세조정)하여 만든 모델을 사용합니다. 해당 모델을 이용하여 항공교통관제의 교신내용을 Speech To Text하여, DB에 저장하고 웹 상에서 열람하도록 하는 기능을 제공합니다.

Whisper-ATC uses the Whisper model developed by OPENAI, which is an additional Fine-Tuning model of Air Traffic Control (ATC) communications. Using this model, it provides a function that allows you to speak to text communication content of air traffic control, store it in the DB, and view it on the web.

논문 (Paper)

음성인식을 이용한 항공교통관제(ATC) 보조시스템 - Whisper-ATC : Air Traffic Control Assistance System Using Speech Recognition

Paper PDF

웹페이지 (Webpage)

<메인>

image

<기록열람> image

<통계> image

<녹음> image

모델 (Model)

음성인식 모델은 아래 링크를 방문해주세요. For voice recognition models, please visit the link below.

사용기술

image

구성도

image

참고

  • Zuluaga-Gomez, Juan, et al. "How does pre-trained wav2vec 2.0 perform on domain-shifted asr? an extensive benchmark on air traffic control communications." 2022 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2023.

  • Zuluaga-Gomez, Juan, et al. "Bertraffic: Bert-based joint speaker role and speaker change detection for air traffic control communications." 2022 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2023.

  • Zuluaga-Gomez, Juan, et al. "Atco2 corpus: A large-scale dataset for research on automatic speech recognition and natural language understanding of air traffic control communications." arXiv preprint arXiv:2211.04054 (2022).