Review of Automatic Speech Recognition Methodologies

Details

• Creators:
  Achour, Gabriel ; Salunke, Oojas ; Payan, Alexia P ; Harrison, Evan ; Sahbani, Chiheb ; Carannante, Giuseppina ; Ditzler, Gregory ; Bouaynaya, Nidhal
• Corporate Creators:
  Georgia Institute of Technology. Aerospace Systems Design Laboratory ; Rowan University
• Corporate Contributors:
  United States. Department of Transportation. Federal Aviation Administration. Flight Technologies and Procedures Division ; United States. Department of Transportation. Federal Aviation Administration. William J. Hughes Technical Center
• Subject/TRT Terms:
  • Machine learning
  • Speech recognition
  • Speech synthesis
  • Language Automatic Speech Recognition
  • Speech to Text
  • Natural Language Processing
• Publication/ Report Number:
  DOT/FAA/TC-23/47
• DOI:
  https://doi.org/10.21949/1528227
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Contracting Officer:
  Li, Huasheng
• Corporate Publisher:
  United States. Department of Transportation. Federal Aviation Administration. William J. Hughes Technical Center
• Abstract:
  This report highlights the crucial role of Automatic Speech Recognition (ASR) techniques in enhancing safety for air traffic control (ATC) in terminal environments. ASR techniques facilitate efficient and accurate transcription of verbal communications, reducing the likelihood of errors. The report also details the evolution of ASR technologies, converging to machine learning approaches from Hidden Markov Models (HMMs), Deep Neural Networks (DNNs) to End-to-End models. Finally, the report details the latest advancements in ASR techniques, focusing on transformer-based models that have outperformed traditional ASR approaches and achieved state-of-the-art results on ASR benchmarks.
• Format:
  PDF
• Funding:
  DTFACT-14-D-00004,692M152240001
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/68518/dot_68518_DS1.pdf
• File Type:
  [PDF - 1.29 MB]
• Collection(s):
  FAA William J. Hughes Technical Center for Advanced Aerospace
• Main Document Checksum:
  urn:sha-512:dd8ea5d883837ab7f502a583eb10306510cd10859808dd58865962d4f6157b60449026ee975f4cd3bcad1ff932df58fe6dd674d7bc7b8ef944ca7d1219d68216