Abstract
The research presented in this dissertation aims to address the need for improved communication between heavy machinery operators and external personnel, aiming to improve safety and efficiency by overcoming the communication barriers posed by equipment noise and cab insulation. The primary purpose of this research was to develop a hands-free communication system that allows the operator to hear speech from outside the cab without requiring any personal communication devices like radios or headsets. Key objectives included effective speech extraction from ambient noise and accurate estimation of the location of the speaker. Operating without active user control, the system emphasizes clarity of speech content, minimal latency, and robustness across diverse speaker positions. This dissertation presents in detail the development of several acoustic filtering and processing techniques utilized in the pursuit of these objectives. Also included are publications describing methods which were developed alongside the main body of research, which aided in the development of the communication system.
Degree
MS
College and Department
Ira A. Fulton College of Engineering; Mechanical Engineering
Rights
https://lib.byu.edu/about/copyright/
BYU ScholarsArchive Citation
Garner, Curtis L., "Extracting Speech Content From High-Amplitude Background Machine Noise" (2024). Theses and Dissertations. 11110.
https://scholarsarchive.byu.edu/etd/11110
Date Submitted
2024-12-13
Document Type
Thesis
Keywords
Noise filtering, Speech extraction, DOA estimation, Localization uncertainty
Language
english