摘要 |
PROBLEM TO BE SOLVED: To provide a method and a system for removing acoustic noise from human speech, wherein noise is removed to restore a signal therefrom regardless of noise type, amplitude, or orientation.SOLUTION: The system includes a microphone and a sensor coupled with a processor. The microphone receives an acoustic signal, and VAD (voice activity detection) provides a binary one when speech (voiced and unvoiced) is occurring, and a binary zero in the absence of speech. The processor includes denoising algorithms that generate transfer functions. The transfer functions include a transfer function generated in response to a determination that voicing information is absent in the received acoustic signal during a specified time period. The transfer functions are used to generate at least one denoised acoustic data stream. |