Noise Reduction with Microphone Arrays for Speaker Identification
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Reducing acoustic noise in audio recordings is an ongoing problem that plagues many applications. This noise is hard to reduce because of interfering sources and non-stationary behavior of the overall background noise. Many single channel noise reduction algorithms exist but are limited in that the more the noise is reduced; the more the signal of interest is distorted due to the fact that the signal and noise overlap in frequency. Specifically acoustic background noise causes problems in the area of speaker identification. Recording a speaker in the presence of acoustic noise ultimately limits the performance and confidence of speaker identification algorithms. In situations where it is impossible to control the environment where the speech sample is taken, noise reduction filtering algorithms need to be developed to clean the recorded speech of background noise. Because single channel noise reduction algorithms would distort the speech signal, the overall challenge of this project was to see if spatial information provided by microphone arrays could be exploited to aid in speaker identification. The goals are: (1) Test the feasibility of using microphone arrays to reduce background noise in speech recordings; (2) Characterize and compare different multichannel noise reduction algorithms; (3) Provide recommendations for using these multichannel algorithms; and (4) Ultimately answer the question - Can the use of microphone arrays aid in speaker identification?
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- W-7405-ENG-48; AC52-07NA27344
- OSTI ID:
- 1034487
- Report Number(s):
- LLNL--TR-524752
- Country of Publication:
- United States
- Language:
- English
Similar Records
Laser-induced breakdown spectroscopy acoustic testing of the Mars 2020 microphone
System And Method For Characterizing Voiced Excitations Of Speech And Acoustic Signals, Removing Acoustic Noise From Speech, And Synthesizi