Abstract
In this paper, we compare the performance of fixed and adaptive beamformers as an application to speech enhancement (SE) algorithm. The proposed signal processing pipeline works in real-time for hearing aid devices using only a smartphone with no additional hardware as an assistive tool. The proposed method consists of a Wiener filter based single-channel SE method along with beamformer as a pre-filter using only two built-in microphones of the smartphone. In this work, multiple beamforming approaches like delay and sum, minimum variance distortionless response (MVDR) and generalized sidelobe canceller (GSC) beamformers are considered and compared. The use of beamformers is shown to improve the signal to noise ratio (SNR) of speech signal in real-world noisy conditions through the results presented in this paper. Objective test measures are used to evaluate perceptual quality and intelligibility of enhanced speech achieved by different approaches. Test results show the performance comparison of different approaches as well as the efficiency of proposed method at different SNR levels.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
