Abstract
This paper proposes a new technique for improving a generalized sidelobe canceller (GSC) for dual-microphone speech enhancement to be applied in an auditory device such as a hearing aid. Here, the GSC is implemented on a 32-channel uniform polyphase discrete Fourier transform filter bank, where the overall algorithm processing delay is 8 ms to meet hearing aid requirements. The proposed method can improve the fixed beamformer (FBF) and control the adaptive algorithm in the noise canceller (NC) using the phase difference obtained from dual-microphone signals. For this, spatial cues such as the phase differences are used to estimate the target-to-non-target directional signal ratio (TNR). A target-directional speech enhancing spectral gain-attenuator is calculated based on the estimated TNR, which is then incorporated to improve the FBF in the GSC. Furthermore, the weight update of the adaptive NC in the GSC is formulated using the phase difference-based TNR. The experimental results show that the auditory speech enhancement system that employs the proposed dual-microphone GSC algorithm provides better perceptual quality and intelligibility scores than conventional methods such as a beamformer, phase-error-based filter (PEF), GSC, or PEF-controlled GSC under multiple noise conditions of signal-to-noise ratio range 0-20 dB.
Highlights
Individuals with hearing impairment have difficulty understanding the important content of speech in their daily lives
PERFORMANCE EVALUATUION We evaluate the performance of the proposed PD-target directional signal ratio (TNR)-based generalized sidelobe canceller (GSC) to improve the approach for noisy speech signals generated by a simulated dual-microphone system
The proposed method provided significantly better perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI) scores than the conventional methods except phase-error-based filter (PEF)-GSC and phase difference–based TNR (PD-TNR) for all the considered reverberant conditions
Summary
Individuals with hearing impairment have difficulty understanding the important content of speech in their daily lives. The problem has been overcome using electronic auditory devices such as hearing aids, which are widely used to amplify or compress the signal that enters the ear to match the dynamic range and compensate for hearing loss [1]. Hearing aids achieve this by estimating the signal envelop power according to frequency channels, which is based on a filter bank system [2], [3]. It has the advantage of being implemented as an overlapand-add (OLA) short-term Fourier transform (STFT), which makes it easy to implement single- or multi-microphone noise
Sign-in/Register to view highlights & summary 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.
