Framewise Finite Impulse Response Filtering Based on Time-Frequency Mask for Low-Latency Speech Enhancement | IEEE Conference Publication | IEEE Xplore

Framewise Finite Impulse Response Filtering Based on Time-Frequency Mask for Low-Latency Speech Enhancement


Abstract:

We propose a low-latency speech enhancement method using framewise finite impulse response (FIR) filters based on time-frequency (T-F) mask. In many real-time audio appli...Show More

Abstract:

We propose a low-latency speech enhancement method using framewise finite impulse response (FIR) filters based on time-frequency (T-F) mask. In many real-time audio applications, such as hearing aids, low-latency processing is highly required. T-F masking-based speech enhancement algorithms improve speech intelligibility for hearing impaired people in noisy environments, but an algorithmic delay due to frame analysis occurs. To shorten this delay, we replace time-frequency masking with framewise filtering in the time domain. The filters are designed on the basis of the signal and noise spectra in each frame, which are the same information used as that for designing a Wiener-filter-based T-F mask. The latency is shortened by designing a causal FIR filter and predicting the signal and noise spectra only from the information in the past frames. Evaluation experiments showed that causal framewise FIR filtering reduced the delay with little degradation of the performance compared with T-F masking.
Date of Conference: 14-17 December 2021
Date Added to IEEE Xplore: 03 February 2022
ISBN Information:

ISSN Information:

Conference Location: Tokyo, Japan

Funding Agency:


I. Introduction

People with hearing loss suffer not only from an elevated threshold for detecting sounds but also from understanding speech, especially in noisy environments [1]. One of the ef-fective approaches to address hearing loss is the use of hearing aids. Hearing aids amplify the acoustic signals and send the amplified signals into the ear canal. The signal is amplified frequency-dependently and the amount of amplification at each frequency region is appropriately determined by the degree of the user's hearing loss in each frequency region [2]–[4]. This process significantly improves speech understanding in quiet environments [5]. However, when background noise is present, both the speech and the noise are amplified, and users with cochlear hearing loss cannot understand speech as effectively as prople with [1]. Therefore, nowadays, most commercially available hearing aids have speech enhancement systems, and there have been many studies on speech enhancement [6]–[9].

References

References is not available for this document.