A Two-Stage Approach for Noisy-Reverberant Speech Intelligibility Improvement

Abstract

In this paper, a two-stage time domain technique is proposed to improve intelligibility of speech signals under noisy-reverberant conditions. In this method, the NNESE and ARA NSD methods are jointly taken into account to mitigate the effects of noise and reverberation separately. Additionally, the resulting approach is adaptive in the sense that no prior knowledge of speech statistics or room information is required. Two intelligibility measures (ASII ST and ESII) are used for objective evaluation. The results show that the proposed twostage scheme leads to a higher intelligibility improvement when compared to competing methods, specially for low SNR values. Furthermore, the PESQ and the updated version of the SRMR quality measure (SRMRnorm) demonstrate that the proposed technique also attains quality improvement.

Sixty Years of Frequency-Domain Monaural Speech Enhancement: From Traditional to Deep Learning Methods

“…Both time- and frequency-domain methods of monaural speech enhancement have been proposed and widely studied. For the former, the clean speech is estimated directly in the time domain without (short-term) spectral analysis and synthesis (Lee & Jung, 2000; Benesty & Chen, 2011; Luo & Mesgarani, 2018; Macartney & Weyde, 2018; Pandey & Wang, 2018, 2019b; Hao et al, 2019; Pandey & Wang, 2019a; Von Neumann et al, 2020; Zucatelli & Coelho, 2021; Pandey & Wang, 2022). For the latter, the short-term complex spectrum of the clean speech is estimated, the spectrum is converted back to a time-domain signal, and this process is repeated for a series of overlapping frames (time segments) to reconstruct the complete time-domain signal, using the overlap-add method (Allen, 1977; Boll, 1979; Ephraim & Malah, 1984; Griffin & Lim, 1984; Loizou, 2013; Wang & Chen, 2018).…”