Optimal Near-End Speech Intelligibility Improvement Incorporating Additive Noise and Late Reverberation Under an Approximation of the Short-Time SII

Abstract

The presence of environmental additive noise in the vicinity of the user typically degrades the speech intelligibility of speech processing applications. This intelligibility loss can be compensated by properly preprocessing the speech signal prior to playout, often referred to as near-end speech enhancement. Although the majority of such algorithms focus primarily on the presence of additive noise, reverberation can also severely degrade intelligibility. In this paper we investigate how late reverberation and additive noise can be jointly taken into account in the near-end speech enhancement process. For this effort we use a recently presented approximation of the speech intelligibility index under a power constraint, which we optimize for speech degraded by both additive noise and late reverberation. The algorithm results in time-frequency dependent amplification factors that depend on both the additive noise power spectral density as well as the late reverberation energy. These amplification factors redistribute speech energy across frequency and perform a dynamic range compression. Experimental results using both instrumental intelligibility measures as well as intelligibility listening tests show that the proposed approach improves speech intelligibility over state-of-the-art reference methods when speech signals are degraded simultaneously by additive noise and reverberation. Speech intelligibility improvements in the order of 20% are observed.Index Terms-Additive noise, approximated speech intelligibility index (SII), late reverberation, speech intelligibility.

Adaptive Reverberation Absorption Using Non-Stationary Masking Components Detection for Intelligibility Improvement

“…The proposed method improves 9, 7 and 9 against 3, 1 and 5 for the AGC under SNR values of −3 dB, 0 dB and 3 dB, respectively. In accordance with findings of [10] [13], SSS attains scores less than or equal to the UNP case.…”

“…The noisy-reverberant scenario is composed of two real reverberant rooms and four background non-stationary acoustic noises with five different SNR values. The ESII [12] and ASII ST [13] measures are adopted for the intelligibility prediction. These measures are explicitly designed to deal with the non-stationarity of speech and its distortions.…”

Nonintrusive Speech Intelligibility Prediction Using Convolutional Neural Networks

“…The dataset has 32 conditions in total. • D 6 : (Described in [72].) Speech intelligibility was measured for sentences from the Dutch matrix sentence test [71] convolved with a room impulse response (T 60 = 1s) and further degraded by additive SSN.…”

Speech intelligibility improvement in noisy reverberant environments based on speech enhancement and inverse filtering

“…In recent years, only a few studies have considered the effects of reverberation and background noise simultaneously [19][20][21][22]. Some methods just use the near-end speech enhancement method to reduce the influence of both reverberation and background noise [19,20].…”

“…Some methods just use the near-end speech enhancement method to reduce the influence of both reverberation and background noise [19,20]. Other methods pre-compensate the output speech by obtaining the optimal solution of the established mathematical model to improve intelligibility [21,22]. Crespo and Hendriks [21] proposed a multizone speech reinforcement method based on a general optimization framework.…”