Signal-to-noise ratio adaptive post-filtering method for intelligibility enhancement of telephone speech

Abstract

Post-filtering can be utilized to improve the quality and intelligibility of telephone speech. Previous studies have shown that energy reallocation with a high-pass type filter works effectively in improving the intelligibility of speech in difficult noise conditions. The present study introduces a signal-to-noise ratio adaptive post-filtering method that utilizes energy reallocation to transfer energy from the first formant to higher frequencies. The proposed method adapts to the level of the background noise so that, in favorable noise conditions, the post-filter has a flat frequency response and the effect of the post-filtering is increased as the level of the ambient noise increases. The performance of the proposed method is compared with a similar post-filtering algorithm and unprocessed speech in subjective listening tests which evaluate both intelligibility and listener preference. The results indicate that both of the post-filtering methods maintain the quality of speech in negligible noise conditions and are able to provide intelligibility improvement over unprocessed speech in adverse noise conditions. Furthermore, the proposed post-filtering algorithm performs better than the other post-filtering method under evaluation in moderate to difficult noise conditions, where intelligibility improvement is mostly required.

Learning static spectral weightings for speech intelligibility enhancement in noise

“…Methods based on post-filtering (e.g. Hall and Flanagan, 2010;Jokinen et al, 2012) might achieve similar effects in terms of reallocating energy across frequencies. While the frequency response of the filter in Jokinen et al (2012) is close to the static weighting found in the current study (i.e.…”

“…it tends to be flat after approximately 1.5 kHz), the filter proposed in Hall and Flanagan (2010) has an incremental response from approximately 0.4 to 3.5 kHz, which then holds constant thereafter 3.5 kHz. By comparing the performance of the two filters, Jokinen et al (2012) demonstrated that the filter with nearly equal frequency response for mid-high frequencies is more efficient than that with an incremental response in increasing narrowband (up to 4 kHz) intelligibility for listeners, especially in more severe conditions.…”

“…However, there is some evidence revealing that severely attenuating frequencies where pitch and harmonic information exist may lead to poor perceptual speech quality in quiet (Gabrielsson et al, 1988). This might explain the finding of Jokinen et al (2012) that post-filtering with a frequency response which has smooth transition between low and mid frequencies leads to better naturalness of the processed speech than when the filter has a steep cut-off.…”

“…Thus, when deploying speech modification techniques in practice, it may be worthwhile performing SNR estimation online (e.g. Jokinen et al, 2012), in order to determine the threshold for modification (de)activation in respect to speech quality.…”

Exploring the feasibility of smart phone microphone for measurement of acoustic voice parameters and voice pathology screening

“…Several earlier studies showed that the performance of speech and speaker recognition systems decreased when processing telephone-quality signals comparing to systems utilizing high-quality recordings [8]. However, more recent studies highlighted the real possibility for cost-effective remote detection and assessment of voice pathology over telephone channels reaching normal/pathological voice classification accuracy close to 90 % [6,[9][10][11].…”