Estimation model for the speech-quality dimension “Noisiness.”

Abstract

State-of-the-art assessment method of speech-transmission quality (e.g., PESQ or TOSQA) predict the mean-opinion score (MOS) quite accurately, but cannot provide diagnostic information, which is, however, highly desirable for system developers. In our research project, we aim at the development of an attribute-based speech-quality measure, which provides estimates of different attributes of speech samples and then maps them to one integral-quality estimate. Three dominant, mutually orthogonal perceptual dimensions were firstly identified by auditory experiments and multidimensional analysis (MDA) for narrow-band speech transmission: “directness/ frequency content,” “continuity,” and “noisiness.” The present paper focuses on the further decomposition and measurement of the global dimension “Noisiness.” Therefore, an auditory test including samples degraded by different kinds of noises has been conducted. The subsequent MDA indicates that at least two sub-dimensions (SD), “Speech Contamination” and (perceived) “Additive-Noise Level,” are further describing the global dimension “Noisiness.” The first SD characterizes the degree the noise distorts the speech signal as such, whereas the second SD reflects the degree the additive circuit or background noise itself annoys the listener. The instrumental estimation methods for both SDs and the mapping to the integral-quality ratings are presented in this paper.

Assessment of speech quality degradation indicators for “continuity” dimension in super wideband telephony context

“…Additive Artifacts sub-dimension (i) The "r A " indicator found in [3] quantifies the rate of perceived artifacts using the artifact estimator developed in [8]. This estimator uses a Weighted Spectral Slope (WSS) algorithm to detect distortions in the interpolated frames, mostly due to PLC techniques.…”

“…The sub-dimensions of the "Continuity" dimension we used in what follows have been determined (see [8]) in a purely narrow-band context (but we believe that they apply also on larger audio bandwidths) from auditory test results on speech samples degraded by different levels of packet/frame loss, front-end clipping or musical noise. These sub-dimensions are:…”

On the identification of relevant degradation indicators in super wideband listening quality assessment models

“…In this section, we first report how we identified and/or estimated these QDIs in POLQA and compared them with the corresponding explicit indicators found in DIAL, for the four perceptual dimensions mentioned above. Furthermore, recent studies [18][19][20] have…”

Diagnostic Instrumental Speech Quality Assessment in a Super-Wideband Context

“…This set is composed of a DFC estimator developed by Scholz and Heute [15] and a Continuity estimator developed by Huo [16], both extended to S-WB transmissions. Two new estimators have been developed for the dimensions Noisiness and Loudness.…”

“…including continuous variable delay. The estimator for the dimension Continuity has been developed by [16]. This estimator detects the discontinuities in the speech signal using Weighted Spectral Slope (WSS) distances [18] and the system gain variation (∆ gain).…”