Computational auditory models in predicting noise reduction performance for wideband telephony applications

The performance of several noise reduction algorithms intended for wideband telephony was evaluated both subjectively and objectively. The chosen algorithms were based on statistical modeling, spectral subtraction, Wiener filtering, or subspace modelling principles. A customized wideband noise reduction database containing speech samples corrupted by three types of background noises at three SNR levels, along with their enhanced versions was created. The overall quality of the speech samples in the database was subsequently rated by a group of listeners with normal hearing capabilities. Comprehensive statistical analyses were performed to assess the reliability of the subjective data, and to assess the performance of noise reduction algorithms across varied noisy conditions. The subjective quality ratings were then used to investigate the performance of several auditory model-based objective quality metrics. Key results from these investigations include: (a) there was a high degree of inter- and intra-subject reliability in the subjective ratings, (b) noise reduction algorithms enhance speech quality for only a subset of the noise conditions, and (c) auditory model-based metrics perform similarly in predicting speech quality ratings, when speech quality scores pertaining to a particular noise condition were averaged.