Improving the Performance of Far-Field Speaker Verification Using Multi-Condition Training: The Case of GMM-UBM and i-vector Systems

While considerable work has been done to characterize the detrimental effects of channel variability on automatic speaker verification (ASV) performance, little attention has been paid to the effects of room reverberation. This paper investigates the effects of room acoustics on the performance of two far-field ASV systems: GMM-UBM (Gaussian mixture model- univer-sal background model) and i-vector. We show that ASV per-formance is severely affected by reverberation, particularly for i-vector based systems. Three multi-condition training meth-ods are then investigated to mitigate such detrimental effects. The first uses matched train/test speaker models based on esti-mated reverberation time (RT) values. The second utilizes two-condition training where clean and reverberant models are used. Lastly, a four-condition training setup is proposed where mod-els for clean, mild, moderate, and severe reverberation levels are used. Experimental results show the first and third multi-condition training methods providing significant gains in per-formance relative to the baseline, with the latter being more suitable for practical resource-constrained far-field applications. Index Terms: Automatic speaker verification, GMM-UBM, i-vector, far-field, reverberation time