We present an enhanced method for the application of Gaussian mixture modeling (GMM) to the coherent WaveBurst (cWB) algorithm in the search for short-duration gravitational wave (GW) transients. The supervised machine learning method of GMM allows for the multidimensional distributions of noise and signal to be modeled over a set of representative attributes, which aids in the classification of GW signals against noise transients (glitches) in the data. We demonstrate that updating the approach to model construction eliminates bias previously seen in the GMM analysis, increasing the robustness and sensitivity of the analysis over a wider range of burst source populations. The enhanced methodology is applied to the generic burst all-sky short search in the LIGO-Virgo full third observing run (O3), marking the first application of GMM to the 3 detector Livingston-Hanford-Virgo network. For both 2- and 3- detector networks, we observe comparable sensitivities to an array of generic signal morphologies, with significant sensitivity improvements to waveforms in the low quality factor parameter space at false alarm rates of 1 per 100 years. This proves that GMM can effectively mitigate blip glitches, which are one of the most problematic sources of noise for unmodeled GW searches. The cWB-GMM search recovers similar numbers of compact binary coalescence (CBC) events as other cWB postproduction methods, and concludes on no new gravitational wave detection after known CBC events are removed.
