Associating gamma-ray sources to their low-energy counterparts is one of the major challenges of modern gamma-ray astronomy. In the context of the Fourth Fermi Large Area Telescope Source Catalog (4FGL), the associations rely mainly on parameters as apparent magnitude, integrated flux, and angular separation between the gamma-ray source and its low-energy candidate counterpart. In this work we propose a new use of likelihood ratio and a complementary supervised learning technique to associate gamma-ray blazars in 4FGL, based only on spectral parameters as gamma-ray photon index, mid-infrared colors and radio-loudness. In the likelihood ratio approach, we crossmatch the WISE Blazar-Like Radio-Loud Sources catalog with 4FGL and compare the resulting candidate counterparts with the sources listed in the gamma-ray blazar locus to compute an association probability for 1138 counterparts. In the supervised learning approach, we train a random forest algorithm with 869 high confidence blazar associations and 711 fake associations, and then compute an association probability for 1311 candidate counterparts. A list with all 4FGL blazar candidates of uncertain type associated by our method is provided to guide future optical spectroscopic follow up observations.