Passive acoustic monitoring can be an effective way of monitoring wildlife populations that are acoustically active but difficult to survey visually, but identifying target species calls in recordings is non-trivial. Machine learning (ML) techniques can do detection quickly but may miss calls and produce false positives, i.e., misidentify calls from other sources as being from the target species. While abundance estimation methods can address the former issue effectively, methods to deal with false positives are under-investigated. We propose an acoustic spatial capture-recapture (ASCR) method that deals with false positives by treating species identity as a latent variable. Individual-level outputs from ML techniques are treated as random variables whose distributions depend on the latent identity. This gives rise to a mixture model likelihood that we maximize to estimate call density. We compare our method to existing methods by applying it to an ASCR survey of frogs and simulated acoustic surveys of gibbons based on real gibbon acoustic data. Estimates from our method are closer to ASCR applied to the dataset without false positives than those from a widely used false positive "correction factor" method. Simulations show our method to have bias close to zero and accurate coverage probabilities and to perform substantially better than ASCR without accounting for false positives.
