The problem of detecting the number of speakers for a particular segment occurs in many dif-ferent speech applications. In single channel speech separation, for example, this information isoften used to simplify the separation process, as the signal has to be treated differently dependingon the number of speakers. Inspired by the asymptotic maximum a posteriori rule proposed formodel selection, we pose the problem as a model selection problem. More specifically, we derivea multiple hypotheses test for determining the number of speakers at a frame level in an observedsignal based on underlying parametric speaker models, trained a priori. The experimental resultsindicate that the suggested method improves the quality of the separated signals in a single-channelspeech separation scenario at different signal-to-signal ratio levels.
展开▼
