This paper presents recent developments at our site toward speech recognition using decision tree based acoustic models. Previously, robust decision trees have been shown to achieve better performance compared to standard Gaussian mixture model (GMM) acoustic models. This was achieved by converting hard questions (decisions) of a standard tree into soft questions using sigmoid function. In this paper, we report our work where soft-decision trees are trained from scratch. These soft-decision trees are shown to yield better speech recognition accuracy compared to standard GMM acoustic models on Aurora digit recognition task.
Bibliographic reference. Ajmera, Jitendra / Akamine, Masami (2008): "Speech recognition using soft decision trees", In INTERSPEECH-2008, 940-943.