Tomoya Yoshinaga, Keitaro Tanaka, Yoshiaki Bando, Keisuke Imoto, and Shigeo Morishima

The overview of the proposed frame-to-event mapping. \( \mathbf{x}_t \) and \( z_t \) denote the input acoustic feature and sound event activity, respectively.

The overview of the proposed frame-to-event mapping. \( \mathbf{x}_t \) and \( z_t \) denote the input acoustic feature and sound event activity, respectively.

Abstract: This paper presents a sound event detection (SED) method that handles sound event boundaries in a statistically principled manner. A typical approach to SED is to train a deep neural network (DNN) in a supervised manner such that the model predicts frame-wise event activities. Since the predicted activities often contain fine insertion and deletion errors due to their temporal fluctuations, post-processing has been applied to obtain more accurate onset and offset boundaries. Existing postprocessing methods are, however, non-differentiable and prohibit end-to-end (E2E) training. In this paper, we propose an E2E detection method based on a probabilistic formulation of sound event sequences called a hidden semi-Markov model (HSMM). The HSMM is utilized to transform frame-wise features predicted by a DNN into posterior probabilities of sound events represented by their class labels and temporal boundaries. We jointly train the DNN and HSMM in a supervised E2E manner by maximizing the event-wise posterior probabilities of the HSMM. This objective is a differentiable function thanks to the forward-backward algorithm of the HSMM. Experimental results with real recordings show that our method outperforms baseline systems with standard post-processing methods.

Source code: We will release the source code soon.