The spatial acoustic information of a scene, i.e., how sounds emitted from a particular location in the scene are perceived in another location, is key for immersive scene modeling. Robust representation of scene's acoustics can be formulated through a continuous field formulation along with impulse responses varied by emitter-listener locations. The impulse responses are then used to render sounds perceived by the listener. While such representation is advantageous, parameterization of impulse responses for generic scenes presents itself as a challenge. Indeed, traditional pre-computation methods have only implemented parameterization at discrete probe points and require large storage, while other existing methods such as geometry-based sound simulations still suffer from inability to simulate all wave-based sound effects. In this work, we introduce a novel neural network for light-weight Implicit Neural Representation for Audio Scenes (INRAS), which can render a high fidelity time-domain impulse responses at any arbitrary emitter-listener positions by learning a continuous implicit function. INRAS disentangles scene's geometry features with three modules to generate independent features for the emitter, the geometry of the scene, and the listener respectively. These lead to an efficient reuse of scene-dependent features and support effective multi-condition training for multiple scenes. Our experimental results show that INRAS outperforms existing approaches for representation and rendering of sounds for varying emitter-listener locations in all aspects, including the impulse response quality, inference speed, and storage requirements.

In this paper, we present an acoustic scene classification framework based on a large-margin factorized convolutional neural network (CNN). We adopt the factorized CNN to learn the patterns in the time-frequency domain by factorizing the 2D kernel into two separate 1D kernels. The factorized kernel leads to learn the main component of two patterns: the long-term ambient and short-term event sounds which are the key patterns of the audio scene classification. In training our model, we consider the loss function based on the triplet sampling such that the same audio scene samples from different environments are minimized, and simultaneously the different audio scene samples are maximized. With this loss function, the samples from the same audio scene are clustered independently of the environment, and thus we can get the classifier with better generalization ability in an unseen environment. We evaluated our audio scene classification framework using the dataset of the DCASE challenge 2019 task1A. Experimental results show that the proposed algorithm improves the performance of the baseline network and reduces the number of parameters to one third. Furthermore, the performance gain is higher on unseen data, and it shows that the proposed algorithm has better generalization ability.