No abstract

No abstract

In this paper, feature extraction methods are developed based on the non-negative matrix factorization (NMF) algorithm to be applied in weakly supervised sound event detection. Recently, the development of various features and systems have been attempted to tackle the problems of acoustic scene classification and sound event detection. However, most of these systems use data-independent spectral features, e.g., Mel-spectrogram, log-Mel-spectrum, and gammatone filterbank. Some data-dependent feature extraction methods, including the NMF-based methods, recently demonstrated the potential to tackle the problems mentioned above for long-term acoustic signals. In this paper, we further develop the recently proposed NMF-based feature extraction method to enable its application in weakly supervised sound event detection. To achieve this goal, we develop a strategy for training the frequency basis matrix using a heterogeneous database consisting of strongly- and weakly-labeled data. Moreover, we develop a non-iterative version of the NMF-based feature extraction method so that the proposed feature extraction method can be applied as a part of the model structure similar to the modern “on-the-fly” transform method for the Mel-spectrogram. To detect the sound events, the temporal basis is calculated using the NMF method and then used as a feature for the mean-teacher-model-based classifier. The results are improved for the event-wise post-processing method. To evaluate the proposed system, simulations of the weakly supervised sound event detection were conducted using the Detection and Classification of Acoustic Scenes and Events 2020 Task 4 database. The results reveal that the proposed system has F1-score performance comparable with the Mel-spectrogram and gammatonegram and exhibits 3–5% better performance than the log-Mel-spectrum and constant-Q transform.

Augmented reality (AR) is a popular service in mobile devices, and many AR applications can be downloaded from app stores. As TV broadcasting has continued to integrate with the Internet, it has become an area in which the AR concept is able to reside, although in a simple form, such as an advertisement placed in the static region of a scene. There are some restrictions against TV broadcasting realizing AR since TVs are fixed devices and typically do not have GPS, geomagnetic, or acceleration sensors, which are standard equipment in mobile devices. However, the desire to experience AR on a large TV screen has triggered research and development for an ideal AR business model and service type. This paper introduces several use cases for augmented broadcasting services and also presents an augmented broadcasting metadata scheme designed for a broadcasting environment. We also verify some of the use cases and an augmented broadcasting metadata scheme in an implemented augmented broadcasting system based on a hybrid TV platform.

No abstract