Social background profiling of speakers refers to estimating the geographical origin by their speech features. Methods for accent that use linguistic features, require phoneme alignment and transcription samples. This paper proposes a purely acoustic model, composed multiple convolutional networks with global average-pooling layers, classify temporal sequence The bottleneck representations netw...

Abstract Social participation is an important factor for students’ socio-emotional/academic development. The literature on the topic discusses four domains in this regard: friendships, interactions, social acceptance, and self-perception of inclusion. It shows that marginalized groups (e.g., students with behavioral problems/learning deficiencies/physical disabilities) are experience difficulti...

Recommender systems nowadays are commonly deployed in e-commerce platforms to help customers making purchase decisions. Dynamic recommender considers not only static user-item interaction data, but the temporal information at time of recommendation. Previous researches have suggested incorporate social media as dynamic neural recommenders after transforming them into embeddings. While such an a...