The Speech Emotion Recognition Adaptation Benchmark (SERAB) is a new framework to evaluate the performance and generalization capacity of different approaches for utterance-level SER. The benchmark is composed of nine datasets for SER in six languages. We used the proposed framework to evaluate a selection of standard hand-crafted feature sets and state-of-the-art DNN representations. The results highlight that using only a subset of the data included in SERAB can result in biased evaluation, while compliance with the proposed protocol can circumvent this issue.
As an essential task for natural language understanding, slot filling aims to identify the contiguous spans of specific slots in an utterance. In real-world applications, the labeling costs of utterances may be expensive, and transfer learning techniques have been developed to ease this problem. However, cross-domain slot filling could significantly suffer from negative transfer due to non-targeted or zero-shot slots.
Using the shared-private paradigm and adversarial training
can significantly improve the performance of multi-domain
text classification (MDTC) models. However, there are two
issues for the existing methods: First, instances from the multiple
domains are not sufficient for domain-invariant feature
extraction. Second, aligning on the marginal distributions
may lead to a fatal mismatch. In this paper, we propose mixup
regularized adversarial networks (MRANs) to address these
two issues. More specifically, the domain and category mixup