4 accepted papers
Multimodal learning is of continued interest in artificial intelligence-based applications, motivated by the potential information gain from combining different types of data. However, modalities observed in the source environment may differ from the modalities observed in the target environment due…
Electrocardiograms (ECGs) are a non-invasive measurement used to observe the condition of the heart. Modern wearable devices can record ECGs, but typically provide fewer leads–signal outputs from electrodes–than the 12 in standard electrocardiograms. Consequently, data generated from these devices m…
We propose an adapter based multi-domain Transformer based language model (LM) for Transformer ASR. The model consists of a big size common LM and small size adapters. The model can perform multi-domain adaptation with only the small size adapters and its related layers. The proposed model can reuse…
Most automatic speech recognition (ASR) neural network models are not suitable for mobile devices due to their large model sizes. Therefore, it is required to reduce the model size to meet the limited hardware resources. In this study, we investigate sequence-level knowledge distillation techniques…