Abstract Time Delay Neural Networks (TDNNs), also known as onedimensional
Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural …

Abstract Machine learning models are often considered as black-box solutions which is one
of the main reasons why they are still not widely used in operation of process engineering …

We investigate a number of Deep Neural Network (DNN) architectures for emotion
identification with the IEMOCAP database. First we compare different feature extraction …

Bidirectional long short-term memory (BLSTM) acoustic models provide a significant word
error rate reduction compared to their unidirectional counterpart, as they model both the past …

In this paper we show how we have achieved the state-of-the-art performance on the
industry-standard NIST 2000 Hub5 English evaluation set. We explore densely connected …

Teacher-student (TS) learning is a transfer learning approach, where a teacher network is
used to “teach” a student network to make the same predictions as the teacher. Originally …

Visual and audiovisual speech recognition are witnessing a renaissance which is largely
due to the advent of deep learning methods. In this paper, we present a deep learning …

We describe a novel way to implement subword language models in speech recognition
systems based on weighted finite state transducers, hidden Markov models, and deep …

Speech recognition is a well developed research field so that the current state of the art
systems are being used in many applications in the software industry, yet as by today, there …

This study demonstrates the utility of internal nutrient loads as an additional parameter to
improve the performance of machine learning models in predicting the temporal variations of …