[PDF][PDF] Semi-orthogonal low-rank matrix factorization for deep neural networks.
Abstract Time Delay Neural Networks (TDNNs), also known as onedimensional
Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural …
Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural …
[HTML][HTML] Combining machine learning and process engineering physics towards enhanced accuracy and explainability of data-driven models
T Bikmukhametov, J Jäschke - Computers & Chemical Engineering, 2020 - Elsevier
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 …
of the main reasons why they are still not widely used in operation of process engineering …
[PDF][PDF] Emotion Identification from Raw Speech Signals Using DNNs.
We investigate a number of Deep Neural Network (DNN) architectures for emotion
identification with the IEMOCAP database. First we compare different feature extraction …
identification with the IEMOCAP database. First we compare different feature extraction …
Low latency acoustic modeling using temporal convolution and LSTMs
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 …
error rate reduction compared to their unidirectional counterpart, as they model both the past …
The CAPIO 2017 conversational speech recognition system
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 …
industry-standard NIST 2000 Hub5 English evaluation set. We explore densely connected …
A teacher-student learning approach for unsupervised domain adaptation of sequence-trained asr models
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 …
used to “teach” a student network to make the same predictions as the teacher. Originally …
Pushing the boundaries of audiovisual word recognition using residual networks and LSTMs
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 …
due to the advent of deep learning methods. In this paper, we present a deep learning …
[HTML][HTML] Advances in subword-based HMM-DNN speech recognition across languages
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 …
systems based on weighted finite state transducers, hidden Markov models, and deep …
Automatic lyrics transcription using dilated convolutional neural networks with self-attention
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 …
systems are being used in many applications in the software industry, yet as by today, there …
Novel simulation of aqueous total nitrogen and phosphorus concentrations in Taihu Lake with machine learning
H Lu, L Yang, Y Fan, X Qian, T Liu - Environmental Research, 2022 - Elsevier
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 …
improve the performance of machine learning models in predicting the temporal variations of …