Universal phone recognition with a multilingual allophone system

X Li, S Dalmia, J Li, M Lee, P Littell… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
Multilingual models can improve language processing, particularly for low resource
situations, by sharing parameters across languages. Multilingual acoustic models, however …

Efficient few-shot machine learning for classification of EBSD patterns

K Kaufmann, H Lane, X Liu, KS Vecchio - Scientific reports, 2021 - nature.com
Deep learning is quickly becoming a standard approach to solving a range of materials
science objectives, particularly in the field of computer vision. However, labeled datasets …

Ultrasound speckle reduction using wavelet-based generative adversarial network

HG Khor, G Ning, X Zhang… - IEEE Journal of Biomedical …, 2022 - ieeexplore.ieee.org
The visual quality of ultrasound (US) images is crucial for clinical diagnosis and treatment.
The main source of image quality degradation is the inherent speckle noise generated …

Spatiotemporal fusion network for land surface temperature based on a conditional variational autoencoder

Y Chen, Y Yang, X Pan, X Meng… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
High spatiotemporal resolution land surface temperature (LST) data are essential for
dynamic monitoring and prediction in climate change research. Due to the limitations of …

Challenges and Opportunities for the Web 3.0 Metaverse Turn in Education

S Fan, B Yecies, ZI Zhou, J Shen - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The metaverse, along with its various Web 3.0 sub-domains, represents a ground-breaking
extension of the physical and digital worlds. In this emerging landscape, real and virtual …

Infant cry classification with graph convolutional networks

J Chunyan, M Chen, L Bin, Y Pan - 2021 IEEE 6th International …, 2021 - ieeexplore.ieee.org
We propose an approach of graph convolutional networks for robust infant cry classification.
We construct non-fully connected graphs with weighted edges based on the similarities …

Phase mapping in EBSD using convolutional neural networks

K Kaufmann, C Zhu, AS Rosengarten… - Microscopy and …, 2020 - academic.oup.com
The emergence of commercial electron backscatter diffraction (EBSD) equipment ushered in
an era of information rich maps produced by determining the orientation of user-selected …

[PDF][PDF] Hierarchical Phone Recognition with Compositional Phonetics.

X Li, J Li, F Metze, AW Black - Interspeech, 2021 - isca-archive.org
There is growing interest in building phone recognition systems for low-resource languages
as the majority of languages do not have any writing systems. Phone recognition systems …

The effect of task and training on intermediate representations in convolutional neural networks revealed with modified RV similarity analysis

JAF Thompson, Y Bengio, M Schönwiesner - arXiv preprint arXiv …, 2019 - arxiv.org
Centered Kernel Alignment (CKA) was recently proposed as a similarity metric for
comparing activation patterns in deep networks. Here we experiment with the modified RV …

End-to-End speech recognition models for a low-resourced Indonesian Language

S Suyanto, A Arifianto, A Sirwan… - 2020 8th International …, 2020 - ieeexplore.ieee.org
Recent automatic speech recognition (ASR) is commonly developed using deep learning
(DL), instead of the Hidden Markov Model (HMM). Many researchers show that DL is much …