Results 1 to 10 of about 11,850,628 (306)

Improving Hybrid CTC/Attention Architecture for Agglutinative Language Speech Recognition

Sensors, 2022
Unlike the traditional model, the end-to-end (E2E) ASR model does not require speech information such as a pronunciation dictionary, and its system is built through a single neural network and obtains performance comparable to that of traditional methods.
Zeyu Ren, Nurmemet Yolwas, Wushour Slamu, Ronghe Cao, Huiru Wang   +4 more
doaj   +1 more source

Framework to assess eco-efficiency improvement: Case study of a meat production industry

Energy Reports, 2021
The industry sector accounts for nearly a quarter of the total global final energy and heat makes up two-thirds of that parcel. Sectors such as food & drinks, steel, cement, ceramic and glass, among others represent a considerable part of the energy ...
Muriel Iten, Ulisses Fernandes, Miguel Castro Oliveira   +2 more
doaj   +1 more source

Effect of supervised home-based training on functional outcome in severe exercise intolerance in post-COVID syndrome

Indian Journal of Respiratory Care, 2021
Globally, millions of people have been impacted with COVID-19. A fraction of these people develop severe respiratory distress and require prolonged intensive care unit stay.
Shraddha Shah
doaj   +1 more source

AB-LaBSE: Uyghur Sentiment Analysis via the Pre-Training Model with BiLSTM

Applied Sciences, 2022
In recent years, more and more attention has been paid to text sentiment analysis, which has gradually become a research hotspot in information extraction, data mining, Natural Language Processing (NLP), and other fields.
Yijie Pei, Siqi Chen, Zunwang Ke, Wushour Silamu, Qinglang Guo   +4 more
doaj   +1 more source

Named Entity Recognition for Nepali: Data Sets and Algorithms

Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022
Named Entity Recognition (NER) task involves locating Named Entities (NEs) in free text and classifying them into predefined categories such as Person Name, Location and Organization.
Nobal Niraula, Jeevan Chapagain
doaj   +1 more source

Regulation of Interface Compatibility and Performance in Soft Magnetic Composites with Inorganic Insulation Layers by FePO₄ Intermediate Transition Layer

Molecules
In the fabrication of soft magnetic composites, the lattice mismatch between the inorganic insulation layer and the iron matrix often leads to the formation of cracks during the molding process, which significantly impairs the operational performance of ...
Sanao Huang, Junjie Ma, Yang Liu, Hao He, Peisheng Lyu, Huaqin Huang, Bing Dai   +6 more
doaj   +1 more source

Improving Aphasic Speech Recognition by Using Novel Semi-Supervised Learning Methods on AphasiaBank for English and Spanish

Applied Sciences, 2021
Automatic speech recognition in patients with aphasia is a challenging task for which studies have been published in a few languages. Reasonably, the systems reported in the literature within this field show significantly lower performance than those ...
Iván G. Torre, Mónica Romero, Aitor Álvarez   +2 more
doaj   +1 more source

Hierarchical Transfer Learning for Multilingual, Multi-Speaker, and Style Transfer DNN-Based TTS on Low-Resource Languages

IEEE Access, 2020
This work applies a hierarchical transfer learning to implement deep neural network (DNN)-based multilingual text-to-speech (TTS) for low-resource languages. DNN-based system typically requires a large amount of training data.
Kurniawati Azizah, Mirna Adriani, Wisnu Jatmiko   +2 more
doaj   +1 more source

Effects of Continuous Rolling and Reversible Rolling on 2.4% Si Non-Oriented Silicon Steel

Crystals
The cold-rolled non-oriented silicon steel sheets with a Si content of 2.4 wt.%, produced by continuous and reversible cold rolling, were used as the experimental material. The effects of annealing temperature on the microstructure, texture, and magnetic
Kaixuan Shao, Yuhao Niu, Yinghao Pei, Jialong Qiao, Hongbo Pan, Haijun Wang   +5 more
doaj   +1 more source

Transfer Learning, Style Control, and Speaker Reconstruction Loss for Zero-Shot Multilingual Multi-Speaker Text-to-Speech on Low-Resource Languages

IEEE Access, 2022
Deep neural network (DNN)-based systems generally require large amounts of training data, so they have data scarcity problems in low-resource languages.
Kurniawati Azizah, Wisnu Jatmiko
doaj   +1 more source