Results 91 to 100 of about 45,674 (282)

Under-Represented Speech Dataset from Open Data: Case Study on the Romanian Language

Applied Sciences
This paper introduces the USPDATRO dataset. This is a speech dataset, in the Romanian language, constructed from open data, focusing on under-represented voice types (children, young and old people, and female voices).
Vasile Păiș, Verginica Barbu Mititelu, Elena Irimia, Radu Ion, Dan Tufiș   +4 more
doaj   +1 more source

A Factoid Question Answering System for Vietnamese

, 2018
In this paper, we describe the development of an end-to-end factoid question answering system for the Vietnamese language. This system combines both statistical models and ontology-based methods in a chain of processing modules to provide high-quality ...
Bui, Duc-Thien, Le-Hong, Phuong
core   +1 more source

Remote Monitoring in Myasthenia Gravis: Exploring Symptom Variability

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Background Myasthenia gravis (MG) is a rare, autoimmune disorder characterized by fluctuating muscle weakness and potential life‐threatening crises. While continuous specialized care is essential, access barriers often delay timely interventions. To address this, we developed MyaLink, a telemedical platform for MG patients.
Maike Stein, Maximilian Mönch, Meret Herdick, Frauke Stascheit, Sarah Hoffmann, Hannah Preßler, Philipp Mergenthaler, Carla Dusemund, Paolo Doksani, Haoqi Sun, Pushpa Narayanaswami, Andreas Meisel, Lea Gerischer, Sophie Lehnerer   +13 more
wiley   +1 more source

Multimodal Multisource Neural Machine Translation: Building Resources for Image Caption Translation from European Languages into Arabic

Computation
Neural machine translation (NMT) models combining textual and visual inputs generate more accurate translations compared with unimodal models. Moreover, translation models with an under-resourced target language benefit from multisource inputs (source ...
Roweida Mohammed, Inad Aljarrah, Mahmoud Al-Ayyoub, Ali Fadel   +3 more
doaj   +1 more source

Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model

, 2018
Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages.
Bourlard, Hervé, Garner, Philip N., Tong, Sibo   +2 more
core  

Brainstem and Cerebellar Volume Loss and Associated Clinical Features in Progressive Supranuclear Palsy

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Introduction Progressive Supranuclear Palsy (PSP) is a neurodegenerative ‘tauopathy’ with predominating pathology in the basal ganglia and midbrain. Caudal tau spread frequently implicates the cerebellum; however, the pattern of atrophy remains equivocal.
Chloe Spiegel, Timothy P. Siejka, Cassandra Marotta, Josh J. Y. Lee, Kelly Bertram, Terence J. O'Brien, Meng Law, Lucy Vivash, Ian H. Harding   +8 more
wiley   +1 more source

Automatic Documentation of Faetar’s [i]: A Methodology for Discovering Vowel Space Using Artificial Neural Networks

Géolinguistique, 2018
Consider a huge, untagged speech corpus from a language without a written tradition. How can we quickly and accurately measure vowel space, without expending large amounts of labour and funds?
Lyndon Rey, Naomi Nagy
doaj   +1 more source

Collecting Resources in Sub-Saharan African Languages for Automatic Speech Recognition: a Case Study of Wolof

, 2016
International audienceThis article presents the data collected and ASR systems developped for 4 sub-saharan african languages (Swahili, Hausa, Amharic and Wolof). To illustrate our methodology, the focus is made on Wolof (a very under-resourced language)
Besacier, Laurent, Elingui, Uriel Pascal, Gauthier, Elodie, Melese, Michael, Voisin, Sylvie   +4 more
core   +1 more source

TermEval: an automatic metric for evaluating terminology translation in MT [PDF]

, 2019
Terminology translation plays a crucial role in domain-specific machine translation (MT). Preservation of domain-knowledge from source to target is arguably the most concerning factor for the customers in translation industry, especially for critical ...
Haque, Rejwanul, Hasanuzzaman, Mohammed, Way, Andy   +2 more
core  

Tied Multitask Learning for Neural Speech Translation

, 2018
We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task, since higher-level
Anastasopoulos, Antonios, Chiang, David
core   +1 more source