Results 21 to 30 of about 351,465 (318)
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 +4 more
doaj +1 more source
A Study of Speech Recognition for Kazakh Based on Unsupervised Pre-Training
Sensors, 2023 Building a good speech recognition system usually requires a lot of pairing data, which poses a big challenge for low-resource languages, such as Kazakh.
Weijing Meng, Nurmemet Yolwas
doaj +1 more source
JSUM: A Multitask Learning Speech Recognition Model for Jointly Supervised and Unsupervised Learning
Applied Sciences, 2023 In recent years, the end-to-end speech recognition model has emerged as a popular alternative to the traditional Deep Neural Network—Hidden Markov Model (DNN-HMM).
Nurmemet Yolwas, Weijing Meng
doaj +1 more source
Pairwise networks for feature ranking of a geomagnetic storm model
South African Computer Journal, 2020 Feedforward neural networks provide the basis for complex regression models that produce accurate predictions in a variety of applications. However, they generally do not explicitly provide any information about the utility of each of the input ...
Jacques Beukes +2 more
doaj +1 more source
Enduring musician advantage among former musicians in prosodic pitch perception
Scientific Reports, 2023 Musical training has been associated with various cognitive benefits, one of which is enhanced speech perception. However, most findings have been based on musicians taking part in ongoing music lessons and practice.
Xin Ru Toh +4 more
doaj +1 more source
Ethnicity and Tone Production on Singlish Particles
Languages, 2022 Recent research on Singlish, also known as Colloquial Singapore English, suggests that it is subject to ethnic variation across the three major ethnic groups in Singapore, namely Chinese, Malay, and Indian. Discourse particles, said to be one of the most
Ying Qi Soh, Junwen Lee, Ying-Ying Tan
doaj +1 more source
IEEE Access, 2023 In recent years, with the development of deep learning, research on end-to-end mispronunciation detection and diagnosis(MDD) methods has been further promoted.
Shen Guo +4 more
doaj +1 more source
Benign interpolation of noise in deep learning
South African Computer Journal, 2020 The understanding of generalisation in machine learning is in a state of flux, in part due to the ability of deep learning models to interpolate noisy training data and still perform appropriately on out-of-sample data, thereby contradicting long-held ...
Marthinus Wilhelmus Theunissen +2 more
doaj +1 more source
Massively Multilingual Lexical Specialization of Multilingual Transformers
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023 Accepted in ACL ...
Green, Tommaso +2 more
openaire +3 more sources
Dublin City University at CLEF 2004: experiments in monolingual, bilingual and multilingual retrieval [PDF]
, 2005 The Dublin City University group participated in the monolingual, bilingual and multilingual retrieval tasks this year. The main focus of our investigation this year was extending our retrieval system to document languages other than English, and ...
Burke, Michael +5 more
core +1 more source