Results 11 to 20 of about 132,661 (296)
Applied Sciences, 2021 Vowel reduction is a common pronunciation phenomenon in stress-timed languages like English. Native speakers tend to weaken unstressed vowels into a schwa-like sound.
Zongming Liu +3 more
doaj +1 more source
IEEE Access, 2019 Nowadays, most end-to-end task-oriented dialog systems are based on sequence-to-sequence (Seq2seq), which is an encoder-decoder framework. These systems sometimes produce grammatically correct, but logically incorrect responses.
Junqing He +4 more
doaj +1 more source
GuidedMix: An on‐the‐fly data augmentation approach for robust speaker recognition system
Electronics Letters, 2022 Data augmentation is an essential technique for building a high‐robustness speaker recognition system. this letter proposes a novel on‐the‐fly data augmentation strategy called GuidedMix.
Runqiu Xiao +4 more
doaj +1 more source
Restricted Boltzmann Machine-Based Approaches for Link Prediction in Dynamic Networks
IEEE Access, 2018 Link prediction in dynamic networks aims to predict edges according to historical linkage status. It is inherently difficult because of the linear/non-linear transformation of underlying structures.
Taisong Li +4 more
doaj +1 more source
AUTOMATIC MUSIC TRANSCRIPTION USING ROW WEIGHTED DECOMPOSITIONS [PDF]
, 2013 (c) 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or ...
IEEE, O'Hanlon, K, Plumbley, MD
core +1 more source
Parallel global convolutional network for semantic image segmentation
IET Image Processing, 2021 In this paper, a novel convolutional neural network for fast semantic segmentation is presented. Deep convolutional neural networks have achieved great progress in the task of vision scene understanding.
Xing Bai, Jun Zhou
doaj +1 more source
A Complementary Effect in Active Control of Powertrain and Road Noise in the Vehicle Interior
IEEE Access, 2022 This study shows that a concurrent active noise control strategy for engine harmonics and road noise has a complementary effect. In particular, we found that engine booming noise is additionally attenuated when road noise control is concurrently used ...
Seonghyeon Kim, M. Ercan Altinsoy
doaj +1 more source
Acoustic voice variation in spontaneous speech
The Journal of the Acoustical Society of America, 2022 This study replicates and extends the recent findings of Lee, Keating, and Kreiman [J. Acoust. Soc. Am. 146(3), 1568–1579 (2019)] on acoustic voice variation in read speech, which showed remarkably similar acoustic voice spaces for groups of female and male talkers and the individual talkers within these groups. Principal component analysis was applied
Yoonjeong Lee, Jody Kreiman
openaire +4 more sources
Applying deep matching networks to Chinese medical question answering: a study and a dataset
BMC Medical Informatics and Decision Making, 2019 Background Medical and clinical question answering (QA) is highly concerned by researchers recently. Though there are remarkable advances in this field, the development in Chinese medical domain is relatively backward.
Junqing He, Mingming Fu, Manshu Tu
doaj +1 more source
Applied Sciences, 2019 As demonstrated in hybrid connectionist temporal classification (CTC)/Attention architecture, joint training with a CTC objective is very effective to solve the misalignment problem existing in the attention-based end-to-end automatic speech recognition (
Long Wu, Ta Li, Li Wang, Yonghong Yan
doaj +1 more source