Zobrazeno 1 - 10
of 78
pro vyhledávání: '"Raymond W. M. Ng"'
Autor:
Sheung-Ching Chow, Yang Zhang, Raymond W. M. Ng, Shu-Yuen Ron Hui, Ilia A. Solov’yov, Wing-Yee Lui
Publikováno v:
Frontiers in Public Health, Vol 12 (2024)
The influence of weak radio-frequency electromagnetic field (RF-EMF) on living organisms raises new concern because of the Industrial, Scientific, and Medical (ISM) frequency band at 6.78 MHz being promoted by the AirFuel Alliance for mid-range wirel
Externí odkaz:
https://doaj.org/article/47bebdff239f4b178684280948a79463
Publikováno v:
ACC
The study of underactuated robotics, especially with hardware implementation, has received more and more attention recently. Many existing underactuated robotic systems were often built with complicated structures and algorithms that prohibit learner
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ff7316aabd79e831fec6c0bd0b6d0297
https://doi.org/10.23919/acc50511.2021.9482939
https://doi.org/10.23919/acc50511.2021.9482939
Publikováno v:
ASRU
For speech emotion datasets, it has been difficult to acquire large quantities of reliable data and acted emotions may be over the top compared to less expressive emotions displayed in everyday life. Lately, larger datasets with natural emotions have
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::54eeb76c7b36f822bf832989dbc1c92f
https://doi.org/10.1109/asru46091.2019.9003838
https://doi.org/10.1109/asru46091.2019.9003838
Autor:
Madina Hasan, Oscar Saz, Thomas Hain, Salil Deena, Rosanna Milner, Mortaza Doulaty, Julia Olcoz, Bilal Khaliq, Raymond W. M. Ng
Publikováno v:
Multimedia Tools and Applications. 77:30533-30550
This paper describes a system for performing alignment of subtitles to audio on multigenre broadcasts using a lightly supervised approach. Accurate alignment of subtitles plays a substantial role in the daily work of media companies and currently sti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::77180e6d71ed8e86dc0712de23d221c3
https://doi.org/10.1007/s11042-018-6050-1
https://doi.org/10.1007/s11042-018-6050-1
Publikováno v:
Computer Speech & Language. 46:327-342
Phone tokenisers are used in spoken language recognition (SLR) to obtain elementary\ud phonetic information. We present a study on the use of deep neural\ud network tokenisers. Unsupervised crosslingual adaptation was performed to\ud adapt the baseli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::296a558031f9e443a37f18c8befed9a6
https://doi.org/10.1016/j.csl.2017.05.002
https://doi.org/10.1016/j.csl.2017.05.002
Publikováno v:
ICASSP
This paper studies Acoustic Event Detection (AED) systems and the problem of their rapid and easy customisation to arbitrary deployment scenarios. Due to inherent challenges related to annotation processes of AED data (time-consuming and error-prone
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d45b57584b8cc58fbcf0e61ac43f6a9
https://doi.org/10.1109/icassp.2019.8683048
https://doi.org/10.1109/icassp.2019.8683048
Publikováno v:
SLT
This paper investigates text-independent speaker recognition using neural embedding extractors based on the time-delay neural network. Our primary focus is to explore the teacher-student (TS) training framework for knowledge distillation in a text-in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d795dfad6d84977b43e6793f8ff22966
https://doi.org/10.1109/slt.2018.8639564
https://doi.org/10.1109/slt.2018.8639564
Publikováno v:
ASRU
Neural Machine Translation (NMT) has recently demonstrated improved performance over statistical machine translation and relies on an encoder-decoder framework for translating text from source to target. The structure of NMT makes it amenable to add
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b9746ca07170a8f0fc2cb1741504fcf3
https://doi.org/10.1109/asru.2017.8268971
https://doi.org/10.1109/asru.2017.8268971
Publikováno v:
INTERSPEECH
Recurrent neural network language models (RNNLMs) can be augmented with auxiliary features, which can provide an extra modality on top of the words. It has been found that RNNLMs perform best when trained on a large corpus of generic text and then fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af343af5c6b7ace76dd9ef89730cdc47
https://doi.org/10.21437/interspeech.2017-1598
https://doi.org/10.21437/interspeech.2017-1598
Publikováno v:
IWSSIP
In active learning for Automatic Speech Recognition (ASR), a portion of data is automatically selected for manual transcription. The objective is to improve ASR performance with retrained acoustic models. The standard approaches are based on confiden
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3695e2e1164bf994ab8de2de5c6add1f
https://doi.org/10.1109/iwssip.2017.7965609
https://doi.org/10.1109/iwssip.2017.7965609