Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Ghorbani, Shahram"'
Autor:
Ghorbani, Shahram, Hansen, John H. L.
Accurately classifying accents and assessing accentedness in non-native speakers are both challenging tasks due to the complexity and diversity of accent and dialect variations. In this study, embeddings from advanced pre-trained language identificat
Externí odkaz:
http://arxiv.org/abs/2310.11004
In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text representations ex
Externí odkaz:
http://arxiv.org/abs/2011.04084
The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder network with ski
Externí odkaz:
http://arxiv.org/abs/2007.09131
Autor:
Yu, Jianwei, Zhang, Shi-Xiong, Wu, Jian, Ghorbani, Shahram, Wu, Bo, Kang, Shiyin, Liu, Shansong, Liu, Xunying, Meng, Helen, Yu, Dong
Automatic recognition of overlapped speech remains a highly challenging task to date. Motivated by the bimodal nature of human speech perception, this paper investigates the use of audio-visual technologies for overlapped speech recognition. Three is
Externí odkaz:
http://arxiv.org/abs/2001.01656
Training acoustic models with sequentially incoming data -- while both leveraging new data and avoiding the forgetting effect-- is an essential obstacle to achieving human intelligence level in speech recognition. An obvious approach to leverage data
Externí odkaz:
http://arxiv.org/abs/1910.00565
Autor:
Ghorbani, Shahram, Hansen, John H. L.
Recognition of accented speech is a long-standing challenge for automatic speech recognition (ASR) systems, given the increasing worldwide population of bi-lingual speakers with English as their second language. If we consider foreign-accented speech
Externí odkaz:
http://arxiv.org/abs/1904.09038
Non-native speech causes automatic speech recognition systems to degrade in performance. Past strategies to address this challenge have considered model adaptation, accent classification with a model selection, alternate pronunciation lexicon, etc. I
Externí odkaz:
http://arxiv.org/abs/1809.06833
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.