Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Gales, MJF"'
The growing demand for learning English as a second language has increased interest in automatic approaches for assessing and improving spoken language proficiency. A significant challenge in this field is to provide interpretable scores and informat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f9e0037184b2967a78f16396cf17bd2
Autor:
Fathullah, Y, Gales, MJF
Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model’s prediction to ensure appropriate decisions are made by the system. Deep ensembles are the de-f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4748cc4e646d355046326c84d47d946a
Autor:
Manakul, P, Gales, MJF
Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the target ta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d56aff7d54e491ef7cf624bbd9bfd3c
A significant concern with deep learning based approaches is that they are difficult to interpret, which means detecting bias in network predictions can be challenging. Concept Activation Vectors (CAVs) have been proposed to address this problem. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f62c677932be1b42e2ac9d7e20cce843
In automatic speech recognition, performance gains can often be obtained by combining an ensemble of multiple models. However, this can be computationally expensive when performing recognition. Teacher-student learning alleviates this cost by trainin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95719021381e7018ccdee4be8cf54c65
Detecting individual pronunciation errors and diagnosing pronunciation error tendencies in a language learner based on their speech are important components of computer-aided language learning (CALL). The tasks of error detection and error tendency d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1dfa93c876cb2280df6f905ae2b86dc5
Deep learning has dramatically improved the performance of automated systems on a range of tasks including spoken language assessment. One of the issues with these deep learning approaches is that they tend to be overconfident in the decisions that t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4e85b17651c39d5847c88cde44716a2
Automatic spoken language assessment (SLA) is a challenging problem due to the large variations in learner speech combined with limited resources. These issues are even more problematic when considering children learning a language, with higher level
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6f7e9204c7589abfc03c4682314a285
A speaker's rhythm contributes to the intelligibility of their speech and can be characteristic of their language and accent. For non-native learners of a language, the extent to which they match its natural rhythm is an important predictor of their
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f0eff8d9f9d67f6186f62b73ebf95c0
Autor:
Wong, JHM, Gales, MJF
Student-teacher training allows a large teacher model or ensemble of teachers to be compressed into a single student model, for the purpose of efficient decoding. However, current approaches in automatic speech recognition assume that the state clust
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3560c4a3aa3eaeef72b3b419cd13f5e4