1 |
Challenges and responses: A Complex Dynamic Systems approach to exploring language teacher agency in a blended classroom
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Eliciting positive emotion through strategic responses to COVID-19 crisis: evidence from the tourism sector
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Exploring the paths to big data analytics implementation success in banking and financial service: an integrated approach
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Voice for oneself: Self-interested voice and its antecedents and consequences
|
|
|
|
BASE
|
|
Show details
|
|
7 |
The trans-ancestral genomic architecture of glycemic traits.
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Into the Real World: Autonomous and Integrated Chinese Language Learning Through a 3D Immersive Experience
|
|
|
|
BASE
|
|
Show details
|
|
9 |
The trans-ancestral genomic architecture of glycemic traits.
|
|
|
|
In: Nature genetics, vol. 53, no. 6, pp. 840-860 (2021)
|
|
BASE
|
|
Show details
|
|
10 |
Finding my voice: an interdisciplinary and multi-methodological investigation into the relationship between performers’ speech and musical expression
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Non-native children's automatic speech recognition: The INTERSPEECH 2020 shared task ALTA systems ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Non-native children's automatic speech recognition: The INTERSPEECH 2020 shared task ALTA systems
|
|
Knill, Katherine; Wang, L; Wang, Y. - : ISCA, 2020. : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2020
|
|
BASE
|
|
Show details
|
|
13 |
Study of central exclusive [Image: see text] production in proton-proton collisions at [Formula: see text] and 13TeV
|
|
|
|
In: Eur Phys J C Part Fields (2020)
|
|
BASE
|
|
Show details
|
|
14 |
Enhancing the learning of multi-level undergraduate Chinese language with a 3D immersive experience - an exploratory study
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Internal Meanings of the Language in Russian-Chinese Translation ... : Передача внутрилингвистических значений в русско-китайском переводе ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Exploiting future word contexts in neural network language models for speech recognition
|
|
|
|
Abstract:
Language modeling is a crucial component in a wide range of applications including speech recognition. Language models (LMs) are usually constructed by splitting a sentence into words and computing the probability of a word based on its word history. This sentence probability calculation, making use of conditional probability distributions, assumes that there is little impact from approximations used in the LMs, including the word history representations and finite training data. This motivates examining models that make use of additional information from the sentence. In this paper, future word information, in addition to the history, is used to predict the probability of the current word. For recurrent neural network LMs (RNNLMs), this information can be encapsulated in a bi-directional model. However, if used directly, this form of model is computationally expensive when trained on large quantities of data, and can be problematic when used with word lattices. This paper proposes a novel neural network language model structure, the succeeding-word RNNLM, su-RNNLM, to address these issues. Instead of using a recurrent unit to capture the complete future word contexts, a feedforward unit is used to model a fixed finite number of succeeding words. This is more efficient in training than bi-directional models and can be applied to lattice rescoring. The generated lattices can be used for downstream applications, such as confusion network decoding and keyword search. Experimental results on speech recognition and keyword spotting tasks illustrate the empirical usefulness of future word information, and the flexibility of the proposed model to represent this information.
|
|
URL: http://eprints.whiterose.ac.uk/150520/1/article.pdf http://eprints.whiterose.ac.uk/150520/
|
|
BASE
|
|
Hide details
|
|
17 |
Impact of ASR performance on free speaking language assessment ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Phonetic and graphemic systems for multi-genre broadcast transcription
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Impact of ASR performance on free speaking language assessment
|
|
|
|
BASE
|
|
Show details
|
|
|
|