| 2 |
The "Fat Face" illusion: A robust adaptation for processing pairs of faces
|
|
|
|
In: ISSN: 0042-6989 ; EISSN: 0042-6989 ; Vision Research ; https://hal.archives-ouvertes.fr/hal-03579276 ; Vision Research, Elsevier, 2022, 195, pp.108015. ⟨10.1016/j.visres.2022.108015⟩ (2022)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Intermedial Effects, Sanctified Surfaces: Embedded Devotional Objects in Italian Medieval Mural Decoration
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Graph theoretical analysis reveals the adaptive role of the left ventral occipito-temporal cortex in the brain networks during speech processing
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03576260 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Inter-Individual Variability in Dorsal Stream Dynamics During Word Production
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03629184 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Sentiment Analysis of the Undergraduate STEM Community at UCLA Using the Bruinwalk Course Reviews
|
|
Wang, Kaixin. - : eScholarship, University of California, 2022
|
|
BASE
|
|
Show details
|
|
|
| 8 |
L’interview d’Alain Lemaréchal ; 法国语言学家 Faguo yuyanxuejia A. Lemaréchal fangtan
|
|
|
|
In: In Xiuli Wang (éd) 法国著名语言学家采访录Faguo dangdai yuyanxuejia caifanglu [Recueil d’interviews d’éminents linguistes français] ; https://hal.archives-ouvertes.fr/hal-03551905 ; In Xiuli Wang (éd) 法国著名语言学家采访录Faguo dangdai yuyanxuejia caifanglu [Recueil d’interviews d’éminents linguistes français], 2022 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Detecting Tax Avoidance: Evidence from Quantitative and Linguistic Cues ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Sentence repetition as a clinical marker for Mandarin DLD (Wang et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Sentence repetition as a clinical marker for Mandarin DLD (Wang et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 12 |
How does sleeping help language acquisition? A meta-analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Genetic admixture of Chinese Tajik people inferred from genome-wide array genotyping and mitochondrial genome sequencing ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Genetic admixture of Chinese Tajik people inferred from genome-wide array genotyping and mitochondrial genome sequencing ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Subspace-based Representation and Learning for Phonotactic Spoken Language Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Machine learning reveals cryptic dialects that explain mate choice in a songbird ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
兒童華語教材中的飲食文化分析:以《學華語向前走》為例 ; Analysis of Food Culture of Chinese Teaching Material for Children — With Reference to “Let’s Learn Chinese”
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Mining an English-Chinese parallel Dataset of Financial News
|
|
|
|
In: Journal of Open Humanities Data; Vol 8 (2022); 9 ; 2059-481X (2022)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems ...
|
|
|
|
Abstract:
Contextual biasing is an important and challenging task for end-to-end automatic speech recognition (ASR) systems, which aims to achieve better recognition performance by biasing the ASR system to particular context phrases such as person names, music list, proper nouns, etc. Existing methods mainly include contextual LM biasing and adding bias encoder into end-to-end ASR models. In this work, we introduce a novel approach to do contextual biasing by adding a contextual spelling correction model on top of the end-to-end ASR system. We incorporate contextual information into a sequence-to-sequence spelling correction model with a shared context encoder. Our proposed model includes two different mechanisms: autoregressive (AR) and non-autoregressive (NAR). We propose filtering algorithms to handle large-size context lists, and performance balancing mechanisms to control the biasing degree of the model. We demonstrate the proposed model is a general biasing solution which is domain-insensitive and can be ... : This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://dx.doi.org/10.48550/arxiv.2203.00888
https://arxiv.org/abs/2203.00888
|
|
BASE
|
|
Hide details
|
|
|
|
|
