1 |
Domain-Adversarial Based Model with Phonological Knowledge for Cross-Lingual Speech Recognition
|
|
|
|
In: http://infoscience.epfl.ch/record/291292 (2022)
|
|
Abstract:
Phonological-based features (articulatory features, AFs) describe the movements of the vocal organ which are shared across languages. This paper investigates a domain-adversarial neural network (DANN) to extract reliable AFs, and different multi-stream techniques are used for cross-lingual speech recognition. First, a novel universal phonological attributes definition is proposed for Mandarin, English, German and French. Then a DANN-based AFs detector is trained using source languages (English, German and French). When doing the cross-lingual speech recognition, the AFs detectors are used to transfer the phonological knowledge from source languages (English, German and French) to the target language (Mandarin). Two multi-stream approaches are introduced to fuse the acoustic features and cross-lingual AFs. In addition, the monolingual AFs system (i.e., the AFs are directly extracted from the target language) is also investigated. Experiments show that the performance of the AFs detector can be improved by using convolutional neural networks (CNN) with a domain-adversarial learning method. The multi-head attention (MHA) based multi-stream can reach the best performance compared to the baseline, cross-lingual adaptation approach, and other approaches. More specifically, the MHA-mode with cross-lingual AFs yields significant improvements over monolingual AFs with the restriction of training data size and, which can be easily extended to other low-resource languages.
|
|
URL: https://doi.org/10.3390/electronics10243172 http://infoscience.epfl.ch/record/291292 https://infoscience.epfl.ch/record/291292/files/electronics-10-03172.pdf
|
|
BASE
|
|
Hide details
|
|
2 |
Online Literacy Instruction for Young Korean Dual Language Learners in General Education
|
|
|
|
In: J Behav Educ (2022)
|
|
BASE
|
|
Show details
|
|
6 |
From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Temporal trends in incidence and mortality rates of laryngeal cancer at the global, regional and national levels, 1990–2017
|
|
|
|
In: BMJ Open (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Development and Validation of an Unethical Professional Behavior Tendencies Scale for Student Teachers
|
|
|
|
In: Front Psychol (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Pragmatics to Reveal Intent in Social Media Peer Interactions: Mixed Methods Study
|
|
|
|
In: J Med Internet Res (2021)
|
|
BASE
|
|
Show details
|
|
10 |
The second language acquisition of the Chinese aspect marker "le"
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Measurement of single-diffractive dijet production in proton-proton collisions at $\sqrt{s} =$ 8 TeV with the CMS and TOTEM experiments
|
|
|
|
In: Eur.Phys.J.C ; https://hal.archives-ouvertes.fr/hal-02507664 ; Eur.Phys.J.C, 2020, 80 (12), pp.1164. ⟨10.1140/epjc/s10052-020-08562-y⟩ (2020)
|
|
BASE
|
|
Show details
|
|
12 |
Lens on China: Intermediate and Advanced Readings on Film for Learning Chinese
|
|
|
|
In: Faculty Books (2020)
|
|
BASE
|
|
Show details
|
|
15 |
Neural representations of the concepts in simple sentences: Concept activation prediction and context effects ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Neural representations of the concepts in simple sentences: Concept activation prediction and context effects ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
The role of growth mindset, self-efficacy and intrinsic value in self-regulated learning and English language learning achievements ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
The role of growth mindset, self-efficacy and intrinsic value in self-regulated learning and English language learning achievements ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Measurement of the top quark mass with lepton+jets final states using $\mathrm {p}$ $\mathrm {p}$ collisions at $\sqrt{s}=13\,\text {TeV} $
|
|
|
|
In: http://infoscience.epfl.ch/record/275278 (2020)
|
|
BASE
|
|
Show details
|
|
20 |
Conversational topics of social media messages associated with state-level mental distress rates
|
|
|
|
In: J Ment Health (2020)
|
|
BASE
|
|
Show details
|
|
|
|