1 |
ClassSPLOM -- A Scatterplot Matrix to Visualize Separation of Multiclass Multidimensional Data ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Code-Switching Text Augmentation for Multilingual Speech Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Telehealth and Artificial Intelligence Insights into Healthcare during the COVID-19 Pandemic
|
|
|
|
In: Healthcare; Volume 10; Issue 2; Pages: 385 (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Acceptance of COVID-19 Vaccine Among Refugees in the United States ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Acceptance of COVID-19 Vaccine Among Refugees in the United States ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Arabic Speech Recognition by End-to-End, Modular Systems and Human ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Arabic Code-Switching Speech Recognition using Monolingual Data ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR ...
|
|
|
|
Abstract:
With the advent of globalization, there is an increasing demand for multilingual automatic speech recognition (ASR), handling language and dialectal variation of spoken content. Recent studies show its efficacy over monolingual systems. In this study, we design a large multilingual end-to-end ASR using self-attention based conformer architecture. We trained the system using Arabic (Ar), English (En) and French (Fr) languages. We evaluate the system performance handling: (i) monolingual (Ar, En and Fr); (ii) multi-dialectal (Modern Standard Arabic, along with dialectal variation such as Egyptian and Moroccan); (iii) code-switching -- cross-lingual (Ar-En/Fr) and dialectal (MSA-Egyptian dialect) test cases, and compare with current state-of-the-art systems. Furthermore, we investigate the influence of different embedding/character representations including character vs word-piece; shared vs distinct input symbol per language. Our findings demonstrate the strength of such a model by outperforming ... : Accepted in INTERSPEECH 2021, Multilingual ASR, Multi-dialectal ASR, Code-Switching ASR, Arabic ASR, Conformer, Transformer, E2E ASR, Speech Recognition, ASR, Arabic, English, French ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Human-Computer Interaction cs.HC; Sound cs.SD
|
|
URL: https://dx.doi.org/10.48550/arxiv.2105.14779 https://arxiv.org/abs/2105.14779
|
|
BASE
|
|
Hide details
|
|
12 |
Balanced End-to-End Monolingual pre-training for Low-Resourced Indic Languages Code-Switching Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Enhanced forensic speaker verification performance using the ICA-EBM algorithm under noisy and reverberant environments
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
A Study On the Use of Collocations in Business Class Learners
|
|
|
|
In: Colombian Applied Linguistics Journal, Vol 22, Iss 2, Pp 183-193 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
20 |
Representation of Racial Segregation and Identity Crisis in Richard Wright’s Novel Black Boy
|
|
|
|
In: Studies in Literature and Language; Vol 20, No 1 (2020): Studies in Literature and Language; 21-26 ; 1923-1563 ; 1923-1555 (2020)
|
|
BASE
|
|
Show details
|
|
|
|