Deep Neural Networks Based Automatic Speech Recognition for Four Ethiopian Languages

Abate, Solomon Teferra; Tachbelie, Martha Yifiru; Schultz, Tanja

doi:10.1109/icassp40776.2020.9053883

Cited by 10 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite Tigrinya sharing similarity with most Semitic languages in several ways, Tigrinya has different compound prepositions such as "ኣብልዕሉዓራት or ab leliarat" (on (top of) the bed), which has the preposition ኣብ/ab, preposition ልዕሉ/leli, and noun ዓራት/arat. Furthermore, Abate et al [18] mentioned that Tigrinya is a highly inflected language and features complex morphological characteristics due to basic word formations being based on sequences of consonants expressed by "roots" and "template patterns." Littell et al [19] stated that Tigrinya also shows both inflectional and derivational morphologies, where the former pertains to the tense, mood, gender, person, number, etc.…”

Section: Previous Attempts For Tigrinya Natural Language Processingmentioning

confidence: 99%

“…Furthermore, Abate et al [18] mentioned that Tigrinya is a highly inflected language and features complex morphological characteristics due to basic word formations being based on sequences of consonants expressed by "roots" and "template patterns." Littell et al [19] stated that Tigrinya also shows both inflectional and derivational morphologies, where the former pertains to the tense, mood, gender, person, number, etc.…”

Section: Previous Attempts For Tigrinya Natural Language Processingmentioning

confidence: 99%

“…Main Application Sentences/Tokens Year Fisseha [20] Stemming algorithm 690,000 2011 Reda et al [21] Unsupervised ML word sense disambiguation 190,000 2018 Osman et al [3] Stemming Tigrinya words 164,634 2012 Yemane et al [6] Post tagging for Tigrinya 72,000 2016 /arat. Furthermore, Abate et al [18] mentioned that Tigrinya is a highly inflected language and features complex morphological characteristics due to basic word formations being based on sequences of consonants expressed by "roots" and "template patterns." Littell et al [19] stated that Tigrinya also shows both inflectional and derivational morphologies, where the former pertains to the tense, mood, gender, person, number, etc.…”

Section: Authormentioning

confidence: 99%

See 2 more Smart Citations

Text Classification Based on Convolutional Neural Networks and Word Embedding for Low-Resource Languages: Tigrinya

et al. 2021

View full text Add to dashboard Cite

This article studies convolutional neural networks for Tigrinya (also referred to as Tigrigna), which is a family of Semitic languages spoken in Eritrea and northern Ethiopia. Tigrinya is a “low-resource” language and is notable in terms of the absence of comprehensive and free data. Furthermore, it is characterized as one of the most semantically and syntactically complex languages in the world, similar to other Semitic languages. To the best of our knowledge, no previous research has been conducted on the state-of-the-art embedding technique that is shown here. We investigate which word representation methods perform better in terms of learning for single-label text classification problems, which are common when dealing with morphologically rich and complex languages. Manually annotated datasets are used here, where one contains 30,000 Tigrinya news texts from various sources with six categories of “sport”, “agriculture”, “politics”, “religion”, “education”, and “health” and one unannotated corpus that contains more than six million words. In this paper, we explore pretrained word embedding architectures using various convolutional neural networks (CNNs) to predict class labels. We construct a CNN with a continuous bag-of-words (CBOW) method, a CNN with a skip-gram method, and CNNs with and without word2vec and FastText to evaluate Tigrinya news articles. We also compare the CNN results with traditional machine learning models and evaluate the results in terms of the accuracy, precision, recall, and F1 scoring techniques. The CBOW CNN with word2vec achieves the best accuracy with 93.41%, significantly improving the accuracy for Tigrinya news classification.

show abstract

Section: Previous Attempts For Tigrinya Natural Language Processingmentioning

confidence: 99%

Section: Previous Attempts For Tigrinya Natural Language Processingmentioning

confidence: 99%

Section: Authormentioning

confidence: 99%

See 1 more Smart Citation

Text Classification Based on Convolutional Neural Networks and Word Embedding for Low-Resource Languages: Tigrinya

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recently, we have witnessed the emergence and explosion of deep learning, since deep neural networks (DNNs) have been widely applied in various fields, such as computer vision, natural language processing, and speech recognition. [1][2][3] Especially in the field of image recognition, the top-5 predictive error against ImageNet is decreased steadily from 16.4% to 2.25% during the last several years. 4 The evidence shows that the robustness of DNNs has been improved rapidly through effective neural architecture design and regularization techniques.…”

Section: Introductionmentioning

confidence: 99%

Attention‐guided black‐box adversarial attacks with large‐scale multiobjective evolutionary optimization

Wang¹,

Yin²,

Jiang³

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Fooling deep neural networks (DNNs) with black-box optimization has become a popular adversarial attack fashion, as the prior structural knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may struggle to balance their attack ability and visual quality of the generated adversarial examples (AEs) in tackling high-resolution images. In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed LMOA. By considering the spatial semantic information of images, we first take advantage of the attention map to determine the perturbed pixels. Instead of attacking the entire image, reducing the perturbed pixels with the attention mechanism can help to avoid the notorious curse of dimensionality and thereby improve the performance of attacking. Second, a large-scale multiobjective evolutionary algorithm traverse the reduced pixels in the salient region. Benefiting from its characteristics, the generated AEs can fool target DNNs while being invisible by human vision. Extensive experimental results have verified the effectiveness of the proposed LMOA on the ImageNet data set. More importantly, it is more competitive to generate highresolution AEs with the better visual quality than the existing black-box adversarial attacks.

show abstract

“…R ECENT years have witnessed the emergence and explosion of deep learning, since deep neural networks (DNNs) have been widely applied in various fields, such as computer vision, natural language processing, and speech recognition [1]- [3]. Especially in the field of image recognition, the top-5 predictive error against ImageNet is increased steadily from 83.6% to 97.75% during the last several years [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

Wang¹,

Yin²,

Jiang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may struggle to balance their attack ability and visual quality of the generated adversarial examples (AEs) in tackling high-resolution images. In this paper, we propose an attention-guided blackbox adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA. By considering the spatial semantic information of images, we firstly take advantage of the attention map to determine the perturbed pixels. Instead of attacking the entire image, reducing the perturbed pixels with the attention mechanism can help to avoid the notorious curse of dimensionality and thereby improves the performance of attacking. Secondly, a large-scale multiobjective evolutionary algorithm is employed to traverse the reduced pixels in the salient region. Benefiting from its characteristics, the generated AEs have the potential to fool target DNNs while being imperceptible by the human vision. Extensive experimental results have verified the effectiveness of the proposed LMOA on the ImageNet dataset. More importantly, it is more competitive to generate highresolution AEs with better visual quality compared with the existing black-box adversarial attacks.

show abstract

Deep Neural Networks Based Automatic Speech Recognition for Four Ethiopian Languages

Cited by 10 publications

References 10 publications

Text Classification Based on Convolutional Neural Networks and Word Embedding for Low-Resource Languages: Tigrinya

Text Classification Based on Convolutional Neural Networks and Word Embedding for Low-Resource Languages: Tigrinya

Attention‐guided black‐box adversarial attacks with large‐scale multiobjective evolutionary optimization

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

Contact Info

Product

Resources

About