Assessment of dutch pronunciation by means of automatic speech recognition technology

Cucchiarini, Catia; Wet, Febe de; Strik, Helmer; Boves, L.W.J.

doi:10.21437/icslp.1998-720

Cited by 19 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ReLU is a non-linearity layer that works as a half-wave rectifier and used to speed-up the training process of the network. It also prevents over-fitting problem as described in (1).…”

Section: Dataset Acquisitionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Mispronunciation Detection of Arabic Words for Non-Native Learners Using Deep Convolutional Neural Network Features

et al. 2020

View full text Add to dashboard Cite

Computer-Aided Language Learning (CALL) is growing nowadays because learning new languages is essential for communication with people of different linguistic backgrounds. Mispronunciation detection is an integral part of CALL, which is used for automatic pointing of errors for the non-native speaker. In this paper, we investigated the mispronunciation detection of Arabic words using deep Convolution Neural Network (CNN). For automated pronunciation error detection, we proposed CNN features-based model and extracted features from different layers of Alex Net (layers 6, 7, and 8) to train three machine learning classifiers; K-nearest neighbor (KNN), Support Vector Machine (SVM) and Random Forest (RF). We also used a transfer learning-based model in which feature extraction and classification are performed automatically. To evaluate the performance of the proposed method, a comprehensive evaluation is provided on these methods with a traditional machine learning-based method using Mel Frequency Cepstral Coefficients (MFCC) features. We used the same three classifiers KNN, SVM, and RF in the baseline method for mispronunciation detection. Experimental results show that with handcrafted features, transfer learning-based method and classification based on deep features extracted from Alex Net achieved an average accuracy of 73.67, 85 and 93.20 on Arabic words, respectively. Moreover, these results reveal that the proposed method with feature selection achieved the best average accuracy of 93.20% than all other methods.

show abstract

“…The ReLU is a non-linearity layer that works as a half-wave rectifier and used to speed-up the training process of the network. It also prevents over-fitting problem as described in (1).…”

Section: Dataset Acquisitionmentioning

confidence: 99%

“…CALL accomplished many tasks, such as pronunciation error detection, speech recognition, and pronunciation scoring. Moreover, much research has been done to apply speech processing techniques to different languages [1][2][3]. For a specific language, speakers of different languages tend to form a distinctive muscle of the mouth.…”

Section: Introductionmentioning

confidence: 99%

Improving Mispronunciation Detection of Arabic Words for Non-Native Learners Using Deep Convolutional Neural Network Features

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In [4] we addressed the first problem. In the present paper we will focus on the solutions o f the second and third problem.…”

Section: Introductionmentioning

confidence: 99%

Using likelihood ratios to perform utterance verification in automatic pronunciation assessment

Wet¹,

Cucchiarini²,

Strik³

et al. 1999

6th European Conference on Speech Communication and Technology

Self Cite

View full text Add to dashboard Cite

The aim of our current research is to investigate the possibility of using likelihood ratios to perform utterance verification within the context of automatic oral proficiency assessment. The likelihood ratios under investigation have the appealing feature that they may be computed simply by using an off-theshelf automatic speech recognition system in two different recognition modes (forced and free phone) instead of using a system with specifically trained anti-models. We achieved 93% correct classification for 10 phonetically rich sentences uttered by 60 non-native language students.

show abstract

A Mandarin e‐learning system based on speech recognition and evaluation

Ming

Bai

2011

Comp Applic In Engineering

View full text Add to dashboard Cite

This paper establishes a speaker-independent pronunciation recognition and assessment system under the background of a Mandarin e-learning system framework. The recognition part is based on Hidden Markov Models (HMM) and improved in the aspect of acoustic and tone model. Making use of the recognition and detection results and corresponding parametric scorings, the machine scoring is performed to evaluate the quality of pronunciation its correlation with expert score are discussed. Through integrating recognition and assessment system with Web 2.0, we ultimately establish an open, shared and growing-up virtual Mandarin learning community, where all of learners, viewers, professors, without any restrictions on time and places, can express their perspective about how to advance Mandarin learning freely. ß

show abstract

Assessment of dutch pronunciation by means of automatic speech recognition technology

Cited by 19 publications

References 4 publications

Improving Mispronunciation Detection of Arabic Words for Non-Native Learners Using Deep Convolutional Neural Network Features

Improving Mispronunciation Detection of Arabic Words for Non-Native Learners Using Deep Convolutional Neural Network Features

Using likelihood ratios to perform utterance verification in automatic pronunciation assessment

A Mandarin e‐learning system based on speech recognition and evaluation

Contact Info

Product

Resources

About