A Speech Quality Classifier based on Tree-CNN Algorithm that Considers Network Degradations

Vieira, Samuel Terra; Rosa, Renata Lopes; Rodríguez, Demóstenes Zegarra

doi:10.24138/jcomss.v16i2.1032

Cited by 5 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We followed our data processing design just as we explained earlier, before feeding our TBCNN with the blocks of training, validation, and testing. We adopted this model for this research because of how effective it was in [7,23,26] and how they all had a similar problem area, program source code, although with different objectives. The model, which we implemented with kernels, paddings, and slides aside the various layers, performed well with an accuracy of 94% within 10 epochs, as depicted in Figure 8.…”

Section: Discussion Of Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Classification of Equivalent Mutants in Mutation Testing of Android Applications

et al. 2022

View full text Add to dashboard Cite

Software and symmetric testing methodologies are primarily used in detecting software defects, but these testing methodologies need to be optimized to mitigate the wasting of resources. As mobile applications are becoming more prevalent in recent times, the need to have mobile applications that satisfy software quality through testing cannot be overemphasized. Testing suites and software quality assurance techniques have also become prevalent, which underscores the need to evaluate the efficacy of these tools in the testing of the applications. Mutation testing is one such technique, which is the process of injecting small changes into the software under test (SUT), thereby creating mutants. These mutants are then tested using mutation testing techniques alongside the SUT to determine the effectiveness of test suites through mutation scoring. Although mutation testing is effective, the cost of implementing it, due to the problem of equivalent mutants, is very high. Many research works gave varying solutions to this problem, but none used a standardized dataset. In this research work, we employed a standard mutant dataset tool called MutantBench to generate our data. Subsequently, an Abstract Syntax Tree (AST) was used in conjunction with a tree-based convolutional neural network (TBCNN) as our deep learning model to automate the classification of the equivalent mutants to reduce the cost of mutation testing in software testing of android applications. The result shows that the proposed model produces a good accuracy rate of 94%, as well as other performance metrics such as recall (96%), precision (89%), F1-score (92%), and Matthew’s correlation coefficients (88%) with fewer False Negatives and False Positives during testing, which is significant as it implies that there is a decrease in the risk of misclassification.

show abstract

Section: Discussion Of Resultsmentioning

confidence: 99%

“…To solve this anomaly, we adopted the method of [26] but kept in mind the need to consider semantic and synthetic structures of the software under test (SUT) as proposed by [21]. In Figure 2 below, we present the process flow of our data generation using the µjava tool within MutantBench.…”

Section: Data Generation and Processingmentioning

confidence: 99%

Automatic Classification of Equivalent Mutants in Mutation Testing of Android Applications

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In recent years, unsupervised feature learning receives widespread attention in computer vision because automatic learning to obtain robustness’ visual feature expression in the massive unlabeled data (including images and videos) becomes a crucial task for the next generation of intelligent vision applications [ 25 ]. In the ML application, computer vision and neuroscience researchers have reached the consensus shown in Fig.…”

Section: Methodsmentioning

confidence: 99%

Applying TS-DBN model into sports behavior recognition with deep learning approach

Guo

Wang

2021

J Supercomput

View full text Add to dashboard Cite

The purposes are to automatically collect information about human sports behavior from massive video data and provide an explicit recognition and analysis of body movements. The analysis of multi-scale input data, the improvement of spatiotemporal Deep Belief Network (DBN), and the different pooling strategies are regarded as the focuses to improve the belief networks in deep learning (DL). Moreover, a human sports behavior recognition model is proposed based on particular spatio-temporal features. Also, video frame data are collected from the Royal Institute of Technology (KTH) and University of Central Florida (UCF) datasets for training. The TensorFlow platform is employed to simulate the built algorithm. Finally, the constructed algorithm model is compared with the DBN proposed by Yang et al. the Convolutional Neural Network (CNN) proposed by Ullah et al. and the DBN-Hidden Markov Model (HMM) algorithm proposed by Xu et al. to analyse its performance. The recognition effects of each algorithm in the two datasets are analyzed. Results demonstrate that CNN developed by Ullah et al. has the worst accuracy on the KTH and UCF datasets, followed by DBN developed by Yang et al. and DBN-HMM developed by Xu et al. The constructed algorithm model can provide the highest accuracy, reaching about 90%, and the recognition accuracy of human sports behaviors of each algorithm on the KTH dataset is lower than that on the UCF dataset. On the KTH dataset, the recognition accuracy for boxing is the highest and running the lowest. Analyzing the model’s accuracy in the four scenes (S1, S2, S3, and S4) on the KTH dataset suggests that the recognition accuracy for the indoor scene (S4) is higher than that of the outdoor scenes (S1, S2, and S3). On the UCF dataset, the recognition accuracy for lifting is the highest, reaching 99%, and that for walking is the lowest, reaching 51%. Therefore, the proposed human sports recognition model can provide a higher accuracy than other classic DL algorithms, providing an experimental basis for subsequent human sports recognition research.

show abstract

“…Feng et al [47] found that acoustic investigations can reveal that impaired speech has a substantially shorter voice start time for aspirated consonants, as well as a smaller vowel spacing. Vieira et al [48] presented a non-intrusive voice-quality classifier based on the tree convolutional neural network for measuring user satisfaction with speech communication platforms. Poncelet et al [49] suggested using an end-to-end spoken language understanding system that can be trained by the user through demonstrations and can translate impaired speech directly into semantics.…”

Section: Assessing Speech-signal Impairmentsmentioning

confidence: 99%

Pareto-Optimized Non-Negative Matrix Factorization Approach to the Cleaning of Alaryngeal Speech Signals

Maskeliūnas,

Damaševičius,

Kulikajevas

et al. 2023

Cancers

View full text Add to dashboard Cite

The problem of cleaning impaired speech is crucial for various applications such as speech recognition, telecommunication, and assistive technologies. In this paper, we propose a novel approach that combines Pareto-optimized deep learning with non-negative matrix factorization (NMF) to effectively reduce noise in impaired speech signals while preserving the quality of the desired speech. Our method begins by calculating the spectrogram of a noisy voice clip and extracting frequency statistics. A threshold is then determined based on the desired noise sensitivity, and a noise-to-signal mask is computed. This mask is smoothed to avoid abrupt transitions in noise levels, and the modified spectrogram is obtained by applying the smoothed mask to the signal spectrogram. We then employ a Pareto-optimized NMF to decompose the modified spectrogram into basis functions and corresponding weights, which are used to reconstruct the clean speech spectrogram. The final noise-reduced waveform is obtained by inverting the clean speech spectrogram. Our proposed method achieves a balance between various objectives, such as noise suppression, speech quality preservation, and computational efficiency, by leveraging Pareto optimization in the deep learning model. The experimental results demonstrate the effectiveness of our approach in cleaning alaryngeal speech signals, making it a promising solution for various real-world applications.

show abstract

A Speech Quality Classifier based on Tree-CNN Algorithm that Considers Network Degradations

Cited by 5 publications

References 35 publications

Automatic Classification of Equivalent Mutants in Mutation Testing of Android Applications

Automatic Classification of Equivalent Mutants in Mutation Testing of Android Applications

Applying TS-DBN model into sports behavior recognition with deep learning approach

Pareto-Optimized Non-Negative Matrix Factorization Approach to the Cleaning of Alaryngeal Speech Signals

Contact Info

Product

Resources

About