Pattern recognition and features selection for speech emotion recognition model using deep learning

Jermsittiparsert, Kittisak; Abdurrahman, Abdurrahman; Siriattakul, Parinya; Sundeeva, Ludmila A.; Hashim, Wahidah; Rahim, Robbi; Maseleno, Andino

doi:10.1007/s10772-020-09690-2

Cited by 41 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. Zamil, et al [8], the extricated highlights of the obscure discourse and after that compared them to the put away extricated highlights for each diverse speaker in arrange to distinguish the obscure speaker using a voting mechanism. However, the key process of selecting the extracted features is minimizing the difficulty of speech recognition system computing for matching processes [9]. Therefore, another study has observed the performance of speech recognition system computing [10], [11].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Performance Comparison between Lab-VIEW and MATLAB on Feature Matching-based Speech Recognition System

Widasari¹,

Prasetio²,

Ratnawati³

2022

IJACSA

View full text Add to dashboard Cite

Speech recognition systems are widely used for smart applications. The smart application-based speech recognition system has different requirements for processing the human voice. The most common performance in the speech recognition system is essential to observe, since it is necessary to design smart application-based speech recognition systems for people's needs. Moreover, feature matching is the principal part of speech recognition systems since it plays a key role to authenticate, separate one human voice from another, and their different articulation. Therefore, this work proposes a performance comparison of speech recognition systems based on feature matching using Lab-VIEW and MATLAB. The feature extraction involves calculation of Mel Frequency Cepstral Coefficients (MFCC) for each frame. For the matching process, the system was tested 100 times for each five speeches by making changes in articulation with the same vocal cords. This matching process uses DTW (Dynamic Time Warping), and then the testing is based on the most common performance in the speech recognition system's comparison between Lab-VIEW and MATLAB such as accuracy rate, execution time, and CPU usage. Based on experimental results, the average accuracy rate of MATLAB is better than Lab-VIEW. The execution time testing indicates that Lab-VIEW has a shorter execution time than MATLAB. On the other hand, Lab-VIEW and MATLAB have almost the same CPU usage. This result indicates that the performance comparison is able to be used according to the requirements of smart application-based speech recognition systems.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In the last decade, some works have observed the performance of speech recognition system separately [8], [9], [10], [11]. However, since the most common performance of speech recognition systems based on feature matching was not observed at all.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison between Lab-VIEW and MATLAB on Feature Matching-based Speech Recognition System

Widasari¹,

Prasetio²,

Ratnawati³

2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…It all knows that computers use binary, but humans are used to decimal. So in order for a computer to be able to process data and information, it must convert the previously quantized values to binary [10]. In fact, the process of converting to binary is just a simple encoding process.…”

Section: Signal Digitizationmentioning

confidence: 99%

Voice Timbre Evaluation of Broadcast Host Based on Extraction of Voice Feature Parameters

2022

IJAID

View full text Add to dashboard Cite

The continuous development of science and technology has continuously improved people's quality of life. People's definition of health is also clearer, and more attention is paid to laryngeal diseases and the quality of voice. In real life, accurate evaluation of voice quality and timbre is not only beneficial to the diagnosis and treatment of laryngeal diseases. At the same time, it also plays a vital role in the selection and training of broadcasting and hosting talents. The current evaluation methods for related professional voices have shortcomings such as time-consuming, labor-intensive and highly subjective. In order to overcome these defects and explore how to help the training of broadcast hosts, this paper conducts in-depth research on the processing method of speech signals and the objective evaluation method of artistic voice timbre from the perspective of signal processing. Through experimental analysis, it is found that the objective evaluation method of voice timbre based on acoustic parameters F0, F1, F3 can better realize the objective evaluation of the voice timbre of the broadcast host. Among them, the accuracy rate of the evaluation method based on multiple feature parameter extraction reaches 89.2%.

show abstract

“…Audio classification is widely applied in audio pattern recognition tasks, such as speaker identification [Ravanelli and Bengio 2018a;Snyder et al 2018], acoustic event detection [Kumar and Raj 2016], accent classification [Hansen and Liu 2016;Lopez-Moreno et al 2014], audio emotion recognition [Jermsittiparsert et al 2020]. Recently, deep learning methods showed promising performance compared to traditional approaches for this task [Hershey et al 2017].…”

Section: Audio Classificationmentioning

confidence: 99%

A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches

Guo¹,

Zhang²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Automatic spoken instruction understanding (SIU) of the controller-pilot conversations in the air traffic control (ATC) requires not only recognizing the words and semantics of the speech but also determining the role of the speaker. However, few of the published works on the automatic understanding systems in air traffic communication focus on speaker role identification (SRI). In this paper, we formulate the SRI task of controller-pilot communication as a binary classification problem. Furthermore, the text-based, speech-based, and speech and text based multi-modal methods are proposed to achieve a comprehensive comparison of the SRI task. To ablate the impacts of the comparative approaches, various advanced neural network architectures are applied to optimize the implementation of text-based and speech-based methods. Most importantly, a multi-modal speaker role identification network (MMSRINet) is designed to achieve the SRI task by considering both the speech and textual modality features. To aggregate modality features, the modal fusion module is proposed to fuse and squeeze acoustic and textual representations by modal attention mechanism and self-attention pooling layer, respectively. Finally, the comparative approaches are validated on the ATCSpeech corpus collected from a real-world ATC environment. The experimental results demonstrate that all the comparative approaches are worked for the SRI task, and the proposed MMSRINet shows the competitive performance and robustness than the other methods on both seen and unseen data, achieving 98.56%, and 98.08% accuracy, respectively.

show abstract

Pattern recognition and features selection for speech emotion recognition model using deep learning

Cited by 41 publications

References 12 publications

Performance Comparison between Lab-VIEW and MATLAB on Feature Matching-based Speech Recognition System

Performance Comparison between Lab-VIEW and MATLAB on Feature Matching-based Speech Recognition System

Voice Timbre Evaluation of Broadcast Host Based on Extraction of Voice Feature Parameters

A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches

Contact Info

Product

Resources

About