Muhammad Ishaq¹, Mustaqeem Khan^1,2, Soonil Kwon^1,*

Computer Systems Science and Engineering, Vol.46, No.3, pp. 3355-3369, 2023, DOI:10.32604/csse.2023.037373

Abstract Speech signals play an essential role in communication and provide an efficient way to exchange information between humans and machines. Speech Emotion Recognition (SER) is one of the critical sources for human evaluation, which is applicable in many real-world applications such as healthcare, call centers, robotics, safety, and virtual reality. This work developed a novel TCN-based emotion recognition system using speech signals through a spatial-temporal convolution network to recognize the speaker’s emotional state. The authors designed a Temporal Convolutional Network (TCN) core block to recognize long-term dependencies in speech signals and then feed these temporal cues to a dense network… More >

R. Gayathri^1,*, K. Sheela Sobana Rani²

Computer Systems Science and Engineering, Vol.46, No.1, pp. 43-56, 2023, DOI:10.32604/csse.2023.032491

Abstract Classification of speech signals is a vital part of speech signal processing systems. With the advent of speech coding and synthesis, the classification of the speech signal is made accurate and faster. Conventional methods are considered inaccurate due to the uncertainty and diversity of speech signals in the case of real speech signal classification. In this paper, we use efficient speech signal classification using a series of neural network classifiers with reinforcement learning operations. Prior classification of speech signals, the study extracts the essential features from the speech signal using Cepstral Analysis. The features are extracted by converting the speech… More >

Rakesh Kumar Pattanaik¹, Mihir N. Mohanty^1,*, Srikanta Ku. Mohapatra², Binod Ku. Pattanayak³

Computer Systems Science and Engineering, Vol.46, No.1, pp. 195-208, 2023, DOI:10.32604/csse.2023.029591

Abstract System Identification becomes very crucial in the field of nonlinear and dynamic systems or practical systems. As most practical systems don’t have prior information about the system behaviour thus, mathematical modelling is required. The authors have proposed a stacked Bidirectional Long-Short Term Memory (Bi-LSTM) model to handle the problem of nonlinear dynamic system identification in this paper. The proposed model has the ability of faster learning and accurate modelling as it can be trained in both forward and backward directions. The main advantage of Bi-LSTM over other algorithms is that it processes inputs in two ways: one from the past… More >

Sneha Basak¹, Himanshi Agrawal¹, Shreya Jena¹, Shilpa Gite^2,*, Mrinal Bachute², Biswajeet Pradhan^3,4,5,*, Mazen Assiri⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.135, No.2, pp. 1053-1089, 2023, DOI:10.32604/cmes.2022.021755

Abstract Speech recognition systems have become a unique human-computer interaction (HCI) family. Speech is one of the most naturally developed human abilities; speech signal processing opens up a transparent and hand-free computation experience. This paper aims to present a retrospective yet modern approach to the world of speech recognition systems. The development journey of ASR (Automatic Speech Recognition) has seen quite a few milestones and breakthrough technologies that have been highlighted in this paper. A step-by-step rundown of the fundamental stages in developing speech recognition systems has been presented, along with a brief discussion of various modern-day developments and applications in… More >

Yan Sun^1,2,*, Cun Zhu¹, Qi Cui³

CMC-Computers, Materials & Continua, Vol.73, No.1, pp. 1817-1825, 2022, DOI:10.32604/cmc.2022.029408

Abstract Research on the feature of speech and image signals are carried out from two perspectives, the time domain and the frequency domain. The speech and image signals are a non-stationary signal, so FT is not used for the non-stationary characteristics of the signal. When short-term stable speech is obtained by windowing and framing the subsequent processing of the signal is completed by the Discrete Fourier Transform (DFT). The Fast Discrete Fourier Transform is a commonly used analysis method for speech and image signal processing in frequency domain. It has the problem of adjusting window size to a for desired resolution.… More >

Ahmed S. Almasoud¹, Taiseer Abdalla Elfadil Eisa², Fahd N. Al-Wesabi^3,4, Abubakar Elsafi⁵, Mesfer Al Duhayyim⁶, Ishfaq Yaseen⁷, Manar Ahmed Hamza^7,*, Abdelwahed Motwakel⁷

CMC-Computers, Materials & Continua, Vol.72, No.1, pp. 871-886, 2022, DOI:10.32604/cmc.2022.024596

Abstract Early detection of Parkinson's Disease (PD) using the PD patients’ voice changes would avoid the intervention before the identification of physical symptoms. Various machine learning algorithms were developed to detect PD detection. Nevertheless, these ML methods are lack in generalization and reduced classification performance due to subject overlap. To overcome these issues, this proposed work apply graph long short term memory (GLSTM) model to classify the dynamic features of the PD patient speech signal. The proposed classification model has been further improved by implementing the recurrent neural network (RNN) in batch normalization layer of GLSTM and optimized with adaptive moment… More >

Omar M. El-Habbak¹, Abdelrahman M. Abdelalim¹, Nour H. Mohamed¹, Habiba M. Abd-Elaty¹, Mostafa A. Hammouda¹, Yasmeen Y. Mohamed¹, Mohanad A. Taifor¹, Ali W. Mohamed^2,3,*

CMC-Computers, Materials & Continua, Vol.70, No.2, pp. 2953-2969, 2022, DOI:10.32604/cmc.2022.020109

Abstract Parkinson’s disease (PD), one of whose symptoms is dysphonia, is a prevalent neurodegenerative disease. The use of outdated diagnosis techniques, which yield inaccurate and unreliable results, continues to represent an obstacle in early-stage detection and diagnosis for clinical professionals in the medical field. To solve this issue, the study proposes using machine learning and deep learning models to analyze processed speech signals of patients’ voice recordings. Datasets of these processed speech signals were obtained and experimented on by random forest and logistic regression classifiers. Results were highly successful, with 90% accuracy produced by the random forest classifier and 81.5% by… More >

Shahid Ali Mahar¹, Mumtaz Hussain Mahar¹, Javed Ahmed Mahar¹, Mehedi Masud², Muneer Ahmad³, NZ Jhanjhi^4,*, Mirza Abdur Razzaq¹

Intelligent Automation & Soft Computing, Vol.29, No.1, pp. 183-197, 2021, DOI:10.32604/iasc.2021.015755

Abstract Speech signal analysis for the extraction of speech elements is viable in natural language applications. Rhythm, intonation, stress, and tone are the elements of prosody. These features are essential in emotional speech, speech to speech, speech recognition, and other applications. The current study attempts to extract the pitch and duration from historical Sindhi sound clips using the functional contours model’s superposition. The sampled sound clips contained the speech of 273 undergraduates living in 5 districts of the Sindhi province. Several Python libraries are available for the application of this model. We used these libraries for the extraction of prosodic data… More >

Yongqiang Bao^{1, *}, Qi Shao¹, Xuxu Zhang¹, Jiahui Jiang¹, Yue Xie¹, Tingting Liu¹, Weiye Xu²

CMC-Computers, Materials & Continua, Vol.65, No.3, pp. 2557-2570, 2020, DOI:10.32604/cmc.2020.011241

Abstract The field of digital audio forensics aims to detect threats and fraud in audio signals. Contemporary audio forensic techniques use digital signal processing to detect the authenticity of recorded speech, recognize speakers, and recognize recording devices. User-generated audio recordings from mobile phones are very helpful in a number of forensic applications. This article proposed a novel method for recognizing recording devices based on recorded audio signals. First, a database of the features of various recording devices was constructed using 32 recording devices (20 mobile phones of different brands and 12 kinds of recording pens) in various environments. Second, the audio… More >