Results 61 to 70 of about 3,484 (180)

Construction and Application of GAN Enhanced Virtual Interpretation Model for Sports Communication

Engineering Reports, Volume 8, Issue 6, June 2026.
This model is an end‐to‐end framework. Firstly, the style‐based generation network Style‐based GAN2 (StyleGAN2) is used to generate a highly realistic and adjustable static narrator portrait. Then, Bi‐directional Long Short‐Term Memory (Bi‐LSTM) is used to encode the Mel‐frequency Cepstral Coefficients (MFCCs), phonemes, and prosodic features of the ...
Li Zhang, Hongyuan Xie, Jun Zhang, Ying Yang   +3 more
wiley   +1 more source

Fusion of Linear and Mel Frequency Cepstral Coefficients for Automatic Classification of Reptiles

Applied Sciences, 2017
Bioacoustic research of reptile calls and vocalizations has been limited due to the general consideration that they are voiceless.
Juan J. Noda, Carlos M. Travieso, David Sánchez-Rodríguez   +2 more
doaj   +1 more source

Optoelectronic Control of Redox Dynamics in POM Memristors for Noise‐Resilient Speech and Hardware‐Level Motion Recognition

Advanced Functional Materials, Volume 36, Issue 37, 7 May 2026.
Optoelectronic control of redox‐active polyoxometalate clusters in polymer matrices yields hybrid memristors with switchable volatile and non‐volatile modes, enabling reservoir‐type in‐sensor optical preprocessing and stable multilevel synapses for multimodal neuromorphic computing, including noise‐tolerant audiovisual keyword recognition and hardware ...
Xiangyu Ma, Ziyu Lv, Guohua Zhang, Zhongyue Xu, Yongbiao Zhai, Haiming Huang, Qiyan Zhang, Xiaojin Zhao, Yan Wang, Ye Zhou, Ziyu Xiong, Guanglong Ding, Wentao Xu, Su‐Ting Han   +13 more
wiley   +1 more source

Automatic Speaker Recognition Based on Mel-Frequency Cepstral Coefficients and Gaussian Mixture Models [PDF]

Mehran University Research Journal of Engineering and Technology, 2013
This paper investigates the task of SR (Speaker Recognition) for the state-of-the-art techniques. The paper initially presents the technical description of automatic SR, followed by the comparative analysis of a number of methods available for feature ...
Sheeraz Memon, Sania Bhatti, Farzana Rauf Abro   +2 more
doaj  

Mandarin speech‐based early detection of SCD: a feature‐fusion residual network method

Alzheimer's &Dementia, Volume 22, Issue 5, May 2026.
Abstract INTRODUCTION Alzheimer's disease (AD) poses a global health challenge. Early intervention during the stage of subjective cognitive decline (SCD) – a potential window for delaying disease progression – is crucial. This study aims to assess an exploratory speech‐based model for rapid SCD screening.
Zhou Liu, Chao Che, Guimei He, Hanyu Wu, Lei Cai, Lili Cui, Lizhong Liang   +6 more
wiley   +1 more source

HSD-Net: a dual-branch CNN-BiLSTM network with hybrid cepstral fusion for heart sound classification

Frontiers in Medical Technology
IntroductionCardiovascular diseases (CVDs) represent a major global health threat, making early detection crucial. While cardiac auscultation is cost-effective, its reliance on clinical expertise leads to significant variability in diagnostic accuracy ...
Caijian Hua, Ye Tian, Liuying Li, Xia Zhou   +3 more
doaj   +1 more source

Automated classification of vowel category and speaker type in the high-frequency spectrum

Audiology Research, 2016
The high-frequency region of vowel signals (above the third formant or F3) has received little research attention. Recent evidence, however, has documented the perceptual utility of high-frequency information in the speech signal above the traditional ...
Jeremy J. Donai, Saeid Motiian, Gianfranco Doretto   +2 more
doaj   +1 more source

Spoken English Assisted Training Model Based on Multifeature Parameters and Dynamic Time Warping Algorithm

Engineering Reports, Volume 8, Issue 5, May 2026.
Flow chart of the base sound trace extraction of speech. ABSTRACT With the acceleration of internationalization, the deficiency of traditional English classroom in English spoken teaching is becoming more obvious, especially the lack of effectiveness and immediate feedback. Therefore, a spoken English assisted training model is proposed.
Lubing Shang, Lu Ma
wiley   +1 more source

A dual-stream CNN-based ConvMixer for durian ripeness classification using magnitude and phase features from knocking sounds

Results in Engineering
Knocking-sound analysis provides a non-destructive method for assessing durian ripeness; however, most convolutional neural network methods mainly emphasize magnitude information while disregarding phase information that reflects the overall signal ...
Khomdet Phapatanaburi, Khwanjit Orkweha, Watcharakorn Pinthurat, Chaiwat Makhonpas, Wongsathon Pathonsuwan, Patikorn Anchuen, Monthippa Uthansakul, Peerapong Uthansakul   +7 more
doaj   +1 more source

Comparison of cepstral coefficients to other voice evaluation parameters in patients with occupational dysphonia

Medycyna Pracy, 2013
Background: Special consideration has recently been given to cepstral analysis with mel-frequency cepstral coefficients (MFCCs). The aim of this study was to assess the applicability of MFCCs in acoustic analysis for diagnosing occupational dysphonia in ...
Ewa Niebudek-Bogusz, Paweł Strumiłło, Justyna Wiktorowicz, Mariola Śliwińska-Kowalska   +3 more
doaj   +1 more source