Výsledky vyhledávání - Melspectrogram Generative Adversarial Network*

Combining generative adversarial networks for emotion prediction in college students: An application to interactive musical interpretation.

Autoři: Song, Xi

Zdroj: Molecular & Cellular Biomechanics; 2025, Vol. 22 Issue 4, p1-18, 18p

Témata: GENERATIVE adversarial networks, MUSICAL interpretation, ATTENTION, AFFECTIVE forecasting (Psychology), SENTIMENT analysis, COLLEGE students, CONVOLUTIONAL neural networks

Towards Sustainable Image Synthesis: A Comprehensive Review of Text-to-Image Generation Models.

Autoři: Bharne, Smita Sapkale, Pallavi Sarda, Ekta a další

Zdroj: International Research Journal of Multidisciplinary Technovation (IRJMT); 2025, Vol. 7 Issue 5, p94-120, 27p

Témata: GENERATIVE adversarial networks, IMAGE quality in imaging systems, COMPUTER performance, PROBABILISTIC generative models, LATENT variables

EXPLOITING PRE-TRAINED FEATURE NETWORKS FOR GENERATIVE ADVERSARIAL NETWORKS IN AUDIO-DOMAIN LOOP GENERATION.

Autoři: Yen-Tung Yeh Bo-Yu Chen Yi-Hsuan Yang

Zdroj: International Society for Music Information Retrieval Conference Proceedings; 2022, p132-140, 9p

Témata: GENERATIVE adversarial networks, MUSICAL composition, MUSICAL analysis, MUSIC data processing, AUDIO acoustics

Exploring Generative Adversarial Networks and Meta-Learning Synergies

Autoři: Sarita Simaiya Umesh Kumar Lilhore Yogesh Kumar Sharma a další

Resource Type: eBook.

Témata: Neural networks (Computer science), Artificial intelligence

Categories: COMPUTERS / Artificial Intelligence / Computer Vision & Pattern Recognition, COMPUTERS / Artificial Intelligence / General, COMPUTERS / Data Science / Machine Learning

Demiurge: A Music of Babel.

Autoři: Trillo, Roberto Alonso Poliks, Marek

Zdroj: Leonardo; 2022, Vol. 55 Issue 5, p503-507, 5p, 1 Diagram

Témata: MACHINE learning, ARTIFICIAL neural networks, COMPUTER art, GENERATIVE adversarial networks, RAW materials, MUSICAL performance

People: POLIKS, Marek

Multimodal Sensor-Input Architecture with Deep Learning for Audio-Visual Speech Recognition in Wild.

Autoři: He, Yibo Seng, Kah Phooi Ang, Li Minn

Zdroj: Sensors (14248220); Feb2023, Vol. 23 Issue 4, p1834, 12p

Témata: DEEP learning, SPEECH perception, AUTOMATIC speech recognition, GENERATIVE adversarial networks, HUMAN voice, STREAMING audio

Speech Time-Scale Modification With GANs.

Autoři: Cohen, Eyal Kreuk, Felix Keshet, Joseph

Zdroj: IEEE Signal Processing Letters; May2022, Vol. 29, p1067-1071, 5p

Témata: AUTOMATIC speech recognition, GENERATIVE adversarial networks, MUSICAL perception, MACHINE learning, SIGNAL processing, ARTIFICIAL neural networks, SPEECH perception, SPEECH

Neurally Optimized Decoder for Low Bitrate Speech Codec.

Autoři: Kim, Hyung Yong Yoon, Ji Won Cho, Won Ik a další

Zdroj: IEEE Signal Processing Letters; 2022, Vol. 29, p244-248, 5p

Témata: VIDEO coding, AUTOMATIC speech recognition, SPEECH processing systems, GENERATIVE adversarial networks, BINARY sequences, CODECS

Multiple Predominant Instruments Recognition in Polyphonic Music Using Spectro/Modgd-gram Fusion.

Autoři: Lekshmi, C. R. Rajeev, Rajan

Zdroj: Circuits, Systems & Signal Processing; Jun2023, Vol. 42 Issue 6, p3464-3484, 21p

Témata: CONVOLUTIONAL neural networks, DATA augmentation

DDSP-BASED SINGING VOCODERS: A NEW SUBTRACTIVE-BASED SYNTHESIZER AND A COMPREHENSIVE EVALUATION.

Autoři: Da-Yi Wu Wen-Yi Hsiao Fu-Rong Yang a další

Zdroj: International Society for Music Information Retrieval Conference Proceedings; 2022, p76-83, 8p

Témata: VOCODER, DIGITAL signal processing, MUSICAL analysis, SYNTHESIZER music, HARMONY in music

Deepfake Detection in Manipulated Images/ Audio/ Videos: A Three-Stage Multi-Modal Deep Learning Framework.

Autoři: Nelson, Leema Batra, Harshita P., Radha

Zdroj: Inteligencia Artificial: Revista Iberoamericana de Inteligencia Artificial; Dec2025, Vol. 28 Issue 76, p20-39, 20p

Témata: DEEP learning, CONVOLUTIONAL neural networks, DIGITAL forensics, MISINFORMATION, DATA integrity, SIGNAL processing, LONG short-term memory

REAL-TIME PACKET LOSS CONCEALMENT USING DEEP GENERATIVE NETWORKS

Anomaly detection of aerodynamic noise from wind turbine blades based on the CNN–LSTM–AS–UNet model.

Autoři: Li, Hao Xi, Yibo Chen, Hao a další

Zdroj: Journal of Civil Structural Health Monitoring; Oct2025, Vol. 15 Issue 7, p3063-3078, 16p

Vision-to-Voice: AI for generating Description & Audio of Visual Content.

Autoři: Jayanth, P. Lakshmi Sree, K. Karthik Kumar Reddy, K. a další

Zdroj: International Research Journal of Innovations in Engineering & Technology; 2025 Special Issue, Vol. 9, p206-213, 8p

Témata: LANGUAGE models, SPEECH synthesis, COMPUTER vision, LINGUISTIC models, NATURAL languages

Sensitivity analysis of data augmentation methods on performance of deep learning model for lung sounds classification.

Autoři: Wang, Zhaoping Wang, Yingcui Sun, Zhiqiang

Zdroj: Scientific Reports; 11/10/2025, Vol. 15 Issue 1, p1-16, 16p

Témata: DATA augmentation, DEEP learning, SENSITIVITY analysis, STETHOSCOPES, RESPIRATORY organ sounds, SPECTROGRAMS

Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain.

Autoři: ROSENBERG, ISHAI SHABTAI, ASAF ELOVICI, YUVAL a další

Zdroj: ACM Computing Surveys; Jun2022, Vol. 54 Issue 5, p1-36, 36p

Témata: INTERNET security, MACHINE learning, DEEP learning, CYBERTERRORISM, INSTRUCTIONAL systems

Leveraging CQT-VMD and pre-trained AlexNet architecture for accurate pulmonary disease classification from lung sound signals: Leveraging CQT-VMD and pre-trained AlexNet architecture for accurate...: Z. Neili and K. Sundaraj.

Autoři: Neili, Zakaria Sundaraj, Kenneth

Zdroj: Applied Intelligence; Apr2025, Vol. 55 Issue 6, p1-19, 19p

An Adversarial Training Based Speech Emotion Classifier With Isolated Gaussian Regularization.

Autoři: Fu, Changzeng Liu, Chaoran Ishi, Carlos Toshinori a další

Zdroj: IEEE Transactions on Affective Computing; Jul-Sep2023, Vol. 14 Issue 3, p2361-2374, 14p

A Deep Learning Framework for Audio Deepfake Detection.

Autoři: Khochare, Janavi Joshi, Chaitali Yenarkar, Bakul a další

Zdroj: Arabian Journal for Science & Engineering (Springer Science & Business Media B.V. ); Mar2022, Vol. 47 Issue 3, p3447-3458, 12p

Témata: CONVOLUTIONAL neural networks, DEEP learning, SPEECH synthesis, MACHINE learning, DEEPFAKES, CLASSIFICATION algorithms

Enhanced Speech Emotion Recognition Using Conditional-DCGAN-Based Data Augmentation.

Autoři: Roh, Kyung-Min Lee, Seok-Pil

Zdroj: Applied Sciences (2076-3417); Nov2024, Vol. 14 Issue 21, p9890, 14p

Témata: ARTIFICIAL intelligence, EMOTION recognition, DATA augmentation, DEEP learning, SELF-expression