Global ETD Search

51	Towards a Nuanced Evaluation of Voice Activity Detection Systems : An Examination of Metrics, Sampling Rates and Noise with Deep Learning / Mot en nyanserad utvärdering av system för detektering av talaktivitet Joborn, Ludvig, Beming, Mattias January 2022 (has links) Recently, Deep Learning has revolutionized many fields, where one such area is Voice Activity Detection (VAD). This is of great interest to sectors of society concerned with detecting speech in sound signals. One such sector is the police, where criminal investigations regularly involve analysis of audio material. Convolutional Neural Networks (CNN) have recently become the state-of-the-art method of detecting speech in audio. But so far, understanding the impact of noise and sampling rates on such methods remains incomplete. Additionally, there are evaluation metrics from neighboring fields that remain unintegrated into VAD. We trained on four different sampling rates and found that changing the sampling rate could have dramatic effects on the results. As such, we recommend explicitly evaluating CNN-based VAD systems on pertinent sampling rates. Further, with increasing amounts of white Gaussian noise, we observed better performance by increasing the capacity of our Gated Recurrent Unit (GRU). Finally, we discuss how careful consideration is necessary when choosing a main evaluation metric, leading us to recommend Polyphonic Sound Detection Score (PSDS). voice activity detection VAD deep learning machine learning ML artificial intelligence AI convolutional neural network CNN deep neural network DNN sound event detection SED mel spectrogram audio processing polyphonic sound detection score PSDS signal processing signal to noise ratio SNR RCRNN sampling rate Gaussian noise Computer Sciences Datavetenskap (datalogi)
52	Minds, Machines & Metaphors : Limits of AI Understanding Másson, Mímir January 2024 (has links) This essay critically examines the limitations of artificial intelligence (AI) in achieving human-like understanding and intelligence. Despite significant advancements in AI, such as the development of sophisticated machine learning algorithms and neural networks, current systems fall short in comprehending the cognitive depth and flexibility inherent in human intelligence. Through an exploration of historical and contemporary arguments, including Searle's Chinese Room thought experiment and Dennett's Frame Problem, this essay highlights the inherent differences between human cognition and AI. Central to this analysis is the role of metaphorical thinking and embodied cognition, as articulated by Lakoff and Johnson, which are fundamental to human understanding but absent in AI. Proponents of AGI, like Kurzweil and Bostrom, argue for the potential of AI to surpass human intelligence through recursive self-improvement and technological integration. However, this essay contends that these approaches do not address the core issues of experiential knowledge and contextual awareness. By integrating insights from contemporary scholars like Bender, Koller, Buckner, Thorstad, and Hoffmann, the essay ultimately concludes that AI, while a powerful computational framework, is fundamentally incapaple of replicating the true intelligence and understanding unique to humans. Philosophy Filosofi
53	3D OBJECT DETECTION USING VIRTUAL ENVIRONMENT ASSISTED DEEP NETWORK TRAINING Ashley S Dale (8771429) 07 January 2021 (has links) <div> <div> <div> <p>An RGBZ synthetic dataset consisting of five object classes in a variety of virtual environments and orientations was combined with a small sample of real-world image data and used to train the Mask R-CNN (MR-CNN) architecture in a variety of configurations. When the MR-CNN architecture was initialized with MS COCO weights and the heads were trained with a mix of synthetic data and real world data, F1 scores improved in four of the five classes: The average maximum F1-score of all classes and all epochs for the networks trained with synthetic data is F1∗ = 0.91, compared to F1 = 0.89 for the networks trained exclusively with real data, and the standard deviation of the maximum mean F1-score for synthetically trained networks is σ∗ <sub>F1 </sub>= 0.015, compared to σF 1 = 0.020 for the networks trained exclusively with real data. Various backgrounds in synthetic data were shown to have negligible impact on F1 scores, opening the door to abstract backgrounds and minimizing the need for intensive synthetic data fabrication. When the MR-CNN architecture was initialized with MS COCO weights and depth data was included in the training data, the net- work was shown to rely heavily on the initial convolutional input to feed features into the network, the image depth channel was shown to influence mask generation, and the image color channels were shown to influence object classification. A set of latent variables for a subset of the synthetic datatset was generated with a Variational Autoencoder then analyzed using Principle Component Analysis and Uniform Manifold Projection and Approximation (UMAP). The UMAP analysis showed no meaningful distinction between real-world and synthetic data, and a small bias towards clustering based on image background. </p></div></div></div> Computer Engineering Software Engineering Applied Computer Science Information Systems Signal Processing Computer Graphics Computer Vision Image Processing Pattern Recognition and Data Mining Simulation and Modelling Virtual Reality and Related Simulation Applied Discrete Mathematics Coding and Information Theory Conceptual Modelling Information Engineering and Theory Machine Learning Mask R-CNN Artificial Intelligence Image Processing 3D Image Multispectral Data Signal Processing CNN DNN Object Detection Threat Detection Virtual Environments Synthetic Dataset F1 score image segmentation methods Image Segmentation RGBD RGBD video RGBZ Algorithms MS COCO Microsoft Common Objects in Context Transfer Learning

Page generated in 0.0135 seconds