English
Related papers

Related papers: Interpreting intermediate convolutional layers of …

200 papers

The learning of interpretable representations from raw data presents significant challenges for time series data like speech. In this work, we propose a relevance weighting scheme that allows the interpretation of the speech representations…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-05 Purvi Agrawal , Sriram Ganapathy

Generative Adversarial Networks (GAN) have demonstrated impressive results in modeling the distribution of natural images, learning latent representations that capture semantic variations in an unsupervised basis. Beyond the generation of…

Computer Vision and Pattern Recognition · Computer Science 2019-11-14 Marcos Pividori , Guillermo L. Grinblat , Lucas C. Uzal

Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive successes on downstream tasks, we still have a limited…

Computation and Language · Computer Science 2023-03-20 Ankita Pasad , Bowen Shi , Karen Livescu

Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Georgii Mikriukov , Gesina Schwalbe , Christian Hellert , Korinna Bade

Deep acoustic models typically receive features in the first layer of the network, and process increasingly abstract representations in the subsequent layers. Here, we propose to feed the input features at multiple depths in the acoustic…

Computation and Language · Computer Science 2020-02-14 Andros Tjandra , Chunxi Liu , Frank Zhang , Xiaohui Zhang , Yongqiang Wang , Gabriel Synnaeve , Satoshi Nakamura , Geoffrey Zweig

The latent space of many generative models are rich in unexplored valleys and mountains. The majority of tools used for exploring them are so far limited to Graphical User Interfaces (GUIs). While specialized hardware can be used for this…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Diego Porres

Convolutional neural networks (CNNs) learn abstract features to perform object classification, but understanding these features remains challenging due to difficult-to-interpret results or high computational costs. We propose an automatic…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Maren H. Wehrheim , Pamela Osuna-Vargas , Matthias Kaschube

Speech emotion recognition is a challenging task and heavily depends on hand-engineered acoustic features, which are typically crafted to echo human perception of speech signals. However, a filter bank that is designed from perceptual…

Sound · Computer Science 2020-07-29 Siddique Latif , Rajib Rana , Sara Khalifa , Raja Jurdak , Julien Epps

Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a…

Computer Vision and Pattern Recognition · Computer Science 2021-11-03 Amil Dravid , Aggelos K. Katsaggelos

This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin…

Machine Learning · Computer Science 2025-10-14 Naman Agrawal

This paper argues that training GANs on local and non-local dependencies in speech data offers insights into how deep neural networks discretize continuous data and how symbolic-like rule-based morphophonological processes emerge in a deep…

Computation and Language · Computer Science 2021-09-14 Gašper Beguš

Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-23 Jian Cong , Shan Yang , Lei Xie , Dan Su

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high…

Computer Vision and Pattern Recognition · Computer Science 2018-02-15 Quanshi Zhang , Ying Nian Wu , Song-Chun Zhu

Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within…

Neural and Evolutionary Computing · Computer Science 2018-01-30 Dario Garcia-Gasulla , Ferran Parés , Armand Vilalta , Jonatan Moreno , Eduard Ayguadé , Jesús Labarta , Ulises Cortés , Toyotaro Suzumura

Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this…

Machine Learning · Computer Science 2025-11-17 Peng Wang , Xiao Li , Can Yaras , Zhihui Zhu , Laura Balzano , Wei Hu , Qing Qu

How can deep neural networks encode information that corresponds to words in human speech into raw acoustic data? This paper proposes two neural network architectures for modeling unsupervised lexical learning from raw acoustic inputs,…

Computation and Language · Computer Science 2021-07-29 Gašper Beguš

We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are extracted from all…

Computer Vision and Pattern Recognition · Computer Science 2016-03-02 Nicolas Ballas , Li Yao , Chris Pal , Aaron Courville

How language models process complex input that requires multiple steps of inference is not well understood. Previous research has shown that information about intermediate values of these inputs can be extracted from the activations of the…

Machine Learning · Computer Science 2023-01-18 Yuta Matsumoto , Benjamin Heinzerling , Masashi Yoshikawa , Kentaro Inui

Compared to earlier multistage frameworks using CNN features, recent end-to-end deep approaches for fine-grained recognition essentially enhance the mid-level learning capability of CNNs. Previous approaches achieve this by introducing an…

Computer Vision and Pattern Recognition · Computer Science 2018-06-13 Yaming Wang , Vlad I. Morariu , Larry S. Davis

This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., explaining knowledge representations hidden in middle conv-layers of the CNN.…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Quanshi Zhang , Yu Yang , Yuchen Liu , Ying Nian Wu , Song-Chun Zhu