Related papers: Interpreting intermediate convolutional layers of …
Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by…
Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random…
In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a…
Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler…
Recently, convolutional neural networks (CNNs) have been used as a powerful tool to solve many problems of machine learning and computer vision. In this paper, we aim to provide insight on the property of convolutional neural networks, as…
We propose an end-to-end affect recognition approach using a Convolutional Neural Network (CNN) that handles multiple languages, with applications to emotion and personality recognition from speech. We lay the foundation of a universal…
Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…
Traditionally, CNN models possess hierarchical structures and utilize the feature mapping of the last layer to obtain the prediction output. However, it can be difficulty to settle the optimal network depth and make the middle layers learn…
In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior…
This study proposes a fully convolutional network (FCN) model for raw waveform-based speech enhancement. The proposed system performs speech enhancement in an end-to-end (i.e., waveform-in and waveform-out) manner, which dif-fers from most…
The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN, in order…
The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of…
This paper presents an alternate representation framework to commonly used time-frequency representation for acoustic scene classification (ASC). A raw audio signal is represented using a pre-trained convolutional neural network (CNN) using…
This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually learns regional visual patterns in each intermediate layer…
Deep learning is progressively gaining popularity as a viable alternative to i-vectors for speaker recognition. Promising results have been recently obtained with Convolutional Neural Networks (CNNs) when fed by raw speech samples directly.…
Estimating quality of transmitted speech is known to be a non-trivial task. While traditionally, test participants are asked to rate the quality of samples; nowadays, automated methods are available. These methods can be divided into: 1)…
We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features…
Silent Speech Interfaces aim to reconstruct the acoustic signal from a sequence of ultrasound tongue images that records the articulatory movement. The extraction of information about the tongue movement requires us to efficiently process…
We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…
Convolutional neural networks (CNN's) are powerful and widely used tools. However, their interpretability is far from ideal. One such shortcoming is the difficulty of deducing a network's ability to generalize to unseen data. We use…