Search results for " Speech"
showing 10 items of 519 documents
On the performance of residual block design alternatives in convolutional neural networks for end-to-end audio classification
2019
Residual learning is a recently proposed learning framework to facilitate the training of very deep neural networks. Residual blocks or units are made of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or residual connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers that make up a residual block. While ResNet architectures for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, few w…
Anomalous Sound Detection using unsupervised and semi-supervised autoencoders and gammatone audio representation
2020
Anomalous sound detection (ASD) is, nowadays, one of the topical subjects in machine listening discipline. Unsupervised detection is attracting a lot of interest due to its immediate applicability in many fields. For example, related to industrial processes, the early detection of malfunctions or damage in machines can mean great savings and an improvement in the efficiency of industrial processes. This problem can be solved with an unsupervised ASD solution since industrial machines will not be damaged simply by having this audio data in the training stage. This paper proposes a novel framework based on convolutional autoencoders (both unsupervised and semi-supervised) and a Gammatone-base…
CNN depth analysis with different channel inputs for Acoustic Scene Classification
2019
Acoustic scene classification (ASC) has been approached in the last years using deep learning techniques such as convolutional neural networks or recurrent neural networks. Many state-of-the-art solutions are based on image classification frameworks and, as such, a 2D representation of the audio signal is considered for training these networks. Finding the most suitable audio representation is still a research area of interest. In this paper, different log-Mel representations and combinations are analyzed. Experiments show that the best results are obtained using the harmonic and percussive components plus the difference between left and right stereo channels, (L-R). On the other hand, it i…
Acoustic Scene Classification with Squeeze-Excitation Residual Networks
2020
Acoustic scene classification (ASC) is a problem related to the field of machine listening whose objective is to classify/tag an audio clip in a predefined label describing a scene location (e. g. park, airport, etc.). Many state-of-the-art solutions to ASC incorporate data augmentation techniques and model ensembles. However, considerable improvements can also be achieved only by modifying the architecture of convolutional neural networks (CNNs). In this work we propose two novel squeeze-excitation blocks to improve the accuracy of a CNN-based ASC framework based on residual learning. The main idea of squeeze-excitation blocks is to learn spatial and channel-wise feature maps independently…
A quantum vocal theory of sound
2020
Concepts and formalism from acoustics are often used to exemplify quantum mechanics. Conversely, quantum mechanics could be used to achieve a new perspective on acoustics, as shown by Gabor studies. Here, we focus in particular on the study of human voice, considered as a probe to investigate the world of sounds. We present a theoretical framework that is based on observables of vocal production, and on some measurement apparati that can be used both for analysis and synthesis. In analogy to the description of spin states of a particle, the quantum-mechanical formalism is used to describe the relations between the fundamental states associated with phonetic labels such as phonation, turbule…
Time Difference of Arrival Estimation from Frequency-Sliding Generalized Cross-Correlations Using Convolutional Neural Networks
2020
The interest in deep learning methods for solving traditional signal processing tasks has been steadily growing in the last years. Time delay estimation (TDE) in adverse scenarios is a challenging problem, where classical approaches based on generalized cross-correlations (GCCs) have been widely used for decades. Recently, the frequency-sliding GCC (FS-GCC) was proposed as a novel technique for TDE based on a sub-band analysis of the cross-power spectrum phase, providing a structured two-dimensional representation of the time delay information contained across different frequency bands. Inspired by deep-learning-based image denoising solutions, we propose in this paper the use of convolutio…
Low-Power Audio Keyword Spotting using Tsetlin Machines
2021
The emergence of Artificial Intelligence (AI) driven Keyword Spotting (KWS) technologies has revolutionized human to machine interaction. Yet, the challenge of end-to-end energy efficiency, memory footprint and system complexity of current Neural Network (NN) powered AI-KWS pipelines has remained ever present. This paper evaluates KWS utilizing a learning automata powered machine learning algorithm called the Tsetlin Machine (TM). Through significant reduction in parameter requirements and choosing logic over arithmetic based processing, the TM offers new opportunities for low-power KWS while maintaining high learning efficacy. In this paper we explore a TM based keyword spotting (KWS) pipe…
Hate Speech e messaggi discriminatori: riflessioni internazionalistiche sul caso Casapound c. Facebook
2021
In this intervention the idea is submitted that the interim measures in the case Casapound v. Facebook, by means of which Fb Ireland was ordered by the Rome Tribunal (on December 12, 2019) to reactivate the profile of the extreme right wing political association Casapound - previously closed as a consequence of an alleged violation of fb standards concerning hate speech - can be criticized under international and european law. Such criticisms stem both from the overall picture of the international and european legal standards concerning hate speech (par. 2) and from the relevant case law of the European Court of Human rights (paras. 3 and 4).
Adaptive Distance-Based Pooling in Convolutional Neural Networks for Audio Event Classification
2020
In the last years, deep convolutional neural networks have become a standard for the development of state-of-the-art audio classification systems, taking the lead over traditional approaches based on feature engineering. While they are capable of achieving human performance under certain scenarios, it has been shown that their accuracy is severely degraded when the systems are tested over noisy or weakly segmented events. Although better generalization could be obtained by increasing the size of the training dataset, e.g. by applying data augmentation techniques, this also leads to longer and more complex training procedures. In this article, we propose a new type of pooling layer aimed at …
RECOGNIZABLE PICTURE LANGUAGES
1992
The purpose of this paper is to propose a new notion of recognizability for picture (two-dimensional) languages extending the characterization of one-dimensional recognizable languages in terms of local languages and alphabetic mappings. We first introduce the family of local picture languages (denoted by LOC) and, in particular, prove the undecidability of the emptiness problem. Then we define the new family of recognizable picture languages (denoted by REC). We study some combinatorial and language theoretic properties of REC such as ambiguity, closure properties or undecidability results. Finally we compare the family REC with the classical families of languages recognized by four-way a…