Related papers: Line Harp: Importance-Driven Sonification for Dens…
The visualization of publication and citation data is popular in bibliometrics. Although less common, the representation of empirical data as sound is an alternative form of presentation (in other fields than bibliometrics). In this…
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The…
Dynamic spectrum sharing approach is a paradigm shift from the conventional static and exclusive approach to spectrum allocation. The existing methodologies to define use of the spectrum and quantify its efficiency are based on the static…
Audiograms are a particular type of line charts representing individuals' hearing level at various frequencies. They are used by audiologists to diagnose hearing loss, and further select and tune appropriate hearing aids for customers.…
Connecting large libraries of digitized audio recordings to their corresponding sheet music images has long been a motivation for researchers to develop new cross-modal retrieval systems. In recent years, retrieval systems based on…
Solid materials may appear static, but at the atomic scale they are in constant vibrational motion. These vibrations, described by phonons, govern many key material properties, including structural stability, mechanical strength, optical…
Recent years have witnessed the emerging success of leveraging syntax graphs for the target sentiment classification task. However, we discover that existing syntax-based models suffer from two issues: noisy information aggregation and loss…
Sparse matrix factorization is a popular tool to obtain interpretable data decompositions, which are also effective to perform data completion or denoising. Its applicability to large datasets has been addressed with online and randomized…
This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding…
In this paper, we study the MUltiple SIgnal Classification (MUSIC) algorithm often used to image small targets when multiple measurement vectors are available. We show that this algorithm may be used when the imaging problem can be cast as…
The task of bandwidth extension addresses the generation of missing high frequencies of audio signals based on knowledge of the low-frequency part of the sound. This task applies to various problems, such as audio coding or audio…
Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing…
Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the…
Digitization of scanned Piping and Instrumentation diagrams(P&ID), widely used in manufacturing or mechanical industries such as oil and gas over several decades, has become a critical bottleneck in dynamic inventory management and creation…
Deep learning techniques have proven highly effective in image classification, but their deployment in resourceconstrained environments remains challenging due to high computational demands. Furthermore, their interpretability is of high…
Multi-instrument Automatic Music Transcription (AMT), or the decoding of a musical recording into semantic musical content, is one of the holy grails of Music Information Retrieval. Current AMT approaches are restricted to piano and (some)…
Intensity mapping is a promising technique for surveying the large scale structure of our Universe from $z=0$ to $z \sim 150$, using the brightness temperature field of spectral lines to directly observe previously unexplored portions of…
Medical image segmentation using deep neural networks has been highly successful. However, the effectiveness of these networks is often limited by inadequate dense prediction and inability to extract robust features. To achieve refined…
The project described in this paper explores the informative sonification of data received in real time from a supercomputer. These data capture the current activities in all the nodes of the computer, therefore, their sonification…
We investigate pruning and quantization for deep neural networks. Our goal is to achieve extremely high sparsity for quantized networks to enable implementation on low cost and low power accelerator hardware. In a practical scenario, there…