Related papers: Beneath (or beyond) the surface: Discovering voice…

Word embedding is designed to represent the semantic meaning of a word with low dimensional vectors. The state-of-the-art methods of learning word embeddings (word2vec and GloVe) only use the word co-occurrence information. The learned…

Instrumental playing techniques such as vibratos, glissandos, and trills often denote musical expressivity, both in classical and folk contexts. However, most existing approaches to music similarity retrieval fail to describe timbre beyond…

Mechanistic interpretability strives to explain model behavior in terms of bottom-up primitives. The leading paradigm is to express hidden states as a sparse linear combination of basis vectors, called features. However, this only…

The dynamical equations of clarinet-like systems are known to be reducible to a non-linear iterated map within reasonable approximations. This leads to time oscillations that are represented by square signals, analogous to the Raman regime…

We extend the SKIP-GRAM model of Mikolov et al. (2013a) by taking visual information into account. Like SKIP-GRAM, our multimodal models (MMSKIP-GRAM) build vector-based word representations by learning to predict linguistic contexts in…

Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information. In this paper, we propose a model to learn Chinese word embeddings via three-level composition: (1) a…

Chorus detection is a challenging problem in musical signal processing as the chorus often repeats more than once in popular songs, usually with rich instruments and complex rhythm forms. Most of the existing works focus on the…

Multi-layered structures are widely used in the construction of metamaterial devices to realize various cutting-edge waveguide applications. This paper makes several contributions to the mathematical analysis of subwavelength resonances in…

In this paper we present an attentional neural network for folk song classification. We introduce the concept of musical motif embedding, and show how using melodic local context we are able to model monophonic folk song motifs using the…

The enumeration of chemical graphs is an important topic in cheminformatics and bioinformatics, particularly in the discovery of novel drugs. These graphs are typically either tree-like multigraphs or composed of tree-like multigraphs…

We investigate the integration of word embeddings as classification features in the setting of large scale text classification. Such representations have been used in a plethora of tasks, however their application in classification…

We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the…

While deep learning models have demonstrated robust performance in speaker recognition tasks, they primarily rely on low-level audio features learned empirically from spectrograms or raw waveforms. However, prior work has indicated that…

The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder…

Music structure analysis (MSA) methods traditionally search for musically meaningful patterns in audio: homogeneity, repetition, novelty, and segment-length regularity. Hand-crafted audio features such as MFCCs or chromagrams are often used…

Playlists have become a significant part of our listening experience because of the digital cloud-based services such as Spotify, Pandora, Apple Music. Owing to the meteoric rise in the usage of playlists, recommending playlists is crucial…

How to better utilize sequential information has been extensively studied in the setting of recommender systems. To this end, architectural inductive biases such as Markov-Chains, Recurrent models, Convolutional networks and many others…

We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process…

Most robotic grasping systems rely on converting sensor data into explicit 3D point clouds, which is a computational step not found in biological intelligence. This paper explores a fundamentally different, neuro-inspired paradigm for 6-DoF…

Recent advances in the field of network representation learning are mostly attributed to the application of the skip-gram model in the context of graphs. State-of-the-art analogues of skip-gram model in graphs define a notion of…