Related papers: MTCRNN: A multi-scale RNN for directed audio textu…

Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets. In this paper, we offer contributions in both these areas to enable similar progress in audio…

Noise is one of the primary quality-of-life issues in urban environments. In addition to annoyance, noise negatively impacts public health and educational performance. While low-cost sensors can be deployed to monitor ambient noise levels…

Detecting bird sounds in audio recordings automatically, if accurate enough, is expected to be of great help to the research community working in bio- and ecoacoustics, interested in monitoring biodiversity based on audio field recordings.…

Masked modeling has emerged as a powerful self-supervised learning framework, but existing methods largely rely on random masking, disregarding the structural properties of different modalities. In this work, we introduce structured…

A recent comparative study evaluated all known thunder synthesis techniques in terms of their perceptual realness. The findings concluded that none of the synthesised audio extracts seemed as realistic as the genuine phenomenon. The work…

We present a real-time method for synthesizing highly complex human motions using a novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN). Recently, researchers have attempted to synthesize new motion by using…

In this work, we introduce TexStat, a novel loss function specifically designed for the analysis and synthesis of texture sounds characterized by stochastic structure and perceptual stationarity. Drawing inspiration from the statistical and…

In this paper, a siamese DNN model is proposed to learn the characteristics of the audio dynamic range compressor (DRC). This facilitates an intelligent control system that uses audio examples to configure the DRC, a widely used non-linear…

We conduct a large-scale study of language models for chord prediction. Specifically, we compare N-gram models to various flavours of recurrent neural networks on a comprehensive dataset comprising all publicly available datasets of…

Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS model including RNN components has certain requirements for GPU…

Several studies have been conducted to automatically recognize activities of construction equipment using their generated sound patterns. Most of these studies are focused on single-machine scenarios under controlled environments. However,…

Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…

Presenting real-time rendering of 3D surfaces using radiance textures for fast synthesis of complex incidence-variable effects and environment interactions. This includes iridescence, parallax occlusion and interior mapping, (specular,…

We present TexFusion (Texture Diffusion), a new method to synthesize textures for given 3D geometries, using large-scale text-guided image diffusion models. In contrast to recent works that leverage 2D text-to-image diffusion models to…

Segmenting audio into homogeneous sections such as music and speech helps us understand the content of audio. It is useful as a pre-processing step to index, store, and modify audio recordings, radio broadcasts and TV programmes. Deep…

Deep Neural Networks (DNNs)-based semantic segmentation models trained on a source domain often struggle to generalize to unseen target domains, i.e., a domain gap problem. Texture often contributes to the domain gap, making DNNs vulnerable…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Generating sound effects with controllable variations is a challenging task, traditionally addressed using sophisticated physical models that require in-depth knowledge of signal processing parameters and algorithms. In the era of…

Audio pattern recognition is an important research topic in the machine learning area, and includes several tasks such as audio tagging, acoustic scene classification, music classification, speech emotion classification and sound event…

Auditory models are commonly used as feature extractors for automatic speech-recognition systems or as front-ends for robotics, machine-hearing and hearing-aid applications. Although auditory models can capture the biophysical and nonlinear…